Deep Learning and Neural Networks

Classifications / Machine Learning / Deep Learning and Neural Networks

TRACK

How neural networks build representations, receive credit through gradients, train reliably, encode architectural bias, transfer knowledge, and cross the boundary into inference systems.

How does a neural network turn data into useful representations, propagate credit through many layers, train without losing signal, and become an inference artifact whose limits I can inspect?

32 lessons

Continues to AI Research Literacy and Paper Reading/ Diffusion, Audio, Video, and Generative Media/ GPU Systems and Accelerators/ LLM Foundations/ ML Systems and Training Infrastructure/ Multimodal Foundations and Vision-Language Models/ Reinforcement Learning and Sequential Decision Making/ Representation Learning and Self-Supervision

LESSONS

1. 001
   Perceptron Foundations
   [TODO]
2. 002
   Activation Functions and Nonlinearity
   [TODO]
3. 003
   Feedforward Propagation and Layered Representation
   [TODO]
4. 004
   Loss Functions and Error Signals
   [TODO]
5. 005
   Chain Rule & Computational Graphs
   [TODO]
6. 006
   Backpropagation Algorithm - Step by Step
   [TODO]
7. 007
   Implementing Backpropagation from Scratch
   [TODO]
8. 008
   Gradient Checking & Debugging
   [TODO]
9. 009
   SGD Variants - Momentum, RMSprop, Adam
   [TODO]
10. 010
    Learning Rate Schedules
    [TODO]
11. 011
    Weight Initialization
    [TODO]
12. 012
    Batch Normalization
    [TODO]
13. 013
    Dropout & Regularization Techniques
    [TODO]
14. 014
    Data Augmentation Strategies
    [TODO]
15. 015
    Introduction to PyTorch
    [TODO]
16. 016
    Building Production Neural Networks
    [TODO]
17. 017
    Convolution Operation
    [TODO]
18. 018
    Pooling and CNN Architecture
    [TODO]
19. 019
    Classic CNN Architectures
    [TODO]
20. 020
    Building CNNs in PyTorch
    [TODO]
21. 021
    RNN Fundamentals
    [TODO]
22. 022
    LSTM and GRU
    [TODO]
23. 023
    Sequence-to-Sequence Models
    [TODO]
24. 024
    Text Generation with RNNs
    [TODO]
25. 025
    Transfer Learning Fundamentals
    [TODO]
26. 026
    Fine-Tuning Pre-trained Models
    [TODO]
27. 027
    Embeddings and Feature Extraction
    [TODO]
28. 028
    Domain Adaptation and Few-Shot Learning
    [TODO]
29. 029
    Model Optimization for Production
    [TODO]
30. 030
    Serving Models with APIs
    [TODO]
31. 031
    Containerization with Docker
    [TODO]
32. 032
    Cloud Deployment CAPSTONE
    [TODO]

← Back to Machine Learning