Status Updates From Python Machine Learning

3 Types of ways to find local minima:
Batch: Updating weights over the whole sample
Stochastic: Updating one example at a time
Mini Batch: A compromise between both previous examples

if eta (the learning rate) is too small, the progress of minimizing the cost function will be slow. IF eta is too large, we will never converge: it will keep overshooting

Code implementation for Adaptive Linear Perceptron

The difference between Adaptive Linear Neuron and a perceptron:
Linear function vs. step function
update one example at a time, vs. a full set

The difference between Adaptive Linear Neuron and a perceptron

Coding a simple perceptron

Coding a simple perceptron

Coding a simple perceptron