Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions lessons/04_ML_deep_learning/01_deep_intro.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
# Intro to Deep Learning
Welcome to the exciting world of deep learning! In this lesson, we will introduce you to the fundamental concepts of deep learning and neural networks. Deep learning is a subset of machine learning that focuses on using multi-layered neural networks to model complex patterns in data. It has revolutionized various fields, including computer vision, natural language processing, and speech recognition.

Deep learning models are loosely inspired by biological neural networks, which are made up of many interconnected neurons. While artificial neural networks are much simpler than real brains, they share an important idea: complex behavior can emerge from many simple units working together. By stacking these units into layers, neural networks can learn increasingly rich representations of data.

In this lesson, we will focus on intuition rather than details. The goal is to understand what neural networks are and why they work, before we start building them.

We will cover the following topics:
- **Neurons: real and artificial**: how do real, and artificial neural networks, function?
- **Neural Network Basics**: How neural networks are structured, how data flows through them, and how networks are trained.
- **The deep learning revolution**: How neuralnetworks went from early limitations to modern success.
- **Deep learning frameworks**: A brief overview look at modern tools that make deep learning practical, setting the stage for hands-on work with PyTorch.

# Neurons: Real and Artificial
We will discuss how biological neural networks function and how they have inspired the design of nodes in artificial neural networks (including activation functions)

# Neural network basics
We will discuss the basic structure of neural networks, including layers (input, hidden, and output), weights, and how data flows through the network. We will also discuss the concept of depth in neural networks and how it relates to deep learning, and how neural networks are *trained* using backpropagation.

# The deep learning revolution
We will provide a brief overview of the history of deep learning, highlighting key milestones and breakthroughs that have shaped the field, from machine vision to natural language processing.

# Deep learning frameworks
We will introduce popular deep learning frameworks such as TensorFlow and PyTorch, which provide powerful tools for building and training neural networks. This will lead us naturally into our hands-on work with PyTorch in the following lessons.