Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• Historical context, core concepts, and standard applications of artificial intelligence, moving beyond common misconceptions.
• Collective Intelligence: aggregating knowledge shared across multiple virtual agents.
• Genetic algorithms: evolving a population of virtual agents through selection mechanisms.
• Standard Learning Machine: formal definition.
• Task categories: 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 Machine Learning (e.g., Random Forests & XGBoosts) remains the state of the art.

Basic Concepts of a Neural Network (Application: multi-layer perceptron)

• Review of mathematical foundations.
• Defining a neural network: classical architecture, activation functions,
• weighting of previous activations, and network depth.
• Defining network learning: cost functions, back-propagation, Stochastic gradient descent, and maximum likelihood.
• Neural network modeling: structuring input and output data based on the problem type (regression, classification, etc.). The curse of dimensionality.
• Distinguishing between multi-feature data and signals. Selecting an appropriate cost function based on data characteristics.
• Function approximation by neural networks: overview and examples.
• Distribution approximation by neural networks: overview and examples.
• 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

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

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

Convolutional Neural Networks (CNN).

• Overview of CNNs: fundamental principles and applications.
• Basic CNN operations: convolutional layers and kernel usage.
• Padding and stride, feature map generation, and pooling layers. Extensions to 1D, 2D, and 3D.
• Review of various CNN architectures that have advanced the state of the art in classification.
• Image architectures: LeNet, VGG Networks, Network in Network, Inception, and ResNet. Discussion of innovations introduced by each and their broader applications (e.g., 1x1 convolution or residual connections).
• Implementation of attention models.
• Application to common classification tasks (text or image).
• Generative CNNs: 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 activation, back-propagation through time, and unfolded versions.
• Evolution into Gated Recurrent Units (GRUs) and LSTM (Long Short-Term Memory).
• Discussion of different states and the advancements brought by these architectures.
• Convergence challenges and the vanishing gradient problem.
• Classical architectures: time series prediction and classification.
• RNN Encoder-Decoder architectures and the use of attention models.
• NLP applications: word and character encoding, 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. Defining and utilizing latent space. The reparameterization trick. Observed applications and limitations.
• Generative Adversarial Networks: core fundamentals.
• Dual Network Architecture (Generator and Discriminator) with alternating learning and available cost functions.
• GAN convergence and common difficulties encountered.
• Improved convergence techniques: Wasserstein GAN, BigGAN, 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.
• Based on states and possible actions.
• Using neural networks to approximate the state function.
• 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 Basics

• Introduction.
• Installation and Configuration.

TheanoFunctions

• inputs, outputs, updates, and givens.

Training and Optimization of a Neural Network using Theano

• Neural Network Modeling.
• Logistic Regression.
• Hidden Layers.
• Training a network.
• Computing and Classification.
• Optimization.
• 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.
• Utilizing TensorFlow infrastructure to train models at scale.
• Visualizing and evaluating models with TensorBoard.

TensorFlow Mechanics

• Data Preparation.
• Downloading.
• Inputs and Placeholders.
• Building the 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 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.
• Enhancing neural network learning processes.

Convolutional Neural Networks

• Objectives.
• Model Architecture.
• Core Principles.
• Code Organization.
• Launching and Training the Model.
• Evaluating a 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 your Model.
• Customizing Data Readers.
• Manipulating TensorFlow Model Files.

TensorFlow Serving

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