Intermediate
Deep Learning
Dive into deep neural networks, backpropagation, optimization techniques, and modern architectures including CNNs, RNNs, Transformers, and GANs.
20-30 hours total18 modulesCertificate included
Course Modules
1
Introduction to Deep Learning
What makes deep learning special
2
Neural Network Fundamentals
Neurons, layers, and activations
3
Backpropagation
The math behind learning
4
Optimization Algorithms
SGD, Adam, RMSprop explained
5
Regularization Techniques
Dropout, batch norm, weight decay
6
Convolutional Neural Networks
Architecture and applications
7
CNN Architectures
VGG, ResNet, EfficientNet
8
Recurrent Neural Networks
Sequential data processing
9
LSTM and GRU
Long-term dependencies
10
Attention Mechanisms
The foundation of transformers
11
Transformer Architecture
Self-attention and positional encoding
12
BERT and GPT
Pre-trained language models
13
Generative Adversarial Networks
Generator vs discriminator
14
Variational Autoencoders
Latent space representations
15
Transfer Learning
Leveraging pre-trained models
16
Model Interpretability
Understanding DL decisions
17
Deep Learning at Scale
Distributed training strategies
18
Capstone Project
Build an end-to-end DL system