PYTHON
Free Section Starter Challenge
25 min
7. The Perceptron Algorithm & Decision Boundaries
Overview: Train a single-layer artificial neuron using iterative weight delta updates.
Concept & Syntax Guide
A perceptron calculates a weighted sum of inputs $\sum w_i x_i + b$ and passes it through a step activation threshold. If a sample is misclassified, weights are adjusted via $w_i \leftarrow w_i + \eta (y - \hat{y}) x_i$. For linearly separable data, the perceptron learning rule is guaranteed to converge.
Hands-On Practice Exercise
Train Perceptron to Convergence
Simulate perceptron weight updates over 4 epochs to reach target weights [0.2, 0.4].
Target Output:
Perceptron converged in 4 epochs: Weights [0.2, 0.4]
Need a hint? Click here to reveal
Hint: Check syntax carefully and make sure your code contains:
Perceptron converged in 4 epochs: Weights [0.2, 0.4]
1
2
3
4
5
6
7
8
9
10
2
3
4
5
6
7
8
9
10