Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• History, basic concepts, and common applications of artificial intelligence, separating them from the fantasies often associated with this field.
• Collective Intelligence: aggregating knowledge shared by numerous virtual agents.
• Genetic algorithms: evolving a population of virtual agents through selection.
• Standard Learning Machines: definition.
• Types of tasks: supervised learning, unsupervised learning, reinforcement learning.
• Types of actions: classification, regression, clustering, density estimation, dimensionality reduction.
• Examples of Machine Learning algorithms: Linear regression, Naive Bayes, Random Forests.
• Machine Learning vs. Deep Learning: problems where Machine Learning remains the state of the art today (Random Forests & XGBoosts).

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

• Recap of mathematical foundations.
• Definition of a neuron network: classical architecture, activation functions, and
• Weighting of previous activations, network depth.
• Definition of neural network learning: cost functions, back-propagation, Stochastic Gradient Descent, maximum likelihood.
• Modeling a neural network: modeling input and output data according to the type of problem (regression, classification, etc.). The curse of dimensionality.
• Distinction between multi-feature data and signals. Selection of a cost function based on the data.
• Function approximation by a neural network: presentation and examples.
• Distribution approximation by a neural network: presentation and examples.
• Data Augmentation: how to balance a dataset.
• Generalization of neural network results.
• Initialization and regularization of a neural network: L1 / L2 regularization, Batch Normalization.
• Optimization and convergence algorithms.

Standard ML / DL Tools

A simple presentation outlining advantages, disadvantages, position in the ecosystem, and usage is planned.

• Data management tools: Apache Spark, Apache Hadoop Tools.
• Machine Learning: 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 operation of a CNN: convolutional layer, use of a kernel,
• Padding & stride, feature map generation, pooling layers. Extensions 1D, 2D, and 3D.
• Presentation of various CNN architectures that established the state of the art in classification.
• Images: LeNet, VGG Networks, Network in Network, Inception, Resnet. Presentation of innovations introduced by each architecture and their broader 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.

Recurrent Neural Networks (RNN).

• Presentation of RNNs: fundamental principles and applications.
• Basic operation of the RNN: hidden activation, backpropagation through time, unfolded version.
• Evolutions toward Gated Recurrent Units (GRUs) and LSTM (Long Short-Term Memory).
• Presentation of different states and the evolutions brought by these architectures.
• Convergence and vanishing gradient problems.
• Classical architectures: time series prediction, classification, etc.
• RNN Encoder-Decoder architecture. Use of an attention model.
• NLP applications: word / character encoding, translation.
• Video Applications: prediction of the next generated image in a video sequence.

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

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

Deep Reinforcement Learning.

• Presentation of reinforcement learning: control of an agent in a defined environment.
• Via 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 the 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, 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, 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

• Prepare the Data.
• Download.
• 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.
• Backpropagation.
• 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 following 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.