Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• History, basic concepts, and typical applications of artificial intelligence, distinct from the fantasies often associated with this field.
• Collective Intelligence: aggregating knowledge shared among many virtual agents.
• Genetic algorithms: evolving a population of virtual agents through selection.
• Learning Machines: definition.
• Task types: supervised learning, unsupervised learning, and reinforcement learning.
• Action types: classification, regression, clustering, density estimation, and dimensionality reduction.
• Examples of Machine Learning algorithms: Linear regression, Naive Bayes, Random Trees.
• Machine Learning vs. Deep Learning: issues where Machine Learning remains state-of-the-art (e.g., Random Forests & XGBoosts).

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

• Review of mathematical foundations.
• Definition of a neuron network: classical architecture, activation functions.
• Weighting of previous activations and network depth.
• Defining the learning process of a neuron network: cost functions, back-propagation, Stochastic gradient descent, and maximum likelihood.
• Neural network modeling: input and output data modeling based on the problem type (regression, classification, etc.) and the curse of dimensionality.
• Distinction between multi-feature data and signals; choosing a cost function based on data types.
• Function approximation by a neuron network: presentation and examples.
• Distribution approximation by a neuron network: presentation and examples.
• Data Augmentation: techniques for balancing a dataset.
• Generalization of neuron network results.
• Initialization and regularization of neural networks: L1 / L2 regularization, Batch Normalization.
• Optimization and convergence algorithms.

Standard ML / DL Tools

A simple presentation covering advantages, disadvantages, ecosystem positioning, and usage is planned.

• Data management tools: Apache Spark, Apache Hadoop.
• Machine Learning libraries: Numpy, Scipy, Sci-kit.
• High-level DL frameworks: PyTorch, Keras, Lasagne.
• Low-level DL frameworks: Theano, Torch, Caffe, TensorFlow.

Convolutional Neural Networks (CNN).

• Presentation of CNNs: fundamental principles and applications.
• Basic CNN operation: convolutional layers, kernel usage.
• Padding & stride, feature map generation, pooling layers, and 1D, 2D, and 3D extensions.
• Presentation of various CNN architectures that have achieved state-of-the-art results in classification.
• Image architectures: LeNet, VGG Networks, Network in Network, Inception, Resnet. Presentation of innovations brought by each architecture and their broader applications (e.g., 1x1 Convolution or residual connections).
• Use of attention models.
• Application to common classification cases (text or image).
• CNNs for generation: super-resolution, pixel-to-pixel segmentation. Presentation of.
• Main strategies for increasing feature maps in image generation.

Recurrent Neural Networks (RNN).

• Presentation of RNNs: fundamental principles and applications.
• Basic RNN operation: hidden activation, back propagation through time, unrolled version.
• Evolution towards Gated Recurrent Units (GRUs) and LSTM (Long Short-Term Memory).
• Presentation of different states and architectural evolutions.
• Convergence and vanishing gradient problems.
• Classical architectures: temporal series prediction, classification, etc.
• RNN Encoder-Decoder architecture. Use of attention models.
• NLP applications: word / character encoding, translation.
• Video applications: predicting the next image in a video sequence.

Generative Models: Variational AutoEncoder (VAE) and Generative Adversarial Networks (GAN).

• Presentation of generative models and their link with CNNs.
• Auto-encoder: dimensionality reduction and limited generation.
• Variational Auto-encoder: generative model and approximation of the distribution of a given input. Definition and use of latent space. Reparameterization trick. Applications and observed limitations.
• Generative Adversarial Networks: Fundamentals.
• Dual Network Architecture (Generator and discriminator) with alternating learning and available cost functions.
• GAN convergence and encountered difficulties.
• Improved convergence: Wasserstein GAN, Began, Earth Mover's Distance.
• Applications for image or photo generation, text generation, and super-resolution.

Deep Reinforcement Learning.

• Presentation of reinforcement learning: controlling an agent within a defined environment.
• Defined by state and possible actions.
• Use of a neural network to approximate the state function.
• Deep Q Learning: experience replay and its application to video game control.
• Optimization of learning policy. On-policy && off-policy. Actor-critic architecture. A3C.
• Applications: control of a single video game or a digital system.

Part 2 – Theano for Deep Learning

Theano Basics

• Introduction
• Installation and Configuration

Theano Functions

• Inputs, outputs, updates, and givens.

Training and Optimization of a neural network using Theano

• Neural Network Modeling
• Logistic Regression
• Hidden Layers
• Training a network
• Computing and Classification
• Optimization
• Log Loss

Testing the model

Part 3 – DNN using TensorFlow

TensorFlow Basics

• Creation, Initialization, Saving, and Restoring TensorFlow variables.
• Feeding, Reading, and Preloading TensorFlow Data.
• Using TensorFlow infrastructure to train models at scale.
• Visualizing and Evaluating models with TensorBoard.

TensorFlow Mechanics

• Prepare the Data.
• Download.
• Inputs and Placeholders.
• Build the Graphs.
  • Inference.
  • Loss.
  • Training.
• Train the Model.
  • The Graph.
  • The Session.
  • Training 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.

Basic Introductions to be given to the below modules (Brief Introduction to be provided based on time availability):

TensorFlow - Advanced Usage

• Threading and Queues.
• Distributed TensorFlow.
• Writing Documentation and Sharing your Model.
• Customizing Data Readers.
• Manipulating TensorFlow Model Files.

TensorFlow Serving

• Introduction.
• Basic Serving Tutorial.
• Advanced Serving Tutorial.
• Serving Inception Model Tutorial.