Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning, and Deep Learning

• The history, core concepts, and typical applications of artificial intelligence, distinguishing reality from fiction in the field.
• Collective Intelligence: the aggregation of knowledge shared among multiple virtual agents.
• Genetic algorithms: evolving populations of virtual agents through selection processes.
• Definition of standard Machine Learning paradigms.
• 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 traditional ML methods like Random Forests and XGBoost remain state-of-the-art.

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

• Review of mathematical foundations.
• Defining neural networks: classical architectures and activation mechanisms.
• Weighting of previous activations and determining network depth.
• Defining network learning: cost functions, back-propagation, Stochastic Gradient Descent, and maximum likelihood.
• Modeling neural networks: structuring input and output data based on problem type (e.g., regression, classification) and addressing the curse of dimensionality.
• Distinguishing between multi-feature data and signals, and selecting appropriate cost functions.
• Approximating functions using neural networks: presentations and case studies.
• Approximating distributions using neural networks: presentations and case studies.
• Data Augmentation: techniques for balancing datasets.
• Generalizing the results of 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 an overview of key tools, highlighting their advantages, disadvantages, ecosystem positioning, and typical use cases.

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

Convolutional Neural Networks (CNN).

• Overview of CNNs: core principles and practical applications.
• Basic CNN operations: convolutional layers and the use of kernels.
• Padding and stride, feature map generation, and pooling layers. Extensions to 1D, 2D, and 3D.
• Review of CNN architectures that have set the benchmark for classification performance.
• Image processing architectures: LeNet, VGG Networks, Network in Network, Inception, and ResNet, including their innovations and broader applications (e.g., 1x1 convolutions, residual connections).
• Implementation of attention models.
• Applying CNNs to common classification tasks (text or image).
• CNNs for generative tasks: 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.
• Basic RNN operations: hidden activations, back-propagation through time, and unfolded representations.
• Evolution towards Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) networks.
• Analysis of different states and architectural improvements introduced by these models.
• Addressing convergence and vanishing gradient issues.
• Classical architectures: time series prediction, classification, and other tasks.
• RNN Encoder-Decoder architectures and the application 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).

• Introduction to 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 spaces, reparameterization trick, and observed limitations.
• Generative Adversarial Networks: fundamental concepts.
• Dual network architecture (Generator and Discriminator) with alternating learning and available cost functions.
• Convergence challenges in GANs and common difficulties encountered.
• Improved convergence techniques: Wasserstein GAN, Began, and Earth Mover’s Distance.
• Applications in image/photograph generation, text generation, and super-resolution.

Deep Reinforcement Learning.

• Introduction to reinforcement learning: controlling an agent within a defined environment.
• Environment states and possible actions.
• Utilizing neural networks to approximate state functions.
• Deep Q-Learning: experience replay and application to video game control.
• Policy optimization: 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 Optimizing Neural Networks using Theano

• Modeling Neural Networks
• Logistic Regression
• Hidden Layers
• Network Training
• Computation and Classification
• Optimization
• Log Loss

Model Testing

Part 3 – DNN using TensorFlow

TensorFlow Basics

• Creating, initializing, saving, and restoring TensorFlow variables.
• Feeding, reading, and preloading TensorFlow data.
• Leveraging TensorFlow infrastructure for large-scale model training.
• Visualizing and evaluating models with TensorBoard.

TensorFlow Mechanics

• Data Preparation
• Downloading Data
• Inputs and Placeholders
• Building 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 using the perceptron
• Document classification using the perceptron
• Limitations of the perceptron

From Perceptrons 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
• Enhancing neural network learning efficiency

Convolutional Neural Networks

• Objectives
• Model Architecture
• Principles
• Code Organization
• Launching and Training the Model
• Evaluating the Model

Brief introductions to the following modules will be provided, 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