Course Details/Schedule

Day 1

• Introduction to AI, Machine Learning & Deep Learning
• Definition: AI, ML, DL.
• 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: Specially in perspective of Text analytics, classification, summerization tasks

Day 2

• Basic Concepts of a Neural Network (Application: multi-layer perceptron)
• 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

Day 3

• Natural Language Processing for Text Classification
• Introduction to Deep Learning for Natural Language Processing (NLP)
• Using pre-trained vs trained models 
• Using word embeddings and sentiment analysis to extract meaning from text 
• Word embeddings
• Word vectors: word2vec
• Word vectors: GloVe
• Knowledge transfer and word embeddings

Day 4

• Convolutional Neural Networks (CNN).
• Presentation of the CNNs
• Basic operation of a CNN
• Use of an attention model
• CNNs for generation
• Recurrent Neural Networks (RNN)
• Presentation of the RNNs
• Basic operation of a RNN
• Gated Recurrent Units (GRUs) and Long Short Term Memory (LSTM) 
• Combine feed-forward DNNs, convolutional nets (CNNs), and recurrent networks (RNNs/LSTMs)
• Convergence and vanising gradient problems
• Classical architectures: Prediction of a temporal series, classification
• RNN Encoder Decoder type architecture

Day 5

• Tools, Techniques and Frameworks
• Standard ML / DL Tools
• Theano
• Theano Functions
• Training and Optimization of a neural network using Theano
• Testing the model

Day 6

Day 7

• Spacy 
• Spacy Components
• Using spaCy for Deep Learing