← Back to portal

First Neural Network in Keras

Build and train a neural network from scratch concepts to Keras

0% · 0 of 8 steps completed · ~120 min · From neurons to trained models
1
What is a Neuron?
Weighted sum + activation
2
Activation Functions
ReLU, sigmoid, and softmax
3
Build a Network
Layers, widths, and parameter counts
4
The Forward Pass
Data flows through layers
5
The Training Loop
Epochs, batches, and loss curves
6
Overfitting
When the model memorises instead of learns
7
Neural Net vs Baseline
Is deeper always better?
8
When to Go Deep
The right tool for the job