Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• History, basic concepts, and common applications of artificial intelligence, moving beyond the field's common misconceptions
• Collective Intelligence: aggregating knowledge shared by multiple virtual agents
• Genetic algorithms: evolving a population of virtual agents through selection processes
• Standard Learning Machines: definition and core principles
• 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 Forests
• Machine Learning vs. Deep Learning: identifying problems where traditional Machine Learning (e.g., Random Forests & XGBoost) remains the state of the art

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

• Review of mathematical foundations
• Definition of a neuron network: classical architecture, activation functions
• Weighting of previous activations and network depth
• Learning in neuron networks: cost functions, back-propagation, Stochastic Gradient Descent, and maximum likelihood
• Modelling neuron networks: input and output data modelling based on problem type (regression, classification, etc.) and the curse of dimensionality
• Distinguishing between multi-feature data and signals; selecting an appropriate cost function based on data characteristics
• Function approximation by neuron networks: overview and examples
• Distribution approximation by neuron networks: overview and examples
• Data Augmentation: techniques for balancing datasets
• Generalisation of neuron network results
• Initialisation and regularisation of neuron networks: L1/L2 regularisation and Batch Normalisation
• Optimisation and convergence algorithms

Standard ML/DL Tools

A brief overview covering advantages, disadvantages, ecosystem positioning, and usage of key tools is included.

• 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
• Basic CNN operations: convolutional layers and kernel usage
• Padding & stride, feature map generation, pooling layers, and 1D, 2D, and 3D extensions
• Presentation of CNN architectures that have advanced the state of the art in classification
• Image models: LeNet, VGG Networks, Network in Network, Inception, and ResNet. Discussion of innovations introduced by each architecture and their broader applications (e.g., 1x1 convolutions and residual connections)
• Utilisation of attention models
• Application to common classification cases (text or image)
• CNNs for generation: super-resolution and pixel-to-pixel segmentation overview
• Key strategies for enhancing feature maps in image generation

Recurrent Neural Networks (RNN)

• Overview of RNNs: fundamental principles and applications
• Basic RNN operations: hidden activation, back-propagation through time, and unfolded versions
• Evolution towards Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM)
• Analysis of various states and advancements brought by these architectures
• Convergence and vanishing gradient issues
• Classical architectures: time-series prediction, classification, and more
• RNN Encoder-Decoder architectures and the use of attention models
• NLP applications: word/character encoding and translation
• Video applications: predicting the next image in a video sequence

Generative Models: Variational Auto-Encoders (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 modelling and distribution approximation. Definition and use of latent space, reparameterisation 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 common challenges
• Improved convergence techniques: Wasserstein GAN, BigGAN, and Earth Mover’s Distance
• Applications: image/photograph generation, text generation, and super-resolution

Deep Reinforcement Learning

• Overview of reinforcement learning: controlling an agent within a defined environment
• Managing states and possible actions
• Using neuron networks to approximate state functions
• Deep Q-Learning: experience replay and application to video game control
• Policy optimisation: on-policy and off-policy methods, Actor-Critic architecture, and A3C
• Applications: control of 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 Optimisation of a Neural Network using Theano

• Neural Network Modelling
• Logistic Regression
• Hidden Layers
• Training a network
• Computation and Classification
• Optimisation
• Log Loss

Testing the Model

Part 3 – DNN using TensorFlow

TensorFlow Basics

• Creating, initialising, saving, and restoring TensorFlow variables
• Feeding, reading, and preloading TensorFlow data
• Utilising TensorFlow infrastructure to train models at scale
• Visualising and evaluating models with TensorBoard

TensorFlow Mechanics

• Preparing the Data
• Downloading
• 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
• Minimising the cost function
• Forward propagation
• Back propagation
• Enhancing the way neural networks learn

Convolutional Neural Networks

• Objectives
• Model Architecture
• Principles
• Code Organisation
• Launching and Training the Model
• Evaluating a Model

Basic introductions to be provided for the following modules (brief overview based on time availability):

TensorFlow – Advanced Usage

• Threading and Queues
• Distributed TensorFlow
• Writing documentation and sharing your model
• Customising Data Readers
• Manipulating TensorFlow Model Files

TensorFlow Serving

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