This training is available in a private or personalized format. It can be provided in one of our training centres or at your offices. Call one of our consultants of submit a request online.

Call now at 1 877 624.2344

Duration: 3 days
Regular price: On request

Course outline

Reference : @Python Deep Learning with neural networks

Duration : 3 days

Prerequisites

Pré-requis pour suivre ce cours

Objectives

Objectifs du cours

Contents

Introduction

Basic concepts: (Fully connected neural networks, layers, forward propagation)
Nonlinear activation functions
Loss functions for supervised learning
Initialization and regularization
Backward propagation
Optimization and learning algorithms
Introduction to Pytorch
Use case: Optical Character Recognition (OCR)

Convolutional Neural Networks (CNN) for image recognition

Motivation and key-concepts (local connectivity, weight sharing)
Convolution: kernels, filters and feature maps
Aggregation, downsampling and pooling
Popular architectures: VGG, ResNet, GoogleNet
Image pre-processing
Using a pre trained neural network

Recurrent Neural Networks (RNN)

Motivation and key-concepts (windows size, memory, etc)
RNN most used architectures (LSTM, GRU), their losses and gradients
Discrete sequence: One hot encoding and embeddings
Application to classification
Application to sequence prediction

Representation learning

Autoencoders
Mutual information neural estimator
Deep Info Max
Contrastive Predictive Coding

Generative Models

Variational Autoencoders
GANs
Generation by reinforcement
Generation under condition
Style transfer
Evaluation of generative models

Advanced topics

Multi-task learning
Semi-supervised learning
Transfer learning
Debugging neural networks

Human

Digital Tools

Technology

Data Science

Organizational Strategy

Project Management

Python; Deep Learning with neural networks

Course outline