Introduction to Deep Learning

Remi Genet

2025-04-03

Les cours de cette partie sont:

Activation Functions: Adding Non-linearity

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

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.

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.

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.

Model Training Fundamentals

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

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.