Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• History, core concepts, and practical applications of artificial intelligence, separating reality from speculation.
• Collective Intelligence: Aggregating knowledge from multiple virtual agents.
• Genetic algorithms: Evolving populations of virtual agents through selection.
• Standard Learning Machines: Definitions and characteristics.
• 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 and XGBoosts).

Basic Concepts of a Neural Network (Application: Multi-layer Perceptron)

• Review of mathematical foundations.
• Defining a network of neurons: classical architecture, activation functions, and weighting of previous activations.
• Network depth and structure.
• Defining neural network learning: cost functions, back-propagation, stochastic gradient descent, and maximum likelihood.
• Modeling neural networks: configuring input and output data based on problem type (regression, classification) and addressing the curse of dimensionality.
• Differentiating between multi-feature data and signals; selecting appropriate cost functions.
• Function approximation using neural networks: presentation and examples.
• Distribution approximation using 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 and Batch Normalization.
• Optimization and convergence algorithms.

Standard ML / DL Tools

A concise presentation covering the advantages, disadvantages, ecosystem positioning, and usage of key tools.

• 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).

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

Recurrent Neural Networks (RNN).

• Overview of RNNs: fundamental principles and applications.
• Core operations: hidden activation, back propagation through time, and unfolded versions.
• Evolution towards Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) networks.
• Overview of different states and architectural advancements.
• Addressing convergence and vanishing gradient challenges.
• Classical architectures: Time series prediction, classification, etc.
• 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 capabilities.
• Variational Auto-encoders: Generative modeling and distribution approximation. Definition and use of latent space. The reparameterization trick. Applications and observed limitations.
• Generative Adversarial Networks: Fundamental principles.
• Dual network architecture (Generator and Discriminator) with alternating learning and available cost functions.
• GAN convergence and associated challenges.
• Improving convergence: Wasserstein GAN, BegGAN, and Earth Mover Distance.
• Applications in generating images, photographs, text, and super-resolution.

Deep Reinforcement Learning.

• Overview of reinforcement learning: Agent control within a defined environment.
• Defining states and possible actions.
• Using neural networks to approximate state functions.
• Deep Q-Learning: Experience replay and its application to video game control.
• Optimization of learning policies: On-policy vs. off-policy. Actor-critic architectures 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 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
• Leveraging TensorFlow infrastructure for scalable model training
• Visualizing and evaluating models with TensorBoard

TensorFlow Mechanics

• Preparing the Data
• Downloading datasets
• Inputs and Placeholders
• Building the Graphs
  • Inference
  • Loss
  • Training
• Training the Model
  • The Graph
  • The Session
  • Training 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 how 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