Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• History, basic concepts, and standard applications of artificial intelligence, distinguishing reality from common fantasies in the domain
• Collective Intelligence: aggregating knowledge shared across many virtual agents
• Genetic algorithms: evolving a population of virtual agents through selection processes
• Standard Learning Machines: defining the core concepts
• 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, and Random Trees
• Machine Learning vs. Deep Learning: identifying problems where machine learning remains the state of the art (e.g., Random Forests & XGBoost)

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

• Review of mathematical foundations
• Defining neural networks: classical architecture, activation functions
• Weighting of previous activations and network depth
• Defining network learning: cost functions, back-propagation, stochastic gradient descent, and maximum likelihood
• Modeling neural networks: adapting input and output data to problem types (regression, classification, etc.) and addressing the curse of dimensionality
• Distinguishing between multi-feature data and signals; selecting cost functions based on data characteristics
• Function approximation by neural networks: theory and examples
• Distribution approximation by neural networks: theory and examples
• Data Augmentation: techniques for balancing datasets
• Generalizing results from neural networks
• Initialization and regularization of neural networks: L1/L2 regularization and Batch Normalization
• Optimization and convergence algorithms

Standard ML / DL Tools

This section provides a concise overview of tool advantages, disadvantages, ecosystem positioning, and usage.

• Data management tools: Apache Spark, Apache Hadoop
• Machine Learning libraries: NumPy, SciPy, Sci-kit
• High-level Deep Learning frameworks: PyTorch, Keras, Lasagne
• Low-level Deep Learning frameworks: Theano, Torch, Caffe, TensorFlow

Convolutional Neural Networks (CNN).

• Overview of CNNs: fundamental principles and applications
• Core CNN operations: convolutional layers and kernel usage
• Padding & stride, feature map generation, pooling layers, and 1D, 2D, and 3D extensions
• Overview of CNN architectures that established the state of the art in classification
• Image processing examples: LeNet, VGG Networks, Network in Network, Inception, ResNet, including their innovations and broader applications (e.g., 1x1 convolutions, residual connections)
• Implementing attention models
• Applying CNNs to common classification tasks (text or image)
• Generative applications of CNNs: super-resolution and pixel-to-pixel segmentation
• Key strategies for enhancing feature maps in image generation

Recurrent Neural Networks (RNN).

• Overview of RNNs: fundamental principles and applications
• Core RNN operations: hidden activations, back-propagation through time, and unfolded versions
• Evolution toward Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM)
• Examining different states and architectural evolutions
• Addressing convergence and vanishing gradient problems
• Classical architectures: time series prediction and classification
• RNN Encoder-Decoder architectures and the use of attention models
• NLP applications: word/character encoding and translation
• Video applications: predicting the next frame in a video sequence

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

• Overview of generative models and their relationship with CNNs
• Auto-encoders: dimensionality reduction and limited generation
• Variational Auto-encoders: generative modeling, distribution approximation, latent space definition, the reparameterization trick, applications, and observed limitations
• Generative Adversarial Networks: foundational concepts
• Dual network architecture (Generator and Discriminator) with alternating learning and available cost functions
• GAN convergence and associated challenges
• Enhanced convergence methods: Wasserstein GAN, Began, and Earth Moving Distance
• Applications in image/photograph generation, text generation, and super-resolution

Deep Reinforcement Learning.

• Overview of reinforcement learning: controlling agents within defined environments
• Considering states and possible actions
• Using neural networks to approximate state functions
• Deep Q-Learning: experience replay and its application to video game control
• Optimizing learning policies: on-policy and off-policy methods, Actor-Critic architecture, and A3C
• Applications: controlling single video games or digital systems

Part 2 – Theano for Deep Learning

Theano Basics

• Introduction
• Installation and Configuration

Theano Functions

• Inputs, outputs, updates, and givens

Training and Optimization of Neural Networks 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
• Utilizing TensorFlow infrastructure to train models at scale
• Visualizing and evaluating models with TensorBoard

TensorFlow Mechanics

• Data Preparation
• Data Download
• Inputs and Placeholders
• Building Graphs
  • Inference
  • Loss
  • Training
• Training the Model
  • The Graph
  • The Session
  • Train Loop
• Evaluating the Model
  • Building the Evaluation Graph
  • Evaluation 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 neural network learning processes

Convolutional Neural Networks

• Goals
• Model Architecture
• Principles
• Code Organization
• Launching and Training the Model
• Evaluating a Model

Brief introductions to the following modules (subject to time availability):

Tensorflow – Advanced Usage

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

TensorFlow Serving

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