intrdplrngrsneuing
21 hours (usually 3 days including breaks)
Engineering level
Audience: Engineers, Data-Scientists wishing to learn neural networks / Deep Learning
Тип: Теоретичне навчання з додатками, що вирішуються вгору за течією зі студентами на Лазаньї чи Keras відповідно до педагогічної групи
Методика навчання: презентація, обмін та тематичні дослідження
Штучний інтелект, порушивши багато наукових галузей, почав революціонувати велику кількість галузей економіки (промисловість, медицина, комунікації тощо). Тим не менш, його представлення у великих ЗМІ часто є фантазією, дуже далеко від тих, що є насправді сферами Machine Learning чи Deep Learning . Мета цього тренінгу - надати інженерам, які вже володіють комп'ютерними інструментами (включаючи базу програмування програмного забезпечення), ознайомлення з Deep Learning та його різними напрямами спеціалізації, а отже, і до основних існуючих мережевих архітектур сьогодні. Якщо під час курсу відкликаються математичні бази, для більшої комфортності рекомендується рівень математики типу BAC + 2. Абсолютно можливо пропустити математичну вісь, щоб зберегти лише "системне" бачення, але такий підхід дуже обмежить ваше розуміння теми.
Machine Translated
The course is divided into three separate days, the third being optional.
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
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.
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.
.jpg "international air transport association (iata)")
We are looking to expand our presence in Ukraine!
If you are interested in running a high-tech, high-quality training and consulting business.
Apply now!
