ref material to use later was very good.

*PAUL BEALES- Seagate Technology.*

Machine Learning courses

Code | Name | Duration | Overview |
---|---|---|---|

systemml | Apache SystemML for Machine Learning | 14 hours | Apache SystemML is a distributed and declarative machine learning platform. SystemML provides declarative large-scale machine learning (ML) that aims at flexible specification of ML algorithms and automatic generation of hybrid runtime plans ranging from single node, in-memory computations, to distributed computations on Apache Hadoop and Apache Spark. Audience This course is suitable for Machine Learning researchers, developers and engineers seeking to utilize SystemML as a framework for machine learning. Running SystemML Standalone Spark MLContext Spark Batch Hadoop Batch JMLC Tools Debugger IDE Troubleshooting Languages and ML Algorithms DML PyDML Algorithms |

predio | Machine Learning with PredictionIO | 21 hours | PredictionIO is an open source Machine Learning Server built on top of state-of-the-art open source stack. Audience This course is directed at developers and data scientists who want to create predictive engines for any machine learning task. Getting Started Quick Intro Installation Guide Downloading Template Deploying an Engine Customizing an Engine App Integration Overview Developing PredictionIO System Architecture Event Server Overview Collecting Data Learning DASE Implementing DASE Evaluation Overview Intellij IDEA Guide Scala API Machine Learning Education and Usage Examples Comics Recommendation Text Classification Community Contributed Demo Dimensionality Reducation and usage PredictionIO SDKs (Select One) Java PHP Python Ruby Community Contributed |

cpb100 | Google Cloud Platform Fundamentals: Big Data & Machine Learning | 8 hours | This one-day instructor-led course introduces participants to the big data capabilities of Google Cloud Platform. Through a combination of presentations, demos, and hands-on labs, participants get an overview of the Google Cloud platform and a detailed view of the data processing and machine learning capabilities. This course showcases the ease, flexibility, and power of big data solutions on Google Cloud Platform. This course teaches participants the following skills: Identify the purpose and value of the key Big Data and Machine Learning products in the Google Cloud Platform. Use Cloud SQL and Cloud Dataproc to migrate existing MySQL and Hadoop/Pig/Spark/Hive workloads to Google Cloud Platform. Employ BigQuery and Cloud Datalab to carry out interactive data analysis. Train and use a neural network using TensorFlow. Employ ML APIs. Choose between different data processing products on the Google Cloud Platform. This class is intended for the following: Data analysts, Data scientists, Business analysts getting started with Google Cloud Platform. Individuals responsible for designing pipelines and architectures for data processing, creating and maintaining machine learning and statistical models, querying datasets, visualizing query results and creating reports. Executives and IT decision makers evaluating Google Cloud Platform for use by data scientists. The course includes presentations, demonstrations, and hands-on labs. Module 1: Introducing Google Cloud Platform Google Platform Fundamentals Overview. Google Cloud Platform Data Products and Technology. Usage scenarios. Lab: Sign up for Google Cloud Platform. Module 2: Compute and Storage Fundamentals CPUs on demand (Compute Engine). A global filesystem (Cloud Storage). CloudShell. Lab: Set up a Ingest-Transform-Publish data processing pipeline. Module 3: Data Analytics on the Cloud Stepping-stones to the cloud. Cloud SQL: your SQL database on the cloud. Lab: Importing data into CloudSQL and running queries. Spark on Dataproc. Lab: Machine Learning Recommendations with SparkML. Module 4: Scaling Data Analysis Fast random access. Datalab. BigQuery. Lab: Build machine learning dataset. Machine Learning with TensorFlow. Lab: Train and use neural network. Fully built models for common needs. Lab: Employ ML APIs Module 5: Data Processing Architectures Message-oriented architectures with Pub/Sub. Creating pipelines with Dataflow. Reference architecture for real-time and batch data processing. Module 6: Summary Why GCP? Where to go from here Additional Resources |

cpde | Data Engineering on Google Cloud Platform | 32 hours | This four-day instructor-led class provides participants a hands-on introduction to designing and building data processing systems on Google Cloud Platform. Through a combination of presentations, demos, and hand-on labs, participants will learn how to design data processing systems, build end-to-end data pipelines, analyze data and carry out machine learning. The course covers structured, unstructured, and streaming data. This course teaches participants the following skills: Design and build data processing systems on Google Cloud Platform Process batch and streaming data by implementing autoscaling data pipelines on Cloud Dataflow Derive business insights from extremely large datasets using Google BigQuery Train, evaluate and predict using machine learning models using Tensorflow and Cloud ML Leverage unstructured data using Spark and ML APIs on Cloud Dataproc Enable instant insights from streaming data This class is intended for experienced developers who are responsible for managing big data transformations including: Extracting, Loading, Transforming, cleaning, and validating data Designing pipelines and architectures for data processing Creating and maintaining machine learning and statistical models Querying datasets, visualizing query results and creating reports The course includes presentations, demonstrations, and hands-on labs. Leveraging Unstructured Data with Cloud Dataproc on Google Cloud Platform Module 1: Google Cloud Dataproc Overview Creating and managing clusters. Leveraging custom machine types and preemptible worker nodes. Scaling and deleting Clusters. Lab: Creating Hadoop Clusters with Google Cloud Dataproc. Module 2: Running Dataproc Jobs Running Pig and Hive jobs. Separation of storage and compute. Lab: Running Hadoop and Spark Jobs with Dataproc. Lab: Submit and monitor jobs. Module 3: Integrating Dataproc with Google Cloud Platform Customize cluster with initialization actions. BigQuery Support. Lab: Leveraging Google Cloud Platform Services. Module 4: Making Sense of Unstructured Data with Google’s Machine Learning APIs Google’s Machine Learning APIs. Common ML Use Cases. Invoking ML APIs. Lab: Adding Machine Learning Capabilities to Big Data Analysis. Serverless Data Analysis with Google BigQuery and Cloud Dataflow Module 5: Serverless data analysis with BigQuery What is BigQuery. Queries and Functions. Lab: Writing queries in BigQuery. Loading data into BigQuery. Exporting data from BigQuery. Lab: Loading and exporting data. Nested and repeated fields. Querying multiple tables. Lab: Complex queries. Performance and pricing. Module 6: Serverless, autoscaling data pipelines with Dataflow The Beam programming model. Data pipelines in Beam Python. Data pipelines in Beam Java. Lab: Writing a Dataflow pipeline. Scalable Big Data processing using Beam. Lab: MapReduce in Dataflow. Incorporating additional data. Lab: Side inputs. Handling stream data. GCP Reference architecture. Serverless Machine Learning with TensorFlow on Google Cloud Platform Module 7: Getting started with Machine Learning What is machine learning (ML). Effective ML: concepts, types. ML datasets: generalization. Lab: Explore and create ML datasets. Module 8: Building ML models with Tensorflow Getting started with TensorFlow. Lab: Using tf.learn. TensorFlow graphs and loops + lab. Lab: Using low-level TensorFlow + early stopping. Monitoring ML training. Lab: Charts and graphs of TensorFlow training. Module 9: Scaling ML models with CloudML Why Cloud ML? Packaging up a TensorFlow model. End-to-end training. Lab: Run a ML model locally and on cloud. Module 10: Feature Engineering Creating good features. Transforming inputs. Synthetic features. Preprocessing with Cloud ML. Lab: Feature engineering. Building Resilient Streaming Systems on Google Cloud Platform Module 11: Architecture of streaming analytics pipelines Stream data processing: Challenges. Handling variable data volumes. Dealing with unordered/late data. Lab: Designing streaming pipeline. Module 12: Ingesting Variable Volumes What is Cloud Pub/Sub? How it works: Topics and Subscriptions. Lab: Simulator. Module 13: Implementing streaming pipelines Challenges in stream processing. Handle late data: watermarks, triggers, accumulation. Lab: Stream data processing pipeline for live traffic data. Module 14: Streaming analytics and dashboards Streaming analytics: from data to decisions. Querying streaming data with BigQuery. What is Google Data Studio? Lab: build a real-time dashboard to visualize processed data. Module 15: High throughput and low-latency with Bigtable What is Cloud Spanner? Designing Bigtable schema. Ingesting into Bigtable. Lab: streaming into Bigtable. |

dmmlr | Data Mining & Machine Learning with R | 14 hours | Introduction to Data mining and Machine Learning Statistical learning vs. Machine learning Iteration and evaluation Bias-Variance trade-off Regression Linear regression Generalizations and Nonlinearity Exercises Classification Bayesian refresher Naive Bayes Dicriminant analysis Logistic regression K-Nearest neighbors Support Vector Machines Neural networks Decision trees Exercises Cross-validation and Resampling Cross-validation approaches Bootstrap Exercises Unsupervised Learning K-means clustering Examples Challenges of unsupervised learning and beyond K-means Advanced topics Ensemble models Mixed models Boosting Examples Multidimensional reduction Factor Analysis Principal Component Analysis Examples |

mchdeeplearn | Introduction à l’intelligence artificielle : outils et enjeux | 14 hours | L’intelligence artificielle, après avoir bouleversé de nombreux domaines scientifiques, a commencé à révolutionner un grand nombre de secteurs économiques (industrie, médecine, communication, etc.). Néanmoins, sa présentation dans les grands media relève souvent du fantasme, très éloignée de ce que sont réellement les domaines du Machine Learning ou du Deep Learning. L’objet de cette formation est de présenter réellement ces approches et ce qu’elles apportent dans la résolution de problèmes considérés comme « intelligents ». Un grand nombre d’applications sont présentées, du traitement de donnée brute à la création de contenus « originaux » en passant par le contrôle d’agents, la classification automatisée ou l’approximation d’une donnée pour faciliter sa compréhension et sa manipulation. Enfin, un axe important est celui de l’opportunité comme de la méthodologie de mise en œuvre de tels projets. Le Deep Learning connaît comme tout outil de nombreuses limites, et son application suppose une réelle méthode pour comprendre, contrôler et garantir un résultat final de qualité. Le cours est séparé en deux journées distinctes, quand bien même la première journée peut faire l’objet d’une formation unique limitée. Jour 1 - Intelligence artificielle : concepts et exemples 1. Qu’est-ce que l’intelligence artificielle (jusqu’aux réseaux de neurones) ? - Le fantasme de l’intelligence artificielle et la réalité d’aujourd’hui. - Tâche intellectuelle VS algorithmes - Types de tâches : supervised learning, unsupervised learning, reinforcement learning - Types d’actions : classification, régression, clustering, estimation de densité, réduction de dimensionalité - Intelligence collective : agréger une connaissance partagée par de nombreux agents virtuels - Algorithmes génétiques : faire évoluer une population d’agents virtuels par sélection - Machine learning : présentation et principaux algorithmes (XGBoost, Random Forest) 2. Réseaux de neurones et Deep Learning - Qu’est-ce qu’un réseau de neurones ? Présentation d’un neurone et de couches de neurones logiques - Qu’est-ce que l’apprentissage d’un réseau de neurones ? Deep VS shallow network, overfit, underfit, convergence. - Approximer une fonction par un réseau de neurones : présentation et exemples - Approximer une distribution par un réseau de neurones : présentation et exemples - Génération de représentations internes au sein d’un réseau de neurones - Généralisation des résultats d’un réseau de neurones. - Révolution du Deep Learning : généricité des outils et des problématiques 3. Applications Deep Learning - Classification de données o Comprendre ce qu’est la classification de données dans différents scénarios : donnée brute, image, son, texte, etc. Comprendre les enjeux d’une classification de données et les choix impliqués par un modèle de classification. o Présentation des outils usuels de classification et notamment des réseaux de type MLP (Multilayer perceptron) ou CNN (Convolutional neural network) VS outils de Machine Learnig (Random Forest, Naïve bayes) o Présentation d’exemples de solutions existantes (par exemple : classification d’images médicales, d’historique client, de textes rédigés par des utilisateurs, etc.) o Clustering : cas particulier d’apprentissage non supervisé. - Prédiction d’information et donnée séquentielle/temporelle o Enjeux et limite d’une prédiction d’information. Recherche de règles structurelles au sein de la donnée pouvant permettre une logique de prédiction. o La prédiction comme une classification ou une régression o Présentation des outils usuels de prédiction : RNN (Recurrent Neural Networks), LSTM (Long Short Term Memory) ou côté Machine Learning, ARIMA o Exemples : prévision des images suivant une séquence vidéo. Prédiction de pollution atmosphérique en milieu urbain, ou autres. - Transformation / Génération de données o Qu’est-ce que transformer une donnée exactement ? Quelles barrières, quels enjeux. o Opération de ré-interprétation d’une même donnée : dé-bruitage, génération de résumés textuels, segmentation d’image o Opération de transformation sur un même format : traduction de texte d’une langue à une autre (présentation sommaire de l’architecture Google Machine Translation), super-résolution o Opération de génération de donnée « originale » : neural Style, super-résolution, génération d’images à partir de présentations textuelles - Reinforcement Learning : contrôle d’un environnement o Présentation du Deep Reinforcement Learning o Experience Replay et apprentissage de jeux vidéo par un réseau de neurones o Applications : contrôle de simulations numériques, voiture automatique, robotique Jour 2 - Outils et mise en œuvre d’un projet IA Deux sujets «types » sont choisis avec les élèves afin d’appliquer l’ensemble des principes décrits pendant cette journée à ces cas d’étude. 4. Quels problèmes peut-on adresser avec Machine/Deep Learning ? - Condition sur les données : volumétries, dimensionnement, équilibre entre les classes, description. (Curse of dimensionality, No Free Lunch theorem) - Donnée brute VS features travaillées : que choisir ? - Machine Learning VS Deep Learning : quand préférer les algorithmes plus anciens du Machine Learning aux réseaux de neurones ? - Qualifier le problème : unsupervised learning ? Supervised learning ? - Qualifier la solution d’un problème : comprendre la distance entre une affirmation et le résultat d’un algorithme. 5. Mise en œuvre d’un projet, étape 1 : générer un Dataset - Qu’est-ce qu’un Dataset ? Qu’est-ce qui le sépare une base de données usuelle ? - Accumuler et contrôler la donnée : surveiller les biais, nettoyer ou convertir la donnée sans s’interdire de retours en arrière. - Comprendre la donnée : représentation de quelques outils statistiques permettant une première vision d’une donnée, sa distribution, ses comportements aberrants... - Formater une donnée : décider d’un format d’entrée et de sortie, faire le lien avec la qualification du problème - Préparer la donnée : définition des train set, validation set et test set. Mettre en place une structure permettant de garantir que les algorithmes utilisés sont réellement pertinents (ou non) 6. Mise en œuvre d’un projet, étape 2 : itérations successives - Méthodologie pour avancer dans la recherche d’une meilleure solution à un problème ML/DL - Choix d’une direction de recherche, localisation de publications ou de projets similaires existants - Itérations successives depuis les algorithmes les plus simples jusqu’aux architectures les plus complexes - Conservation d’un banc de comparaison transversal - Grouper et balancer un ensemble de solutions pour obtenir une solution optimale 7. Mise en œuvre d’un projet, étape 3 : industrialisation - Quels outils existent aujourd’hui ? Quels outils pour la recherche et quels outils pour l’industrie ? De Keras/Lasagne à Caffe en passant par Torch, Theano, Tensorflow ou Apache Spark ou Hadoop - Industrialiser un réseau de neurones par un encadrement strict de son processus et un monitoring continu - Mise en place de réapprentissages successifs pour conserver un réseau à jour et optimal - Former des utilisateurs à la compréhension du réseau et à sa bonne utilisation. |

mlfsas | Machine Learning Fundamentals with Scala and Apache Spark | 14 hours | The aim of this course is to provide a basic proficiency in applying Machine Learning methods in practice. Through the use of the Scala programming language and its various libraries, and based on a multitude of practical examples this course teaches how to use the most important building blocks of Machine Learning, how to make data modeling decisions, interpret the outputs of the algorithms and validate the results. Our goal is to give you the skills to understand and use the most fundamental tools from the Machine Learning toolbox confidently and avoid the common pitfalls of Data Sciences applications. Introduction to Applied Machine Learning Statistical learning vs. Machine learning Iteration and evaluation Bias-Variance trade-off Machine Learning with Python Choice of libraries Add-on tools Regression Linear regression Generalizations and Nonlinearity Exercises Classification Bayesian refresher Naive Bayes Logistic regression K-Nearest neighbors Exercises Cross-validation and Resampling Cross-validation approaches Bootstrap Exercises Unsupervised Learning K-means clustering Examples Challenges of unsupervised learning and beyond K-means |

intrdplrngrsneuing | Introduction Deep Learning & Neural Networks for Engineers | 21 hours | Artificial intelligence has revolutionized a large number of economic sectors (industry, medicine, communication, etc.) after having upset many scientific fields. Nevertheless, his presentation in the major media is often a fantasy, far removed from what really are the fields of Machine Learning or Deep Learning. The aim of this course is to provide engineers who already have a master's degree in computer tools (including a software programming base) an introduction to Deep Learning as well as to its various fields of specialization and therefore to the main existing network architectures today. If the mathematical bases are recalled during the course, a level of mathematics of type BAC + 2 is recommended for more comfort. It is absolutely possible to ignore the mathematical axis in order to maintain only a "system" vision, but this approach will greatly limit your understanding of the subject. The course is divided into three separate days, the third being optional. Day 1 - Machine Learning & Deep Learning: theoretical concepts 1. Introduction IA, Machine Learning & Deep Learning - History, basic concepts and usual applications of artificial intelligence far Of the fantasies carried by this domain - Collective Intelligence: aggregating knowledge shared by many virtual agents - Genetic algorithms: to evolve a population of virtual agents by selection - Usual Learning Machine: definition. - Types of tasks: supervised learning, unsupervised learning, reinforcement learning - Types of actions: classification, regression, clustering, density estimation, reduction of dimensionality - Examples of Machine Learning algorithms: Linear regression, Naive Bayes, Random Tree - Machine learning VS Deep Learning: problems on which Machine Learning remains Today the state of the art (Random Forests & XGBoosts) 2. Basic Concepts of a Neural Network (Application: multi-layer perceptron) - Reminder of mathematical bases. - Definition of a network of neurons: classical architecture, activation and Weighting of previous activations, depth of a network - Definition of the learning of a network of neurons: functions of cost, back-propagation, Stochastic gradient descent, maximum likelihood. - Modeling of a neural network: modeling input and output data according to The type of problem (regression, classification ...). Curse of dimensionality. Distinction between Multi-feature data and signal. Choice of a cost function according to the data. - Approximation of a function by a network of neurons: presentation and examples - Approximation of a distribution by a network of neurons: presentation and examples - Data Augmentation: how to balance a dataset - Generalization of the results of a network of neurons. - Initialization and regularization of a neural network: L1 / L2 regularization, Batch Normalization ... - Optimization and convergence algorithms. 3. Standard ML / DL Tools A simple presentation with advantages, disadvantages, position in the ecosystem and use is planned. - Data management tools: Apache Spark, Apache Hadoop - Tools Machine Learning: Numpy, Scipy, Sci-kit - DL high level frameworks: PyTorch, Keras, Lasagne - Low level DL frameworks: Theano, Torch, Caffe, Tensorflow Day 2 - Convolutional and Recurrent Networks 4. Convolutional Neural Networks (CNN). - Presentation of the CNNs: fundamental principles and applications - Basic operation of a CNN: convolutional layer, use of a kernel, Padding & stride, feature map generation, pooling layers. Extensions 1D, 2D and 3D. - Presentation of the different CNN architectures that brought the state of the art in classification Images: LeNet, VGG Networks, Network in Network, Inception, Resnet. Presentation of Innovations brought about by each architecture and their more global applications (Convolution 1x1 or residual connections) - Use of an attention model. - Application to a common classification case (text or image) - CNNs for generation: super-resolution, pixel-to-pixel segmentation. Presentation of Main strategies for increasing feature maps for image generation. 5. Recurrent Neural Networks (RNN). - Presentation of RNNs: fundamental principles and applications. - Basic operation of the RNN: hidden activation, back propagation through time, Unfolded version. - Evolutions towards the Gated Recurrent Units (GRUs) and LSTM (Long Short Term Memory). Presentation of the different states and the evolutions brought by these architectures - Convergence and vanising gradient problems - Classical architectures: Prediction of a temporal series, classification ... - RNN Encoder Decoder type architecture. Use of an attention model. - NLP applications: word / character encoding, translation. - Video Applications: prediction of the next generated image of a video sequence. Day 3 - Generational Models and Reinforcement Learning 6. Generational models: Variational AutoEncoder (VAE) and Generative Adversarial Networks (GAN). - Presentation of the generational models, link with the CNNs seen in day 2 - Auto-encoder: reduction of dimensionality and limited generation - Variational Auto-encoder: generational model and approximation of the distribution of a given. Definition and use of latent space. Reparameterization trick. Applications and Limits observed - Generative Adversarial Networks: Fundamentals. Dual Network Architecture (Generator and discriminator) with alternate learning, cost functions available. - Convergence of a GAN and difficulties encountered. - Improved convergence: Wasserstein GAN, Began. Earth Moving Distance. - Applications for the generation of images or photographs, text generation, super- resolution. 7. Deep Reinforcement Learning. - Presentation of reinforcement learning: control of an agent in a defined environment By a state and possible actions - Use of a neural network to approximate the state function - Deep Q Learning: experience replay, and application to the control of a video game. - Optimization of learning policy. On-policy && off-policy. Actor critic architecture. A3C. - Applications: control of a single video game or a digital system. |

dladv | Advanced Deep Learning | 28 hours | Machine Learning Limitations Machine Learning, Non-linear mappings Neural Networks Non-Linear Optimization, Stochastic/MiniBatch Gradient Decent Back Propagation Deep Sparse Coding Sparse Autoencoders (SAE) Convolutional Neural Networks (CNNs) Successes: Descriptor Matching Stereo-based Obstacle Avoidance for Robotics Pooling and invariance Visualization/Deconvolutional Networks Recurrent Neural Networks (RNNs) and their optimizaiton Applications to NLP RNNs continued, Hessian-Free Optimization Language analysis: word/sentence vectors, parsing, sentiment analysis, etc. Probabilistic Graphical Models Hopfield Nets, Boltzmann machines, Restricted Boltzmann Machines Hopfield Networks, (Restricted) Bolzmann Machines Deep Belief Nets, Stacked RBMs Applications to NLP , Pose and Activity Recognition in Videos Recent Advances Large-Scale Learning Neural Turing Machines |

opennmt | OpenNMT: Setting up a Neural Machine Translation system | 7 hours | OpenNMT is a full-featured, open-source (MIT) neural machine translation system that utilizes the Torch mathematical toolkit. In this training participants will learn how to set up and use OpenNMT to carry out translation of various sample data sets. The course starts with an overview of neural networks as they apply to machine translation. Participants will carry out live exercises throughout the course to demonstrate their understanding of the concepts learned and get feedback from the instructor. By the end of this training, participants will have the knowledge and practice needed to implement a live OpenNMT solution. Source and target language samples will be pre-arranged per the audience's requirements. Audience Translation and localization engineers Machine translation specialists and managers Format of the course Part lecture, part discussion, heavy hands-on practice Introduction Why Neural Machine Translation? Overview of the Torch project Installation and setup Preprocessing your data Training the model Translating Using pre-trained models Working with Lua scripts Using extensions Troubleshooting Joining the community Closing remarks |

mlintro | Introduction to Machine Learning | 7 hours | This training course is for people that would like to apply basic Machine Learning techniques in practical applications. Audience Data scientists and statisticians that have some familiarity with machine learning and know how to program R. The emphasis of this course is on the practical aspects of data/model preparation, execution, post hoc analysis and visualization. The purpose is to give a practical introduction to machine learning to participants interested in applying the methods at work Sector specific examples are used to make the training relevant to the audience. Naive Bayes Multinomial models Bayesian categorical data analysis Discriminant analysis Linear regression Logistic regression GLM EM Algorithm Mixed Models Additive Models Classification KNN Ridge regression Clustering |

mlentre | Machine Learning Concepts for Entrepreneurs and Managers | 21 hours | This training course is for people that would like to apply Machine Learning in practical applications for their team. The training will not dive into technicalities and revolve around basic concepts and business/operational applications of the same. Target Audience Investors and AI entrepreneurs Managers and Engineers whose company is venturing into AI space Business Analysts & Investors Introduction to Neural Networks Introduction to Applied Machine Learning Statistical learning vs. Machine learning Iteration and evaluation Bias-Variance trade-off Machine Learning with Python Choice of libraries Add-on tools Machine learning Concepts and Applications Regression Linear regression Generalizations and Nonlinearity Use cases Classification Bayesian refresher Naive Bayes Logistic regression K-Nearest neighbors Use Cases Cross-validation and Resampling Cross-validation approaches Bootstrap Use Cases Unsupervised Learning K-means clustering Examples Challenges of unsupervised learning and beyond K-means Short Introduction to NLP methods word and sentence tokenization text classification sentiment analysis spelling correction information extraction parsing meaning extraction question answering Artificial Intelligence & Deep Learning Technical Overview R v/s Python Caffe v/s Tensor Flow Various Machine Learning Libraries |

appliedml | Applied Machine Learning | 14 hours | This training course is for people that would like to apply Machine Learning in practical applications. Audience This course is for data scientists and statisticians that have some familiarity with statistics and know how to program R (or Python or other chosen language). The emphasis of this course is on the practical aspects of data/model preparation, execution, post hoc analysis and visualization. The purpose is to give practical applications to Machine Learning to participants interested in applying the methods at work. Sector specific examples are used to make the training relevant to the audience. Naive Bayes Multinomial models Bayesian categorical data analysis Discriminant analysis Linear regression Logistic regression GLM EM Algorithm Mixed Models Additive Models Classification KNN Bayesian Graphical Models Factor Analysis (FA) Principal Component Analysis (PCA) Independent Component Analysis (ICA) Support Vector Machines (SVM) for regression and classification Boosting Ensemble models Neural networks Hidden Markov Models (HMM) Space State Models Clustering |

octnp | Octave not only for programmers | 21 hours | Course is dedicated for those who would like to know an alternative program to the commercial MATLAB package. The three-day training provides comprehensive information on moving around the environment and performing the OCTAVE package for data analysis and engineering calculations. The training recipients are beginners but also those who know the program and would like to systematize their knowledge and improve their skills. Knowledge of other programming languages is not required, but it will greatly facilitate the learners' acquisition of knowledge. The course will show you how to use the program in many practical examples. Introduction Simple calculations Starting Octave, Octave as a calculator, built-in functions The Octave environment Named variables, numbers and formatting, number representation and accuracy, loading and saving data Arrays and vectors Extracting elements from a vector, vector maths Plotting graphs Improving the presentation, multiple graphs and figures, saving and printing figures Octave programming I: Script files Creating and editing a script, running and debugging scripts, Control statements If else, switch, for, while Octave programming II: Functions Matrices and vectors Matrix, the transpose operator, matrix creation functions, building composite matrices, matrices as tables, extracting bits of matrices, basic matrix functions Linear and Nonlinear Equations More graphs Putting several graphs in one window, 3D plots, changing the viewpoint, plotting surfaces, images and movies, Eigenvectors and the Singular Value Decomposition Complex numbers Plotting complex numbers, Statistics and data processing GUI Developmen |

mldt | Machine Learning and Deep Learning | 21 hours | This course covers AI (emphasizing Machine Learning and Deep Learning) Machine learning Introduction to Machine Learning Applications of machine learning Supervised Versus Unsupervised Learning Machine Learning Algorithms Regression Classification Clustering Recommender System Anomaly Detection Reinforcement Learning Regression Simple & Multiple Regression Least Square Method Estimating the Coefficients Assessing the Accuracy of the Coefficient Estimates Assessing the Accuracy of the Model Post Estimation Analysis Other Considerations in the Regression Models Qualitative Predictors Extensions of the Linear Models Potential Problems Bias-variance trade off [under-fitting/over-fitting] for regression models Resampling Methods Cross-Validation The Validation Set Approach Leave-One-Out Cross-Validation k-Fold Cross-Validation Bias-Variance Trade-Off for k-Fold The Bootstrap Model Selection and Regularization Subset Selection [Best Subset Selection, Stepwise Selection, Choosing the Optimal Model] Shrinkage Methods/ Regularization [Ridge Regression, Lasso & Elastic Net] Selecting the Tuning Parameter Dimension Reduction Methods Principal Components Regression Partial Least Squares Classification Logistic Regression The Logistic Model cost function Estimating the Coefficients Making Predictions Odds Ratio Performance Evaluation Matrices [Sensitivity/Specificity/PPV/NPV, Precision, ROC curve etc.] Multiple Logistic Regression Logistic Regression for >2 Response Classes Regularized Logistic Regression Linear Discriminant Analysis Using Bayes’ Theorem for Classification Linear Discriminant Analysis for p=1 Linear Discriminant Analysis for p >1 Quadratic Discriminant Analysis K-Nearest Neighbors Classification with Non-linear Decision Boundaries Support Vector Machines Optimization Objective The Maximal Margin Classifier Kernels One-Versus-One Classification One-Versus-All Classification Comparison of Classification Methods Introduction to Deep Learning ANN Structure Biological neurons and artificial neurons Non-linear Hypothesis Model Representation Examples & Intuitions Transfer Function/ Activation Functions Typical classes of network architectures Feed forward ANN. Structures of Multi-layer feed forward networks Back propagation algorithm Back propagation - training and convergence Functional approximation with back propagation Practical and design issues of back propagation learning Deep Learning Artificial Intelligence & Deep Learning Softmax Regression Self-Taught Learning Deep Networks Demos and Applications Lab: Getting Started with R Introduction to R Basic Commands & Libraries Data Manipulation Importing & Exporting data Graphical and Numerical Summaries Writing functions Regression Simple & Multiple Linear Regression Interaction Terms Non-linear Transformations Dummy variable regression Cross-Validation and the Bootstrap Subset selection methods Penalization [Ridge, Lasso, Elastic Net] Classification Logistic Regression, LDA, QDA, and KNN, Resampling & Regularization Support Vector Machine Resampling & Regularization Note: For ML algorithms, case studies will be used to discuss their application, advantages & potential issues. Analysis of different data sets will be performed using R |

BigData_ | A practical introduction to Data Analysis and Big Data | 28 hours | Participants who complete this training will gain a practical, real-world understanding of Big Data and its related technologies, methodologies and tools. Participants will have the opportunity to put this knowledge into practice through hands-on exercises. Group interaction and instructor feedback make up an important component of the class. The course starts with an introduction to elemental concepts of Big Data, then progresses into the programming languages and methodologies used to perform Data Analysis. Finally, we discuss the tools and infrastructure that enable Big Data storage, Distributed Processing, and Scalability. Audience Developers / programmers IT consultants Format of the course Part lecture, part discussion, heavy hands-on practice and implementation, occasional quizing to measure progress. Introduction to Data Analysis and Big Data What makes Big Data "big"? Velocity, Volume, Variety, Veracity (VVVV) Limits to traditional Data Processing Distributed Processing Statistical Analysis Types of Machine Learning Analysis Data Visualization Languages used for Data Analysis R language (crash course) Why R for Data Analysis? Data manipulation, calculation and graphical display Python (crash course) Why Python for Data Analysis? Manipulating, processing, cleaning, and crunching data Approaches to Data Analysis Statistical Analysis Time Series analysis Forecasting with Correlation and Regression models Inferential Statistics (estimating) Descriptive Statistics in Big Data sets (e.g. calculating mean) Machine Learning Supervised vs unsupervised learning Classification and clustering Estimating cost of specific methods Filtering Natural Language Processing Processing text Understaing meaning of the text Automatic text generation Sentiment/Topic Analysis Computer Vision Acquiring, processing, analyzing, and understanding images Reconstructing, interpreting and understanding 3D scenes Using image data to make decisions Big Data infrastructure Data Storage Relational databases (SQL) MySQL Postgres Oracle Non-relational databases (NoSQL) Cassandra MongoDB Neo4js Understanding the nuances Hierarchical databases Object-oriented databases Document-oriented databases Graph-oriented databases Other Distributed Processing Hadoop HDFS as a distributed filesystem MapReduce for distributed processing Spark All-in-one in-memory cluster computing framework for large-scale data processing Structured streaming Spark SQL Machine Learning libraries: MLlib Graph processing with GraphX Search Engines ElasticSearch Solr Scalability Public cloud AWS, Google, Aliyun, etc. Private cloud OpenStack, Cloud Foundry, etc. Auto-scalability Choosing right solution for the problem The future of Big Data Closing remarks |

mlfunpython | Machine Learning Fundamentals with Python | 14 hours | The aim of this course is to provide a basic proficiency in applying Machine Learning methods in practice. Through the use of the Python programming language and its various libraries, and based on a multitude of practical examples this course teaches how to use the most important building blocks of Machine Learning, how to make data modeling decisions, interpret the outputs of the algorithms and validate the results. Our goal is to give you the skills to understand and use the most fundamental tools from the Machine Learning toolbox confidently and avoid the common pitfalls of Data Sciences applications. Introduction to Applied Machine Learning Statistical learning vs. Machine learning Iteration and evaluation Bias-Variance trade-off Machine Learning with Python Choice of libraries Add-on tools Regression Linear regression Generalizations and Nonlinearity Exercises Classification Bayesian refresher Naive Bayes Logistic regression K-Nearest neighbors Exercises Cross-validation and Resampling Cross-validation approaches Bootstrap Exercises Unsupervised Learning K-means clustering Examples Challenges of unsupervised learning and beyond K-means |

OpenNN | OpenNN: Implementing neural networks | 14 hours | OpenNN is an open-source class library written in C++ which implements neural networks, for use in machine learning. In this course we go over the principles of neural networks and use OpenNN to implement a sample application. Audience Software developers and programmers wishing to create Deep Learning applications. Format of the course Lecture and discussion coupled with hands-on exercises. Introduction to OpenNN, Machine Learning and Deep Learning Downloading OpenNN Working with Neural Designer Using Neural Designer for descriptive, diagnostic, predictive and prescriptive analytics OpenNN architecture CPU parallelization OpenNN classes Data set, neural network, loss index, training strategy, model selection, testing analysis Vector and matrix templates Building a neural network application Choosing a suitable neural network Formulating the variational problem (loss index) Solving the reduced function optimization problem (training strategy) Working with datasets The data matrix (columns as variables and rows as instances) Learning tasks Function regression Pattern recognition Compiling with QT Creator Integrating, testing and debugging your application The future of neural networks and OpenNN |

MLFWR1 | Machine Learning Fundamentals with R | 14 hours | The aim of this course is to provide a basic proficiency in applying Machine Learning methods in practice. Through the use of the R programming platform and its various libraries, and based on a multitude of practical examples this course teaches how to use the most important building blocks of Machine Learning, how to make data modeling decisions, interpret the outputs of the algorithms and validate the results. Our goal is to give you the skills to understand and use the most fundamental tools from the Machine Learning toolbox confidently and avoid the common pitfalls of Data Sciences applications. Introduction to Applied Machine Learning Statistical learning vs. Machine learning Iteration and evaluation Bias-Variance trade-off Regression Linear regression Generalizations and Nonlinearity Exercises Classification Bayesian refresher Naive Bayes Logistic regression K-Nearest neighbors Exercises Cross-validation and Resampling Cross-validation approaches Bootstrap Exercises Unsupervised Learning K-means clustering Examples Challenges of unsupervised learning and beyond K-means |

Torch | Torch: Getting started with Machine and Deep Learning | 21 hours | Torch is an open source machine learning library and a scientific computing framework based on the Lua programming language. It provides a development environment for numerics, machine learning, and computer vision, with a particular emphasis on deep learning and convolutional nets. It is one of the fastest and most flexible frameworks for Machine and Deep Learning and is used by companies such as Facebook, Google, Twitter, NVIDIA, AMD, Intel, and many others. In this course we cover the principles of Torch, its unique features, and how it can be applied in real-world applications. We step through numerous hands-on exercises all throughout, demonstrating and practicing the concepts learned. By the end of the course, participants will have a thorough understanding of Torch's underlying features and capabilities as well as its role and contribution within the AI space compared to other frameworks and libraries. Participants will have also received the necessary practice to implement Torch in their own projects. Audience Software developers and programmers wishing to enable Machine and Deep Learning within their applications Format of the course Overview of Machine and Deep Learning In-class coding and integration exercises Test questions sprinkled along the way to check understanding Introduction to Torch Like NumPy but with CPU and GPU implementation Torch's usage in machine learning, computer vision, signal processing, parallel processing, image, video, audio and networking Installing Torch Linux, Windows, Mac Bitmapi and Docker Installing Torch packages Using the LuaRocks package manager Choosing an IDE for Torch ZeroBrane Studio Eclipse plugin for Lua Working with the Lua scripting language and LuaJIT Lua's integration with C/C++ Lua syntax: datatypes, loops and conditionals, functions, functions, tables, and file i/o. Object orientation and serialization in Torch Coding exercise Loading a dataset in Torch MNIST CIFAR-10, CIFAR-100 Imagenet Machine Learning in Torch Deep Learning Manual feature extraction vs convolutional networks Supervised and Unsupervised Learning Building a neural network with Torch N-dimensional arrays Image analysis with Torch Image package The Tensor library Working with the REPL interpreter Working with databases Networking and Torch GPU support in Torch Integrating Torch C, Python, and others Embedding Torch iOS and Android Other frameworks and libraries Facebook's optimized deep-learning modules and containers Creating your own package Testing and debugging Releasing your application The future of AI and Torch |

annmldt | Artificial Neural Networks, Machine Learning, Deep Thinking | 21 hours | DAY 1 - ARTIFICIAL NEURAL NETWORKS Introduction and ANN Structure. Biological neurons and artificial neurons. Model of an ANN. Activation functions used in ANNs. Typical classes of network architectures . Mathematical Foundations and Learning mechanisms. Re-visiting vector and matrix algebra. State-space concepts. Concepts of optimization. Error-correction learning. Memory-based learning. Hebbian learning. Competitive learning. Single layer perceptrons. Structure and learning of perceptrons. Pattern classifier - introduction and Bayes' classifiers. Perceptron as a pattern classifier. Perceptron convergence. Limitations of a perceptrons. Feedforward ANN. Structures of Multi-layer feedforward networks. Back propagation algorithm. Back propagation - training and convergence. Functional approximation with back propagation. Practical and design issues of back propagation learning. Radial Basis Function Networks. Pattern separability and interpolation. Regularization Theory. Regularization and RBF networks. RBF network design and training. Approximation properties of RBF. Competitive Learning and Self organizing ANN. General clustering procedures. Learning Vector Quantization (LVQ). Competitive learning algorithms and architectures. Self organizing feature maps. Properties of feature maps. Fuzzy Neural Networks. Neuro-fuzzy systems. Background of fuzzy sets and logic. Design of fuzzy stems. Design of fuzzy ANNs. Applications A few examples of Neural Network applications, their advantages and problems will be discussed. DAY -2 MACHINE LEARNING The PAC Learning Framework Guarantees for finite hypothesis set – consistent case Guarantees for finite hypothesis set – inconsistent case Generalities Deterministic cv. Stochastic scenarios Bayes error noise Estimation and approximation errors Model selection Radmeacher Complexity and VC – Dimension Bias - Variance tradeoff Regularisation Over-fitting Validation Support Vector Machines Kriging (Gaussian Process regression) PCA and Kernel PCA Self Organisation Maps (SOM) Kernel induced vector space Mercer Kernels and Kernel - induced similarity metrics Reinforcement Learning DAY 3 - DEEP LEARNING This will be taught in relation to the topics covered on Day 1 and Day 2 Logistic and Softmax Regression Sparse Autoencoders Vectorization, PCA and Whitening Self-Taught Learning Deep Networks Linear Decoders Convolution and Pooling Sparse Coding Independent Component Analysis Canonical Correlation Analysis Demos and Applications |

patternmatching | Pattern Matching | 14 hours | Pattern Matching is a technique used to locate specified patterns within an image. It can be used to determine the existence of specified characteristics within a captured image, for example the expected label on a defective product in a factory line or the specified dimensions of a component. It is different from "Pattern Recognition" (which recognizes general patterns based on larger collections of related samples) in that it specifically dictates what we are looking for, then tells us whether the expected pattern exists or not. Audience Engineers and developers seeking to develop machine vision applications Manufacturing engineers, technicians and managers Format of the course This course introduces the approaches, technologies and algorithms used in the field of pattern matching as it applies to Machine Vision. Introduction Computer Vision Machine Vision Pattern Matching vs Pattern Recognition Alignment Features of the target object Points of reference on the object Determining position Determining orientation Gauging Setting tolerance levels Measuring lengths, diameters, angles, and other dimensions Rejecting a component Inspection Detecting flaws Adjusting the system Closing remarks |

aiintrozero | From Zero to AI | 35 hours | This course is created for people who have no previous experience in probability and statistics. Probability (3.5h) Definition of probability Binomial distribution Everyday usage exercises Statistics (10.5h) Descriptive Statistics Inferential Statistics Regression Logistic Regression Exercises Intro to programming (3.5h) Procedural Programming Functional Programming OOP Programming Exercises (writing logic for a game of choice, e.g. noughts and crosses) Machine Learning (10.5h) Classification Clustering Neural Networks Exercises (write AI for a computer game of choice) Rules Engines and Expert Systems (7 hours) Intro to Rule Engines Write AI for the same game and combine solutions into hybrid approach |

datamodeling | Pattern Recognition | 35 hours | This course provides an introduction into the field of pattern recognition and machine learning. It touches on practical applications in statistics, computer science, signal processing, computer vision, data mining, and bioinformatics. The course is interactive and includes plenty of hands-on exercises, instructor feedback, and testing of knowledge and skills acquired. Audience Data analysts PhD students, researchers and practitioners Introduction Probability theory, model selection, decision and information theory Probability distributions Linear models for regression and classification Neural networks Kernel methods Sparse kernel machines Graphical models Mixture models and EM Approximate inference Sampling methods Continuous latent variables Sequential data Combining models |

mlrobot1 | Machine Learning for Robotics | 21 hours | This course introduce machine learning methods in robotics applications. It is a broad overview of existing methods, motivations and main ideas in the context of pattern recognition. After short theoretical background, participants will perform simple exercise using open source (usually R) or any other popular software. Regression Probabilistic Graphical Models Boosting Kernel Methods Gaussian Processes Evaluation and Model Selection Sampling Methods Clustering CRFs Random Forests IVMs |

Neuralnettf | Neural Networks Fundamentals using TensorFlow as Example | 28 hours | This course will give you knowledge in neural networks and generally in machine learning algorithm, deep learning (algorithms and applications). This training is more focus on fundamentals, but will help you choosing the right technology : TensorFlow, Caffe, Teano, DeepDrive, Keras, etc. The examples are made in TensorFlow. TensorFlow Basics Creation, Initializing, Saving, and Restoring TensorFlow variables Feeding, Reading and Preloading TensorFlow Data How to use TensorFlow infrastructure to train models at scale Visualizing and Evaluating models with TensorBoard TensorFlow Mechanics Inputs and Placeholders Build the GraphS Inference Loss Training Train the Model The Graph The Session Train Loop Evaluate the Model Build the Eval Graph Eval Output The Perceptron Activation functions The perceptron learning algorithm Binary classification with the perceptron Document classification with the perceptron Limitations of the perceptron From the Perceptron to Support Vector Machines Kernels and the kernel trick Maximum margin classification and support vectors Artificial Neural Networks Nonlinear decision boundaries Feedforward and feedback artificial neural networks Multilayer perceptrons Minimizing the cost function Forward propagation Back propagation Improving the way neural networks learn Convolutional Neural Networks Goals Model Architecture Principles Code Organization Launching and Training the Model Evaluating a Model |

matlabml1 | Introduction to Machine Learning with MATLAB | 21 hours | MATLAB Basics MATLAB More Advanced Features BP Neural Network RBF, GRNN and PNN Neural Networks SOM Neural Networks Support Vector Machine, SVM Extreme Learning Machine, ELM Decision Trees and Random Forests Genetic Algorithm, GA Particle Swarm Optimization, PSO Ant Colony Algorithm, ACA Simulated Annealing, SA Dimenationality Reduction and Feature Selection |

aiauto | Artificial Intelligence in Automotive | 14 hours | This course covers AI (emphasizing Machine Learning and Deep Learning) in Automotive Industry. It helps to determine which technology can be (potentially) used in multiple situation in a car: from simple automation, image recognition to autonomous decision making. Current state of the technology What is used What may be potentially used Rules based AI Simplifying decision Machine Learning Classification Clustering Neural Networks Types of Neural Networks Presentation of working examples and discussion Deep Learning Basic vocabulary When to use Deep Learning, when not to Estimating computational resources and cost Very short theoretical background to Deep Neural Networks Deep Learning in practice (mainly using TensorFlow) Preparing Data Choosing loss function Choosing appropriate type on neural network Accuracy vs speed and resources Training neural network Measuring efficiency and error Sample usage Anomaly detection Image recognition ADAS |

Fairsec | Fairsec: Setting up a CNN-based machine translation system | 7 hours | Fairseq is an open-source sequence-to-sequence learning toolkit created by Facebok for use in Neural Machine Translation (NMT). In this training participants will learn how to use Fairseq to carry out translation of sample content. By the end of this training, participants will have the knowledge and practice needed to implement a live Fairseq based machine translation solution. Source and target language content samples can be prepared according to audience's requirements. Audience Localization specialists with a technical background Global content managers Localization engineers Software developers in charge of implementing global content solutions Format of the course Part lecture, part discussion, heavy hands-on practice Introduction Why Neural Machine Translation? Overview of the Torch project Overview of a Convolutional Neural Machine Translation model Convolutional Sequence to Sequence Learning Convolutional Encoder Model for Neural Machine Translation Standard LSTM-based model Overview of training approaches About GPUs and CPUs Fast beam search generation Installation and setup Evaluating pre-trained models Preprocessing your data Training the model Translating Converting a trained model to use CPU-only operations Joining to the community Closing remarks |

Course | Course Date | Course Price [Remote / Classroom] |
---|---|---|

A practical introduction to Data Analysis and Big Data - QC, Quebec - Sainte Foy | Tue, Sep 5 2017, 9:30 am | CA$8400 / CA$11900 |

Machine Learning Fundamentals with Python - ON, Ottawa – Albert & Metcalfe | Tue, Sep 5 2017, 9:30 am | CA$5050 / CA$7650 |

Artificial Neural Networks, Machine Learning, Deep Thinking - BC, Vancouver - Yaletown | Tue, Sep 5 2017, 9:30 am | CA$7350 / CA$10350 |

Applied Machine Learning - ON, Brampton - Brampton County Court | Thu, Sep 7 2017, 9:30 am | CA$5050 / CA$7450 |

Introduction to Machine Learning - BC, Burnaby | Thu, Sep 14 2017, 9:30 am | CA$2750 / CA$4700 |

Course | Venue | Course Date | Course Price [Remote / Classroom] |
---|---|---|---|

Business and IT System Agility in the Digital Age | ON, Ottawa - Fairmont Chateau Laurier | Wed, Sep 6 2017, 9:30 am | CA$2228 / CA$4328 |

Business Plan building with Business Motivation Model | ON, Ottawa - Fairmont Chateau Laurier | Wed, Sep 20 2017, 9:30 am | CA$3870 / CA$6570 |

Microsoft SDL Core | ON, Ottawa – Albert & Metcalfe | Wed, Sep 27 2017, 9:30 am | CA$4257 / CA$6857 |

Cloud Architect | SK, Saskatoon | Mon, Oct 23 2017, 9:30 am | CA$9405 / CA$14655 |

MediaWiki for Developers | PE, Charlottetown | Wed, Nov 1 2017, 9:30 am | CA$5715 / CA$9465 |

Programming with Big Data in R | ON, Ottawa - Fairmont Chateau Laurier | Mon, Jan 29 2018, 9:30 am | CA$6615 / CA$9915 |