Cursos de Introduction Deep Learning & Neural Networks for Engineers

Nossos Clientes

Código do Curso

intrdplrngrsneuing

Duration

21 hours (usually 3 days including breaks)

Requisitos

Engineering level

Audience: Engineers, Data-Scientists wishing to learn neural networks / Deep Learning

 

Overview

Tipo: Formação teórica com candidaturas decididas a montante com os alunos em Lasagne ou Keras acordo com o grupo pedagógico

Método de ensino: apresentação, trocas e estudos de caso

A inteligência artificial, depois de ter interrompido muitos campos científicos, começou a revolucionar um grande número de setores econômicos (indústria, medicina, comunicação, etc.). No entanto, sua apresentação na grande mídia é muitas vezes fantasiosa, muito distante daquelas que são realmente as áreas de Machine Learning ou Deep Learning . O objetivo deste treinamento é fornecer aos engenheiros que já possuem um domínio de ferramentas de informática (incluindo uma base de programação de software) uma introdução ao Deep Learning e suas diversas áreas de especialização e, portanto, às principais arquiteturas de rede existentes. hoje. Se as bases matemáticas forem recuperadas durante o curso, um nível de matemática do tipo BAC + 2 é recomendado para maior conforto. É absolutamente possível pular o eixo matemático para manter apenas uma visão de "sistema", mas essa abordagem limitará enormemente sua compreensão do assunto.

Machine Translated

Programa do Curso

The course is divided into three separate days, the third being optional.

Day 1 - Machine Learning & Deep Learning: theoretical concepts

1. Introduction IA, 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)

2. 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.

3. 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

Day 2 - Convolutional and Recurrent Networks

4. 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

1x1 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.

5. 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.

Day 3 - Generational Models and Reinforcement Learning

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

- Presentation of the generational models, link with the CNNs seen in day 2

- 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.

7. 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.

Declaração de Clientes

★★★★★
★★★★★

Categorias Relacionadas

Cursos Relacionados

Descontos em Cursos

Boletim Informativo de Descontos

Nós respeitamos a privacidade dos seus dados. Nós não vamos repassar ou vender o seu email para outras empresas.
Você sempre poderá editar as suas preferências ou cancelar a sua inscriçāo.

is growing fast!

We are looking to expand our presence in Brazil!

As a Business Development Manager you will:

  • expand business in Brazil
  • recruit local talent (sales, agents, trainers, consultants)
  • recruit local trainers and consultants

We offer:

  • Artificial Intelligence and Big Data systems to support your local operation
  • high-tech automation
  • continuously upgraded course catalogue and content
  • good fun in international team

If you are interested in running a high-tech, high-quality training and consulting business.

Apply now!