Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• A review of the history, core concepts, and standard applications of artificial intelligence, moving beyond common misconceptions.
• Collective Intelligence: the aggregation of knowledge shared among numerous virtual agents.
• Genetic algorithms: evolving populations of virtual agents through selection processes.
• Defining the standard Machine Learning paradigm.
• Categorizing task types: supervised learning, unsupervised learning, and reinforcement learning.
• Action types: classification, regression, clustering, density estimation, and dimensionality reduction.
• Examples of Machine Learning algorithms, including Linear regression, Naive Bayes, and Random Tree.
• Machine Learning vs. Deep Learning: identifying problems where traditional Machine Learning (e.g., Random Forests & XGBoosts) remains the state of the art.

Core Concepts of Neural Networks (Application: multi-layer perceptron)

• Review of essential mathematical foundations.
• Defining neural networks: classical architectures and activation mechanisms.
• The role of weighting previous activations and network depth.
• Defining neural network learning processes: cost functions, back-propagation, stochastic gradient descent, and maximum likelihood.
• Modeling neural networks: structuring input and output data based on problem types (regression, classification, etc.) and addressing the curse of dimensionality.
• Distinguishing between multi-feature data and signals; selecting appropriate cost functions for the data.
• Function approximation using neural networks: theory and examples.
• Distribution approximation using neural networks: theory and examples.
• Data Augmentation: strategies for balancing datasets.
• Generalization of results obtained from neural networks.
• Network initialization and regularization techniques, including 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, Apache Hadoop Tools.
• 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, kernel usage.
• Padding & stride, feature map generation, and pooling layers, including 1D, 2D, and 3D extensions.
• Presentation of leading CNN architectures that have achieved state-of-the-art results in classification.
• Key architectures: LeNet, VGG Networks, Network in Network, Inception, and ResNet, highlighting their innovations and broader applications (e.g., 1x1 convolutions or residual connections).
• Implementing attention models.
• Application to standard classification tasks (text or image).
• CNNs for generation: super-resolution and pixel-to-pixel segmentation.
• Primary 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 the unfolded version.
• Advancements towards Gated Recurrent Units (GRUs) and LSTM (Long Short Term Memory).
• Analysis of different states and the evolutions introduced by these architectures.
• Addressing convergence issues and vanishing gradient problems.
• Classical architectures for time-series prediction and classification.
• RNN Encoder-Decoder architectures and the use 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 models for distribution approximation, latent space definition, reparameterization tricks, and observed applications and limitations.
• Generative Adversarial Networks: core fundamentals.
• Dual Network Architecture (Generator and discriminator) featuring alternate learning and available cost functions.
• GAN convergence behaviors and common difficulties.
• Improved convergence methods: Wasserstein GAN, Began, and Earth Moving 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.
• Managing states and possible actions.
• Utilizing neural networks to approximate the state function.
• Deep Q Learning: experience replay and its application to video game control.
• Learning policy optimization: On-policy & off-policy approaches, Actor-critic architecture, and A3C.
• Applications in controlling single video games or digital systems.

Part 2 – Theano for Deep Learning

Theano Basics

• Introduction
• Installation and Configuration

Theano Functions

• Handling 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.
• Leveraging TensorFlow infrastructure for large-scale model training.
• Visualizing and evaluating models with TensorBoard.

TensorFlow Mechanics

• Data Preparation
• Downloading data
• Inputs and Placeholders
• Building Graphs
  • Inference
  • Loss
  • Training
• Training the Model
  • The Graph
  • The Session
  • Train 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
• Strategies for improving neural network learning

Convolutional Neural Networks

• Goals
• Model Architecture
• Principles
• Code Organization
• Launching and Training the Model
• Evaluating a Model

Brief introductions to the following modules (coverage depends on 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