Back to Learning Center
Intermediate
Neural Networks
Understand neural network architectures from perceptrons to complex multi-layer networks, including activation functions, loss functions, and implementation details.
15-20 hours total14 modulesCertificate included
Course Modules
1
History of Neural Networks
From perceptrons to modern architectures
20 min
2
The Perceptron
The simplest neural unit
35 min
3
Multi-Layer Perceptrons
Building deeper networks
45 min
4
Activation Functions
ReLU, Sigmoid, Tanh, and more
40 min
5
Loss Functions
MSE, Cross-Entropy, and custom losses
45 min
6
Weight Initialization
Xavier, He, and best practices
30 min
7
Forward Propagation
How data flows through networks
40 min
8
Backward Propagation
Computing gradients efficiently
60 min
9
Gradient Descent Variants
Batch, mini-batch, and stochastic
50 min
10
Network Architecture Design
Choosing layers and neurons
55 min
11
Vanishing/Exploding Gradients
Problems and solutions
40 min
12
Skip Connections
ResNets and highway networks
35 min
13
Implementing from Scratch
Build a neural network in NumPy
90 min
14
PyTorch Fundamentals
Modern framework implementation
60 min