Course Outline
The course is divided into three distinct days, with the third day being optional.
Day 1 - Machine Learning & Deep Learning: Theoretical Concepts
1. Introduction to AI, Machine Learning & Deep Learning
- History, fundamental concepts, and common applications of artificial intelligence, distancing ourselves from the myths surrounding the field.
- Collective intelligence: Aggregating shared knowledge among many virtual agents.
- Genetic algorithms: Evolving a population of virtual agents through selection.
- Standard Machine Learning: Definition.
- Types of tasks: Supervised learning, unsupervised learning, reinforcement learning.
- Types of actions: Classification, regression, clustering, density estimation, dimensionality reduction.
- Examples of Machine Learning algorithms: Linear Regression, Naive Bayes, Random Forest.
- Machine Learning VS Deep Learning: Problems where Machine Learning remains the state-of-the-art today (Random Forests & XGBoosts).
2. Fundamental Concepts of Neural Networks (Application: Multi-layer Perceptron)
- Review of mathematical basics.
- Definition of a neural network: Classic architecture, activation functions, weighting of previous activations, network depth.
- Definition of neural network learning: Cost functions, back-propagation, stochastic gradient descent, maximum likelihood.
- Modeling a neural network: Modeling input and output data according to the type of problem (regression, classification, etc.). Curse of dimensionality. Distinction between multi-feature data and signal. Choosing a cost function based on the data type.
- Approximating a function with a neural network: Presentation and examples.
- Approximating a distribution with a neural network: Presentation and examples.
- Data Augmentation: How to balance a dataset.
- Generalization of neural network results.
- Initializations and regularizations of a neural network: L1/L2 regularization, Batch Normalization, etc.
- Optimizations and convergence algorithms.
3. Standard ML/DL Tools
A brief presentation outlining advantages, disadvantages, position in the ecosystem, and usage is planned.
- Data management tools: Apache Spark, Apache Hadoop.
- Standard Machine Learning tools: Numpy, Scipy, Scikit-learn.
- 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, kernel usage, padding & stride, feature map generation, pooling layers. 1D, 2D, and 3D extensions.
- Presentation of various CNN architectures that set the state-of-the-art in image classification: LeNet, VGG Networks, Network in Network, Inception, ResNet. Presentation of the innovations introduced by each architecture and their broader applications (1x1 Convolution or residual connections).
- Use of attention models.
- Application to a standard classification case (text or image).
- CNNs for generation: Super-resolution, pixel-by-pixel segmentation. Presentation of the main feature map augmentation strategies for image generation.
5. Recurrent Neural Networks (RNN).
- Presentation of RNNs: Fundamental principles and applications.
- Fundamental operation of the RNN: Hidden activation, backpropagation through time, unrolled version.
- Evolution toward GRUs (Gated Recurrent Units) and LSTMs (Long Short-Term Memory). Presentation of the different states and evolutionary improvements brought by these architectures.
- Convergence problems and vanishing gradient.
- Types of classic architectures: Time series prediction, classification, etc.
- RNN Encoder-Decoder architecture. Use of an attention model.
- NLP applications: Word/character encoding, translation.
- Video applications: Predicting the next image in a video sequence.
Day 3 - Generative Models and Reinforcement Learning
6. Generative Models: Variational AutoEncoder (VAE) and Generative Adversarial Networks (GAN).
- Presentation of generative models, link with CNNs covered on Day 2.
- Autoencoder: Dimensionality reduction and limited generation.
- Variational Autoencoder: Generative model and approximation of data distribution. Definition and use of latent space. Reparameterization trick. Applications and observed limitations.
- Generative Adversarial Networks: Fundamental principles. Two-network architecture (generator and discriminator) with alternating learning, available cost functions.
- GAN convergence and difficulties encountered.
- Improved convergence: Wasserstein GAN, BeGAN. Earth Mover's Distance.
- Applications in image or photograph generation, text generation, super-resolution.
7. Deep Reinforcement Learning.
- Presentation of reinforcement learning: Controlling an agent in an environment defined by a state and possible actions.
- Use of a neural network to approximate the state function.
- Deep Q-Learning: Experience replay, and application to video game control.
- Policy optimization. On-policy & off-policy. Actor-Critic architecture. A3C.
- Applications: Control of a simple video game or a digital system.
Requirements
Engineer level
Testimonials (2)
The adaptation of exos to our context and the consideration of our request
Amel Guetat - EURO-INFORMATION DEVELOPPEMENTS
Course - Fraud Detection with Python and TensorFlow
Machine Translated
The training was organized and well-planned out, and I come out of it with systematized knowledge and a good look at topics we looked at
