Deep Learning

Journey from first principles to cutting-edge transformer systems through curated lectures, guided notebooks, and pragmatic engineering checklists.

Course Syllabus (PDF)Access Canvas
1

Introduction to Deep Learning

Foundations
Neural Networks Basics
Perceptrons
History of AI
Explore Module
2

Backpropagation

Foundations
Backpropagation
Gradient Descent
Activations
Explore Module
3

Optimization Foundations & Ablation Methodology

Foundations
Optimizers
LR Schedules
Regularization
Explore Module
4

Convolutional Neural Networks

CNN Architectures
Convolution
Pooling
Vision Models
Explore Module
5

Advanced CNN Architectures

CNN Architectures
ResNet
DenseNet
EfficientNet
Explore Module
6

Encoder Decoder Architectures

Encoder • Decoder
Seq2Seq
Encoder–Decoder
U-Net
Explore Module
7

Recurrent Neural Networks

Sequence Models
RNN Basics
LSTM
GRU
Explore Module
8

Attention Mechanism

Attention
Attention Basics
Q-K-V
Scaled Dot-Product
Explore Module
9

Transformer

Transformers
Self-Attention
Positional Encoding
Transformer
Explore Module
10

Transformer Models in Vision and Text

Transformers
ViT
BERT/T5/GPT
Scaling
Explore Module
11

Prompting, PEFT & Quantization

Modern LLM Stack
Prompting/RAG
PEFT
QLoRA
Explore Module
12

Multimodal Learning & GenAI

Modern LLM Stack
Multimodal
Diffusion
VAE
GAN
Explore Module