What Is Deep Learning?

Deep Learning vs Machine Learning

Working of Neural Networks

How does Deep Learning work?

Neurons

Applications of Deep Learning

Limitations of Deep Learning

Quiz

Deep Learning Frameworks

Conclusion

Introduction

Course information

Why deep learning?

The perceptron

Perceptron example

Applying neural networks

Loss functions

Training and gradient descent

Backpropagation

Setting the learning rate

Batched gradient descent

Regularization: dropout and early stopping

Summary

Introduction

Course information

Why deep learning?

The perceptron

Perceptron example

From perceptrons to neural networks

Applying neural networks

Loss functions

Training and gradient descent

Backpropagation

Setting the learning rate

Batched gradient descent

Regularization: dropout and early stopping

Summary

What is Machine Learning?

What is Deep Learning?

Feedforward vs Backpropagation

Wrap up

Course Introduction

The Erlangen Programme

What will be after Deep Learning?

Graph Representation of Caffeine

General blueprint of geometric deep learning

Node-wise prediction

Circular Matrices

Spherical Convolution

Deformation invariance

Course Outline

Course Introduction

The Postulate of Parallels

Symmetries

MIT Summer Vision Project

The Lighthill Report

History of Convolutional Neural Networks

Chemical Abstract Service (CAS)

Early Graph Neural Networks

Hierarchical domains

Speakers of the course

Introduction

Deep learning in one slide

History of ideas and tools

Simple example in TensorFlow

TensorFlow in one slide

Deep learning is representation learning

Why deep learning (and why not)

Challenges for supervised learning

Key low-level concepts

Higher-level methods

Toward artificial general intelligence

History of Geometry

What is Machine Learning?

Scale-separation

Graph isomorphism test

GNN special cases

Manifold learning

The Convolution Theorem in Signal Processing

Gauge Transformations

Drug design

Conclusion

Deep learning example

End-to-end learning

Deep learning in robotics

History of Deep Learning

Why is Deep Learning so popular?

Deep neural networks

Examples

Detecting or locating objects of interest in an image

Introduction

What is Deep Learning

Introduction to Neural Networks

How do Neural Networks LEARN?

Core terminologies used in Deep Learning

Activation Functions

Loss Functions

Optimizers

Parameters vs Hyperparameters

Epochs, Batches & Iterations

Conclusion to Terminologies

Introduction to Learning

Unsupervised Learning

Reinforcement Learning

Regularization

Introduction to Neural Network Architectures

Fully-Connected Feedforward Neural Nets

Recurrent Neural Nets

Convolutional Neural Nets

Introduction to the 5 Steps to EVERY Deep Learning Model

1. Gathering Data

2. Preprocessing the Data

3. Training your Model

4. Evaluating your Model

Conclusion to the Course

Introduction and Themis AI

Background

Challenges for Robust Deep Learning

What is Algorithmic Bias?

Class imbalance

Latent feature imbalance

Debiasing variational autoencoder (DB-VAE)

DB-VAE mathematics

Uncertainty in deep learning

Types of uncertainty in AI

Aleatoric vs epistemic uncertainty

Estimating aleatoric uncertainty

Estimating epistemic uncertainty

Evidential deep learning

Recap of challenges

How Themis AI is transforming risk-awareness of AI

Capsa: Open-source risk-aware AI wrapper

Unlocking the future of trustworthy AI