Neural networks — Study Path Agent

Chapter 1

Fundamentals of neural networks

1

Neuron models and activation functions

2

Forward pass, backpropagation intuition

3

Loss functions basics

Chapter 2

Architectures overview

4

Feedforward networks

5

Convolutional neural networks

6

Recurrent neural networks

7

Transformers and attention

Chapter 3

Training fundamentals

8

Gradient descent and variants

9

Optimization algorithms

10

Learning rate scheduling

11

Mini-batch vs full-batch training

Chapter 4

Regularization techniques

12

Regularization: L1/L2, dropout

13

Normalization and stability (BatchNorm, LayerNorm)

14

Data augmentation techniques

Chapter 5

Evaluation and deployment

15

Evaluation metrics for NN performance

16

Deployment considerations for neural nets

17

Interpretability basics