Lectures

Lecture 1

Introduction to Deep Learning

Lecture 2

Neural Networks

Backpropagation

Modular Design

Code

Lecture 3

Convolutional Neural Networks

Lecture 4

Regularization

Transfer Learning

Data Augmentation

Lecture 5

Recurrent Neural Networks

Long Short-Term Memory

Sequence-to-sequence

Lecture 6

Auto-encoders

Convolutional Auto-encoders

Denoising Auto-encoders

Masked Auto-encoders

Contractive Auto-encoders

Stacked Auto-encoders

Applications

Lecture 7

Generative Adversarial Networks

Cycle-consistent Generative Adversarial Networks

Lecture 8

Object Localization

Object Detection

Faster R-CNN

YOLO

Lecture 9

Curriculum Learning

Object Localization and Detection

Image Generation

Lecture 10

Distributional Semantics

Word Embeddings

Skip-gram Model

Continuous Bag-of-Words Model

Lecture 11

Lessons Learned from Word Embeddings

Document Embeddings

Lecture 12

Multi-Head Self-Attention

Language Transformers

Vision Transformers

Lecture 13

Adversarial Examples

Robustness to Adversarial Examples

Lecture 14

Diffusion Models

Labs

Lab1

Introduction to Tensorflow

CNNs for Image Classification

MNIST Dataset

Solution

Lab2

CNNs for Text Classification

Solution

Lab3

Transfer Learning

If possible, please download in advance the Caltech 101 dataset from this url

Lab4

Long Short-Term Memory networks (LSTM)

Solution

Lab5

Autoencoders and Variational Autoencoders

Solution

Lab6

Generative Adversarial Networks