Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Fundamentals

Introduction to AI, Machine Learning & Deep Learning

• Overview of the history, core concepts, and standard applications of artificial intelligence, distinguishing reality from the domain’s often-held fantasies.
• Collective Intelligence: The aggregation of knowledge shared across multiple virtual agents.
• Genetic Algorithms: Evolving a population of virtual agents through selection mechanisms.
• Definition of standard Learning Machines.
• Categories of tasks: Supervised learning, unsupervised learning, and reinforcement learning.
• Types of actions: 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 Machine Learning remains the state-of-the-art (e.g., Random Forests & XGBoost).

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

• Review of essential mathematical foundations.
• Defining a neuron network: Classical architectures, activation functions, and weighting of prior activations.
• Understanding network depth.
• Defining network learning: Cost functions, back-propagation, Stochastic Gradient Descent, and maximum likelihood.
• Modelling neural networks: Configuring input and output data based on problem types (regression, classification, etc.) and addressing the curse of dimensionality.
• Differentiating between multi-feature data and signals, and selecting appropriate cost functions accordingly.
• Function approximation by neural networks: Theory and practical examples.
• Distribution approximation by neural networks: Theory and practical examples.
• Data Augmentation: Strategies for balancing datasets.
• Generalizing the results of neural networks.
• Initialisation and regularisation of neural networks: L1/L2 regularisation and Batch Normalisation.
• Optimization and convergence algorithms.

Standard ML/DL Tools

A concise overview of these tools, highlighting their advantages, limitations, ecosystem positioning, and practical use cases.

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

Convolutional Neural Networks (CNN).

• Introduction to CNNs: Core principles and applications.
• Fundamental operations of a CNN: Convolutional layers, kernel usage, padding, stride, feature map generation, and pooling layers.
• Extensions across 1D, 2D, and 3D dimensions.
• Overview of prominent CNN architectures that set new standards in classification.
• Image processing examples: LeNet, VGG Networks, Network in Network, Inception, and ResNet, including the innovations introduced by each and their broader applications (e.g., 1x1 convolutions or residual connections).
• Utilising attention models.
• Application to common classification tasks (text or image).
• CNNs for generation: Super-resolution and pixel-to-pixel segmentation.
• Key strategies for enhancing feature maps in image generation.

Recurrent Neural Networks (RNN).

• Introduction to RNNs: Core principles and applications.
• Basic RNN operations: Hidden activations, back-propagation through time, and unfolded versions.
• Evolution towards Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) networks.
• Understanding the distinct states and advancements brought by these architectures.
• Addressing convergence and vanishing gradient issues.
• Classical architectures: Time-series prediction and classification.
• RNN Encoder-Decoder architectures and the integration 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 modelling, distribution approximation, definition and use of latent space, reparameterisation trick, along with observed applications and limitations.
• Generative Adversarial Networks: Core fundamentals.
• Dual network architecture (Generator and Discriminator) involving alternating learning and available cost functions.
• GAN convergence and common challenges.
• Improved convergence techniques: Wasserstein GAN, Began, and Earth Moving Distance.
• Applications in image/photo generation, text generation, and super-resolution.

Deep Reinforcement Learning.

• Introduction to reinforcement learning: Controlling an agent within a defined environment.
• Understanding states and possible actions.
• Using neural networks to approximate state functions.
• Deep Q Learning: Experience replay and its application to video game control.
• Policy optimization: On-policy vs off-policy approaches, Actor-Critic architecture, and A3C.
• Applications: Controlling single video games or digital systems.

Part 2 – Theano for Deep Learning

Theano Fundamentals

• Introduction.
• Installation and configuration.

Theano Functions

• Managing inputs, outputs, updates, and givens.

Training and Optimising Neural Networks with Theano

• Modelling Neural Networks.
• Logistic Regression.
• Implementing Hidden Layers.
• Training the network.
• Computing and Classification.
• Optimization.
• Log Loss.

Model Testing

Part 3 – DNN using TensorFlow

TensorFlow Fundamentals

• Creating, initialising, saving, and restoring TensorFlow variables.
• Feeding, reading, and preloading data in TensorFlow.
• Leveraging TensorFlow infrastructure for large-scale model training.
• Visualising and evaluating models using TensorBoard.

TensorFlow Mechanics

• Data preparation.
• Downloading datasets.
• Defining inputs and placeholders.
• Constructing Graphs:
  • Inference.
  • Loss.
  • Training.
• Training the Model:
  • The Graph.
  • The Session.
  • Training Loop.
• Evaluating the Model:
  • Building the Eval Graph.
  • Eval 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

• Non-linear decision boundaries.
• Feedforward and feedback artificial neural networks.
• Multilayer perceptrons.
• Minimising the cost function.
• Forward propagation.
• Back-propagation.
• Enhancing neural network learning methods.

Convolutional Neural Networks

• Objectives.
• Model architecture.
• Underlying principles.
• Code organisation.
• Launching and training the model.
• Model evaluation.

Brief introductions to the following modules (provided based on time availability):

TensorFlow - Advanced Usage

• Threading and Queues.
• Distributed TensorFlow.
• Writing documentation and sharing models.
• Customising data readers.
• Manipulating TensorFlow model files.

TensorFlow Serving

• Introduction.
• Basic serving tutorial.
• Advanced serving tutorial.
• Serving Inception model tutorial.