Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• History, core concepts, and typical applications of artificial intelligence, separating fact from fiction in this domain
• Collective Intelligence: aggregating knowledge shared among multiple virtual agents
• Genetic algorithms: evolving a population of virtual agents through selection
• Standard Machine Learning: 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 Forests
• Machine Learning vs. Deep Learning: scenarios where Machine Learning (e.g., Random Forests & XGBoosts) remains state-of-the-art

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

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

Standard ML / DL Tools

A brief overview of available tools, including their advantages, disadvantages, ecosystem positioning, and use cases, will be provided.

• Data management tools: Apache Spark, Apache Hadoop Tools
• 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).

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

Recurrent Neural Networks (RNN).

• Overview of RNNs: fundamental principles and applications
• Basic RNN operation: hidden activations, back-propagation through time, and unfolded version
• Evolution towards Gated Recurrent Units (GRUs) and LSTMs (Long Short-Term Memory)
• Overview of different states and architectural evolutions
• Convergence issues and vanishing gradient problems
• Classical architectures: time 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).

• Overview of generative models and their connection to CNNs
• Auto-encoders: dimensionality reduction and limited generation capabilities
• Variational Auto-encoders: generative models and distribution approximation for given data. 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 methods: Wasserstein GAN, BEGAN, Earth Mover's Distance
• Applications for generating images, photographs, text, and super-resolution

Deep Reinforcement Learning.

• Overview of reinforcement learning: agent control in a defined environment
• Based on state and possible actions
• Using neural networks to approximate the state function
• Deep Q-Learning: experience replay and application to video game control
• Learning policy optimization. On-policy && off-policy. Actor-critic architecture. A3C
• Applications: controlling a single video game or 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

• Creating, Initializing, 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