Understanding Deep Neural Networks Training Course


35 hours (usually 5 days including breaks)


Background in physics, mathematics and programming. Involvment in image processing activities.

The delegates should have a prior understanding of machine learning concepts, and should have worked upon Python programming and libraries.


This course begins with giving you conceptual knowledge in neural networks and generally in machine learning algorithm, deep learning (algorithms and applications).

Part-1(40%) of this training is more focus on fundamentals, but will help you choosing the right technology : TensorFlow, Caffe, Theano, DeepDrive, Keras, etc.

Part-2(20%) of this training introduces Theano – a python library that makes writing deep learning models easy.

Part-3(40%) of the training would be extensively based on Tensorflow – 2nd Generation API of Google’s open source software library for Deep Learning. The examples and handson would all be made in TensorFlow.


This course is intended for engineers seeking to use TensorFlow for their Deep Learning projects

After completing this course, delegates will:

  • have a good understanding on deep neural networks(DNN), CNN and RNN
  • understand TensorFlow’s structure and deployment mechanisms
  • be able to carry out installation / production environment / architecture tasks and configuration
  • be able to assess code quality, perform debugging, monitoring
  • be able to implement advanced production like training models, building graphs and logging

Course Outline

Part 1 – Deep Learning and DNN Concepts

Introduction AI, Machine Learning & Deep Learning

  • History, basic concepts and usual applications of artificial intelligence far Of the fantasies carried by this domain
  • Collective Intelligence: aggregating knowledge shared by many virtual agents
  • Genetic algorithms: to evolve a population of virtual agents by selection
  • Usual Learning Machine: definition.
  • Types of tasks: supervised learning, unsupervised learning, reinforcement learning
  • Types of actions: classification, regression, clustering, density estimation, reduction of dimensionality
  • Examples of Machine Learning algorithms: Linear regression, Naive Bayes, Random Tree
  • Machine learning VS Deep Learning: problems on which Machine Learning remains Today the state of the art (Random Forests & XGBoosts)

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

  • Reminder of mathematical bases.
  • Definition of a network of neurons: classical architecture, activation and
  • Weighting of previous activations, depth of a network
  • Definition of the learning of a network of neurons: functions of cost, back-propagation, Stochastic gradient descent, maximum likelihood.
  • Modeling of a neural network: modeling input and output data according to The type of problem (regression, classification …). Curse of dimensionality.
  • Distinction between Multi-feature data and signal. Choice of a cost function according to the data.
  • Approximation of a function by a network of neurons: presentation and examples
  • Approximation of a distribution by a network of neurons: presentation and examples
  • Data Augmentation: how to balance a dataset
  • Generalization of the results of a network of neurons.
  • Initialization and regularization of a neural network: L1 / L2 regularization, Batch Normalization
  • Optimization and convergence algorithms

Standard ML / DL Tools

A simple presentation with advantages, disadvantages, position in the ecosystem and use is planned.

  • Data management tools: Apache Spark, Apache Hadoop Tools
  • Machine Learning: Numpy, Scipy, Sci-kit
  • DL high level frameworks: PyTorch, Keras, Lasagne
  • Low level DL frameworks: Theano, Torch, Caffe, Tensorflow

Convolutional Neural Networks (CNN).

  • Presentation of the CNNs: fundamental principles and applications
  • Basic operation of a CNN: convolutional layer, use of a kernel,
  • Padding & stride, feature map generation, pooling layers. Extensions 1D, 2D and 3D.
  • Presentation of the different CNN architectures that brought the state of the art in classification
  • Images: LeNet, VGG Networks, Network in Network, Inception, Resnet. Presentation of Innovations brought about by each architecture and their more global applications (Convolution 1×1 or residual connections)
  • Use of an attention model.
  • Application to a common classification case (text or image)
  • CNNs for generation: super-resolution, pixel-to-pixel segmentation. Presentation of
  • Main strategies for increasing feature maps for image generation.

Recurrent Neural Networks (RNN).

  • Presentation of RNNs: fundamental principles and applications.
  • Basic operation of the RNN: hidden activation, back propagation through time, Unfolded version.
  • Evolutions towards the Gated Recurrent Units (GRUs) and LSTM (Long Short Term Memory).
  • Presentation of the different states and the evolutions brought by these architectures
  • Convergence and vanising gradient problems
  • Classical architectures: Prediction of a temporal series, classification …
  • RNN Encoder Decoder type architecture. Use of an attention model.
  • NLP applications: word / character encoding, translation.
  • Video Applications: prediction of the next generated image of a video sequence.

Generational models: Variational AutoEncoder (VAE) and Generative Adversarial Networks (GAN).

  • Presentation of the generational models, link with the CNNs
  • Auto-encoder: reduction of dimensionality and limited generation
  • Variational Auto-encoder: generational model and approximation of the distribution of a given. Definition and use of latent space. Reparameterization trick. Applications and Limits observed
  • Generative Adversarial Networks: Fundamentals.
  • Dual Network Architecture (Generator and discriminator) with alternate learning, cost functions available.
  • Convergence of a GAN and difficulties encountered.
  • Improved convergence: Wasserstein GAN, Began. Earth Moving Distance.
  • Applications for the generation of images or photographs, text generation, super-resolution.

Deep Reinforcement Learning.

  • Presentation of reinforcement learning: control of an agent in a defined environment
  • By a state and possible actions
  • Use of a neural network to approximate the state function
  • Deep Q Learning: experience replay, and application to the control of a video game.
  • Optimization of learning policy. On-policy && off-policy. Actor critic architecture. A3C.
  • Applications: control of a single video game or a digital system.

Part 2 – Theano for Deep Learning

Theano Basics

  • Introduction
  • Installation and Configuration

Theano Functions

  • inputs, outputs, updates, 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

  • Creation, Initializing, Saving, and Restoring TensorFlow variables
  • Feeding, Reading and Preloading TensorFlow Data
  • How to use TensorFlow infrastructure to train models at scale
  • Visualizing and Evaluating models with TensorBoard

TensorFlow Mechanics

  • Prepare the Data
  • Download
  • Inputs and Placeholders
  • Build the GraphS
    • Inference
    • Loss
    • Training
  • Train the Model
    • The Graph
    • The Session
    • Train Loop
  • Evaluate the Model
    • Build the Eval Graph
    • Eval Output

The Perceptron

  • Activation functions
  • The perceptron learning algorithm
  • Binary classification with the perceptron
  • Document classification with 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
  • Improving the way neural networks learn

Convolutional Neural Networks

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

Basic Introductions to be given to the below modules(Brief Introduction to be provided based 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

Leave a Reply

Your email address will not be published. Required fields are marked *