Remi Genet

2025-04-03

Rémi Genet

Star this website on Github

Introduction à Python:

Toutes les bases pour bien démarrer !

Un petit aperçu des réjouissances ci-dessous, mais pour commencer…

From Traditional Models to Deep Learning

Foundations of machine learning and econometric modeling, introducing deep learning as a flexible function approximation paradigm for financial problems.

The Multi-Layer Perceptron (MLP)

The MLP is the fundamental building block of deep learning. This chapter breaks down its biological inspiration, mathematical formulation, and financial applications.

Automatic Differentiation: The Engine of Deep Learning

A technical deep-dive into gradient computation methods, highlighting why automatic differentiation became the backbone of modern machine learning.

Computation Backends & Keras 3

Understanding the ecosystem of deep learning frameworks and how Keras 3 abstracts hardware acceleration through backend engines.

GPUs and Deep Learning: When Hardware Matters

Understanding the role of specialized hardware in accelerating neural network training, and why modern AI relies on GPUs.

Keras Fundamentals: Models & Layers

Understanding Keras’ core abstractions for building neural networks through its layered architecture and model composition paradigms.

Keras Matrix Operations: The Building Blocks

Understanding fundamental matrix operations in Keras that form the basis of all neural network computations, with a focus on practical examples and shape manipulation.

Activation Functions: Adding Non-linearity

Understanding activation functions, their mathematical properties, and roles in neural networks.

Model Training Fundamentals

Essential workflow for training neural networks in Keras, covering the basic steps from model creation to prediction.

Sequential Data Processing: From MLPs to RNNs

Understanding the challenges of processing financial time series data and why we need recurrent neural networks.

Long Short-Term Memory Networks (LSTM)

Understanding the mathematics and principles behind LSTM networks, their historical significance, and practical considerations.

Modern RNN Architectures

Understanding modern RNN variants and their mathematical foundations.

RNN Limitations: Computational Challenges

Understanding the computational limitations of RNNs and their impact on training efficiency.

Understanding the Training Loop

Deep dive into the fundamental training loop in deep learning, understanding how models learn step by step.

Understanding Optimizers

Deep dive into optimization algorithms in deep learning, their mathematical foundations and practical applications.

Understanding Callbacks

Understanding callbacks in deep learning: how to monitor and control training processes.

Training Parameters and Practical Considerations

Understanding key training parameters and practical considerations in deep learning.

Residual Connections and Gating Mechanisms

Advanced Concepts

Understanding fundamental building blocks that enable training of deep neural networks: residual connections and gating mechanisms.

Convolutional Layers: From Images to Time Series

Advanced Concepts

Understanding convolution operations in neural networks and their applications beyond computer vision.

Neural Network Embeddings: Learning Meaningful Representations

Advanced Concepts

Understanding embeddings in neural networks: from discrete entities to continuous vector spaces.

Attention Mechanisms: Learning What to Focus On

Advanced Concepts

Understanding attention mechanisms in neural networks: from basic self-attention to multi-head architectures.

Encoder-Decoder Architectures

Advanced Concepts

Understanding encoder-decoder architectures: principles, mathematics, and applications in sequence-to-sequence tasks.