Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• History, fundamental concepts, and common applications of artificial intelligence, separating fact from fantasy
• Collective Intelligence: aggregating knowledge shared among numerous virtual agents
• Genetic algorithms: evolving populations of virtual agents through selection
• Fundamentals of Machine Learning: definition and scope
• 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 traditional Machine Learning remains state-of-the-art (e.g., Random Forests & XGBoost)

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

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

Standard ML / DL Tools

A concise overview of available tools, including their advantages, disadvantages, ecosystem positioning, and use cases.

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

Convolutional Neural Networks (CNNs).

• Overview of CNNs: core principles and applications
• Core operations of a CNN: convolutional layers, kernel usage,
• Padding & stride, feature map generation, pooling layers. Extensions for 1D, 2D, and 3D data.
• Overview of state-of-the-art CNN architectures in classification tasks
• Image architectures: LeNet, VGG Networks, Network-in-Network, Inception, ResNet. Highlighting innovations from each architecture and their broader applications (e.g., 1x1 convolutions, residual connections)
• Implementation of attention models.
• Practical application to common classification tasks (text or image)
• CNNs for generative tasks: super-resolution, pixel-to-pixel segmentation. Overview of
• Key strategies for enhancing feature maps in image generation.

Recurrent Neural Networks (RNNs).

• Overview of RNNs: core principles and applications.
• Core operation of RNNs: hidden activations, back-propagation through time, unfolded versions.
• Evolution toward Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) networks.
• Overview of different states and architectural advancements
• Addressing convergence issues and vanishing gradients
• Classic architectures: Time series prediction, classification, etc.
• RNN Encoder-Decoder architecture. Utilization of attention models.
• NLP applications: word/character encoding, translation.
• Video Applications: predicting the next frame in a video sequence.

Generative Models: Variational AutoEncoders (VAE) and Generative Adversarial Networks (GANs).

• 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 usage of latent space. The reparameterization trick. Applications and observed limitations.
• Generative Adversarial Networks: Core fundamentals.
• Dual network architecture (Generator and Discriminator) with alternating learning and available cost functions.
• GAN convergence and associated challenges.
• Improved convergence methods: Wasserstein GAN, BEGAN, Earth Mover’s Distance.
• Applications for generating images or photographs, text generation, and super-resolution.

Deep Reinforcement Learning.

• Overview of reinforcement learning: controlling an agent within a defined environment
• Based on state and possible actions
• Using neural networks to approximate state-value functions
• Deep Q-Learning: experience replay and application to video game control.
• Learning policy optimization. On-policy && off-policy methods. Actor-Critic architecture. A3C algorithm.
• 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 a Neural Network using Theano

• Neural Network Modeling
• Logistic Regression
• Hidden Layers
• Training a network
• Computing and Classification
• Optimization techniques
• 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 large-scale model training
• Visualizing and evaluating models with TensorBoard

TensorFlow Mechanics

• Preparing the Data
• Downloading datasets
• Inputs and Placeholders
• Building the Graphs
  • Inference
  • Loss calculation
  • Training steps
• Training the Model
  • The Graph structure
  • 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 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
• Core Principles
• Code Organization
• Launching and Training the Model
• Evaluating a Model

Basic Introductions to be given to the following modules (Brief overviews provided subject to 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 the Inception Model Tutorial