Course Modules

Explore the complete curriculum with hands-on exercises and real-world applications

1

Introduction to Deep Learning

Foundations, history, and key concepts

Neural Networks Basics
Perceptrons
History of AI
3-4 hours
2

Neural Network Fundamentals

Architecture, forward/backward propagation

Backpropagation
Gradient Descent
Activation Functions
4-5 hours
3

Optimization and Training

SGD, Adam, learning rates, and regularization

Optimizers
Learning Rate Scheduling
Regularization
4-5 hours
4

Convolutional Neural Networks

CNNs for computer vision applications

Convolution
Pooling
CNN Architectures
5-6 hours
5

Advanced CNN Architectures

ResNet, DenseNet, and modern architectures

ResNet
DenseNet
EfficientNet
4-5 hours
6

Recurrent Neural Networks

RNNs, LSTMs, and sequence modeling

RNN Basics
LSTM
GRU
5-6 hours
7

Attention and Transformers

Self-attention, transformers, and BERT

Attention Mechanism
Transformers
BERT
6-7 hours
8

Generative Models

GANs, VAEs, and generative techniques

GANs
VAEs
Diffusion Models
5-6 hours
9

Reinforcement Learning

Q-learning, policy gradients, and RL applications

Q-Learning
Policy Gradients
Actor-Critic
6-7 hours
10

Deep Learning for NLP

Language models, embeddings, and text processing

Word Embeddings
Language Models
Text Classification
5-6 hours
11

Model Deployment and MLOps

Production deployment, monitoring, and scaling

Model Serving
Monitoring
CI/CD for ML
4-5 hours
12

Final Project and Presentations

Capstone project development and peer review

Project Planning
Implementation
Presentation
8-10 hours