Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
The course is separated into three distinct days, the third being optional.
Day 1 - Machine Learning & Deep Learning: theoretical concepts
1. AI Introduction, Machine Learning & Deep Learning
- History, fundamental concepts and usual applications of artificial intelligence far from the fantasies carried by this field
- Collective intelligence: aggregate knowledge shared by numerous virtual agents
- Genetic algorithms: evolving a population of virtual agents by selection
- Machine Learning usual: definition.
- Types of tasks: supervised learning, unsupervised learning, reinforcement learning
- Types of actions: classification, regression, clustering, density estimation, dimensionality reduction
- Examples of algorithms Machine Learning: Linear regression, Naive Bayes, Random Tree
- Machine learning VS Deep Learning: problems on which Machine Learning remains the state of the art today (Random Forests & XGBoosts)
2. Fundamental concepts of a neural network (Application: multi-layer perceptron)
- Reminder of mathematical basics.
- Definition of a neural network: classic architecture, activation and weighting functions of previous activations, depth of a network
- Definition of learning a neural network: cost functions, back-propagation, stochastic gradient descent, maximum likelihood.
- Modeling of a neural network: modeling of input and output data according to the type of problem (regression, classification, etc.). Curse of dimensionality. Distinction between multi-feature data and signal. Choice of a cost function according to the data.
- Approximate a function using a neural network: presentation and examples
- Approximating a distribution using a neural network: presentation and examples
- Data Augmentation: how to balance a dataset
- Generalization of the results of a neural network.
- Initializations and regularizations of a neural network: L1/L2 regularization, Batch Normalization...
- Optimizations and convergence algorithms.
3. Common ML/DL tools
A simple presentation with advantages, disadvantages, position in the ecosystem and use is planned.
- Data management tools: Apache Spark, Apache Hadoop
- Common tools Machine Learning: Numpy, Scipy, Sci-kit
- High-level DL 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 CNNs: fundamental principles and applications
- Fundamental operation of a CNN: convolutional layer, use of a kernel, padding & stride, generation of feature maps, 'pooling' type layers. 1D, 2D and 3D extensions.
- Presentation of the different CNN architectures that have brought the state of the art to image classification: LeNet, VGG Networks, Network in Network, Inception, Resnet. Presentation of the innovations brought by each architecture and their more global applications (1x1 Convolution or residual connections)
- Use of an attention model.
- Application to a usual classification scenario (text or image)
- CNNs for generation: super-resolution, pixel-to-pixel segmentation. Presentation of the main strategies for augmenting feature maps for generating an image.
5. Recurrent Neural Networks (RNN).
- Presentation of RNNs: fundamental principles and applications.
- Fundamental operation of the RNN: hidden activation, back propagation through time, unfolded version.
- Developments towards GRU (Gated Recurrent Units) and LSTM (Long Short Term Memory). Presentation of the different states and the developments brought about by these architectures
- Convergence and vanishing gradient problems
- Types of classic architectures: Prediction of a time series, classification...
- RNN Encoder Decoder type architecture. Using 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 generational models, link with CNNs seen on day 2
- Auto-encode: dimensionality reduction and limited generation
- Variational Auto-encoder: generational model and approximation of the distribution of data. Definition and use of latent space. Reparameterization trick. Applications and observed limits
- Generative Adversarial Networks: fundamental principles. Two-network architecture (generator and discriminator) with alternating learning, cost functions available.
- Convergence of a GAN and difficulties encountered.
- Improved convergence: Wasserstein GAN, BeGAN. Earth Moving Distance.
- Applications for generating images or photographs, generating text, super
resolution.
7.DeepReinforcement Learning.
- Presentation of reinforcement learning: control of an agent in an environment defined by a state and possible actions
- Using a neural network to approximate the state function
- Deep Q Learning: experience replay, and application to the control of a video game.
- Optimizations of the learning policy. On-policy && off-policy. Actor critical architecture. A3C.
- Applications: control of a simple video game or a digital system.
Requirements
Engineer level
21 Hours
