Understanding Deep Neural Networks Training Course

Part 1 – Deep Learning and DNN Concepts

Introduction to AI, Machine Learning & Deep Learning

• The history, core concepts, and standard applications of artificial intelligence, moving beyond common misconceptions
• Collective Intelligence: Aggregating knowledge shared among multiple virtual agents
• Genetic Algorithms: Evolving populations of virtual agents through selection processes
• Learning Machines: Key definitions and classifications
• Task Categories: Supervised learning, unsupervised learning, and reinforcement learning
• Action Types: Classification, regression, clustering, density estimation, and dimensionality reduction
• Machine Learning Algorithm Examples: Linear regression, Naive Bayes, and Random Forests
• Machine Learning vs. Deep Learning: Identifying problems where Machine Learning remains the state-of-the-art (e.g., Random Forests & XGBoosts)

Fundamentals of Neural Networks (Application: Multi-layer Perceptron)

• Refresher on essential mathematical foundations
• Defining neural networks: Classical architectures and activation functions
• Weighting of previous activations and network depth
• Defining the learning process: Cost functions, back-propagation, Stochastic Gradient Descent, and maximum likelihood
• Modeling neural networks: Handling input and output data based on problem type (regression, classification, etc.) and the Curse of Dimensionality
• Distinguishing between multi-feature data and signals; selecting appropriate cost functions based on data characteristics
• Function approximation by neural networks: Theory and examples
• Distribution approximation by neural networks: Theory and examples
• Data Augmentation: Strategies for balancing datasets
• Generalizing results from 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 is 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 DL frameworks: PyTorch, Keras, Lasagne
• Low-level DL frameworks: Theano, Torch, Caffe, TensorFlow

Convolutional Neural Networks (CNN)

• Introduction to CNNs: Fundamental principles and applications
• Core operations: Convolutional layers, kernel usage
• Padding, stride, feature map generation, pooling layers; extensions to 1D, 2D, and 3D
• Overview of prominent CNN architectures that have achieved state-of-the-art performance in classification
• Image architectures: LeNet, VGG Networks, Network in Network, Inception, ResNet; examining innovations and broader applications (e.g., 1x1 convolutions, residual connections)
• Implementing attention models
• Practical 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: Fundamental principles and applications
• Core operations: Hidden activations, back-propagation through time, and the unfolded version
• Evolution to Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) networks
• Analysis of different states and architectural evolutions
• Addressing convergence and vanishing gradient issues
• Classic architectures: 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 subsequent frames in video sequences

Generative Models: Variational Autoencoder (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 models, distribution approximation, latent space definition, reparameterization trick, 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 challenges
• Enhanced convergence methods: Wasserstein GAN, Began, and Earth Mover’s Distance
• Applications: Image/photograph generation, text generation, and super-resolution

Deep Reinforcement Learning

• Introduction to reinforcement learning: Agent control within a defined environment
• Managing states and possible actions
• Using 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, and A3C
• Applications: Controlling 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 Neural Networks using Theano

• Neural Network Modeling
• Logistic Regression
• Hidden Layers
• Network Training
• Computing and Classification
• Optimization
• Log Loss

Model Testing

Part 3 – DNN using TensorFlow

TensorFlow Basics

• Creating, initializing, saving, and restoring TensorFlow variables
• Feeding, reading, and preloading data in TensorFlow
• Leveraging TensorFlow infrastructure for large-scale model training
• Visualizing and evaluating models with TensorBoard

TensorFlow Mechanics

• Data Preparation
• Downloading Data
• 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
• Perceptron learning algorithm
• Binary classification using the perceptron
• Document classification using the perceptron
• Limitations of the perceptron

From 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 to improve neural network learning

Convolutional Neural Networks

• Objectives
• Model Architecture
• Core Principles
• Code Organization
• Launching and training the model
• Evaluating the model

Brief Introductions to the Following Modules (Coverage depends 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