Hidden Layer Influence example with Simple Python
import numpy as np def sigmoid(x): return 1 / (1 + np.exp(-x)) # Input X = np.array([1, 0]) # Hidden layer W_hidden = np.array([[0.5, 0.4], [0.3, 0.7]]) b_hidden = np.array([-0.3, -0.1]) z_hidden = np.dot(X, W_hidden) + b_hidden a_hidden = sigmoid(z_hidden) # Output layer W_output = np.array([0.6, 0.9]) b_output = -0.2 z_output = np.dot(a_hidden, W_output) + b_output a_output = sigmoid(z_output) print(f"Prediction (Happiness Probability): {a_output:.2f}")
Summary
Layer | Role |
---|---|
Input | Takes raw data |
Hidden | Learns non-obvious patterns (feature builders) |
Output | Combines those patterns into a final prediction |
The hidden layer is where “understanding” happens.