Introduction to Deep Learning (I2DL)
Our website offers an open and free introductory course on deep learning. The course is constructed as self-contained as possible, and enables self-study through lecture videos, PDF slides, cheatsheets, exercises (with solutions), and notebooks in both R (TensorFlow) and Python (PyTorch).
The lecture aims at providing a basic theoretical and practical understanding of neural networks. First, we cover the necessary background on traditional artificial neural networks, backpropagation, online learning, and regularization. Then we explain special methods used in deep learning, like drop-out and rectified linear units. We also talk about further advanced topics like convolutional layers, recurrent neural networks, auto-encoders, and generative adversarial networks (GANs). At the LMU Munich we teach this course for on MSc level (statiscs and data science).
What is not covered: (1) Predictive modeling (supervised learning). (2) Advanced deep learning. (3) Deep learning for NLP. (4) An in-depth coverage of optimization. We are working on separate open courses for the above topics.
- Topic 1: Introduction
- Chapter 01.01: Introduction
- Chapter 01.02: Single Neuron
- Chapter 01.03: XOR Problem
- Chapter 01.04: Single Hidden Layer NN
- Chapter 01.05: Single Hidden Layer Networks for Multi-Class Classification
- Chapter 01.06: MLP: Multi-Layer Feedforward Neural Networks
- Chapter 01.07: Optimization
- Chapter 01.08: Universal Approximation
- Chapter 01.09: Brief History
- Topic 2: Optimization Part-1
- Topic 03: Regularization
- Topic 04: Optimization Part 2
- Topic 05: Convolution Neural Networks
- Topic 06: Modern Convolutional Neural Networks and Adversarial Examples
- Chapter 06.01: 1D/ 2D/ 3D Convolutions
- Chapter 06.02: Important Types of Convolutions
- Chapter 06.03: Separable Convolutions and Flattening
- Chapter 06.04: Modern Convolutional Architecture - Part1
- Chapter 06.05: Modern Convolutional Architecture - Part2
- Chapter 06.06: Adversarial Robustness and Examples
- Topic 07: Deep Recurrent Neural Networks
- Topic 08: Modern Recurrent Neural Networks
- Chapter 09: Auto-Encoders
- Topic 10: Generative Adversarial Neural Networks (GANs)