Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning, & Deep Learning

• Historical context, fundamental concepts, and common applications of artificial intelligence, moving beyond early theoretical fantasies.
• Collective Intelligence: aggregating knowledge shared among numerous virtual agents.
• Genetic algorithms: evolving populations of virtual agents through selection processes.
• Definition of standard learning machines.
• Types of learning tasks: supervised learning, unsupervised learning, and reinforcement learning.
• Types of output 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 Machine Learning (e.g., Random Forests & XGBoost) remains the state-of-the-art.

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

• Recap of essential mathematical foundations.
• Defining a neural network: classical architectures, activation functions.
• Weighting of previous activations and the concept of network depth.
• Defining network learning: cost functions, back-propagation, stochastic gradient descent, and maximum likelihood.
• Modeling neural networks: adapting input and output data structures to problem types (regression, classification, etc.), and addressing the curse of dimensionality.
• Distinguishing between multi-feature data and signals; selecting cost functions based on data characteristics.
• Function approximation by neural networks: theory and illustrative examples.
• Distribution approximation by neural networks: theory and illustrative examples.
• Data Augmentation: techniques for balancing datasets.
• Generalizing the results obtained from neural networks.
• Initialization and regularization of neural networks: L1 / L2 regularization, and Batch Normalization.
• Algorithms for optimization and convergence.

Standard ML / DL Tools

A brief overview will be provided, highlighting the advantages, disadvantages, ecosystem positioning, and usage of key tools.

• 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: fundamental principles and primary applications.
• Core operations in CNNs: convolutional layers, kernel usage.
• Padding and stride, feature map generation, and pooling layers; extensions to 1D, 2D, and 3D.
• Overview of prominent CNN architectures that set the state-of-the-art in classification.
• Image-based architectures: LeNet, VGG, Network-in-Network, Inception, ResNet; analyzing innovations such as 1x1 convolutions and residual connections.
• Integration of attention models.
• Application to standard classification tasks (text or image).
• CNNs for generative tasks: super-resolution and pixel-to-pixel segmentation.
• Primary strategies for enhancing feature maps in image generation.

Recurrent Neural Networks (RNNs).

• Overview of RNNs: fundamental principles and applications.
• Core RNN operations: hidden activations, back-propagation through time, and unfolded versions.
• Evolution towards Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) networks.
• Analysis of different states and the improvements introduced by these architectures.
• Addressing convergence and vanishing gradient issues.
• Classical architectures: time-series prediction and classification.
• RNN Encoder-Decoder architectures; utilizing attention models.
• Natural Language Processing (NLP) applications: word/character encoding and translation.
• Video applications: predicting the next frame in a video sequence.

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

• Introduction to generative models and their relationship with CNNs.
• Autoencoders: dimensionality reduction and limited generation capabilities.
• Variational Autoencoders: generative modeling and distribution approximation; defining and utilizing latent spaces; the reparameterization trick; applications and observed limitations.
• Generative Adversarial Networks: foundational concepts.
• Dual network architecture (Generator and Discriminator) with alternating training and available cost functions.
• GAN convergence and common challenges.
• Enhanced convergence techniques: Wasserstein GAN, Began, and Earth Mover's Distance.
• Applications in image/photograph generation, text synthesis, and super-resolution.

Deep Reinforcement Learning.

• Introduction to reinforcement learning: controlling an agent within a defined environment.
• Defining 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; A3C.
• Applications: controlling single video games or digital systems.

Part 2 – Theano for Deep Learning

Theano Fundamentals

• Introduction.
• Installation and configuration.

TheanoFunctions

• Inputs, outputs, updates, and givens.

Training and Optimizing Neural Networks with Theano

• Modeling neural networks.
• Logistic Regression.
• Implementing hidden layers.
• Training the network.
• Computation and classification.
• Optimization.
• Log Loss.

Model Testing

Part 3 – DNNs using TensorFlow

TensorFlow Fundamentals

• Creating, initializing, saving, and restoring TensorFlow variables.
• Feeding, reading, and preloading data in TensorFlow.
• Leveraging TensorFlow infrastructure to train models at scale.
• Visualizing and evaluating models using TensorBoard.

TensorFlow Mechanics

• Data preparation.
• Downloading data.
• Defining inputs and placeholders.
• Constructing Graphs.
  • Inference.
  • Loss calculation.
  • Training process.
• Training the Model.
  • The Graph structure.
  • The Session.
  • The Training Loop.
• Evaluating the Model.
  • Building the Evaluation Graph.
  • Evaluation Outputs.

The Perceptron

• Activation functions.
• The perceptron learning algorithm.
• Binary classification using the perceptron.
• Document classification using the perceptron.
• Limitations of the perceptron model.

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.
• Strategies to enhance neural network learning.

Convolutional Neural Networks

• Learning objectives.
• Model architecture.
• Underlying principles.
• Code organization.
• Launching and training the model.
• Model evaluation.

Brief introductions to the following modules (to be provided based on 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.