---
title: "Short note: Neural network, perceptron rule"
subject: "Data Mining"
chapter: 3
key: "semester_7/data_mining:neural-network-perceptron-note"
source: https://www.bctengineer.com/q/semester_7/data_mining/neural-network-perceptron-note
site: BCT Engineering
---

# Short note: Neural network, perceptron rule

Data Mining · Chapter 3: Classification

- Asked in: year not given, 3 marks
- Video: [Lec-48: Understanding Single Layer Perceptron (SLP) with Example | Machine Learning](https://www.youtube.com/watch?v=rvxd13IHx1Y) — Gate Smashers
- Answer checked by Claude Opus 5.5 (high effort) on 2026-10-14
- Page: https://www.bctengineer.com/q/semester_7/data_mining/neural-network-perceptron-note
- Whole chapter: https://www.bctengineer.com/md/semester_7/data_mining/chapter-3

## Question

Write a short note on the characteristics of Neural Network & Perceptron Learning rule.

## Short answer

Neural networks learn from examples by adjusting weights, can approximate non-linear functions, tolerate noise, and work in parallel. The perceptron learning rule updates weights as w_i(new) = w_i(old) + η(t - y)x_i, where η is learning rate, t target, y output; it converges for linearly separable data.

## Answer

#### Characteristics of neural networks
- Learn from examples by adjusting the **weights** of connections; need no explicit rules.
- Can approximate complex **non-linear** functions; multilayer networks are universal approximators.
- **Tolerant to noisy data** and able to classify patterns they were not trained on.
- Work in **parallel** (many simple neurons), and can be fast once trained.
- Inputs must be numeric (categorical data must be encoded and scaled to 0-1).
- Weaknesses: long training time, choice of topology and learning rate by trial, risk of local minima, and low interpretability (black box).

#### Perceptron and its learning rule
The **perceptron** is the simplest neural network: a single neuron that computes y = f(Σ wᵢxᵢ + b), with f a step function giving output 1 if the sum > 0, else 0 (or −1). It can classify only **linearly separable** classes (such as AND, OR, but not XOR).

**Perceptron learning rule** (error-correction): for each training example (x, target t) with actual output y:

wᵢ(new) = wᵢ(old) + η (t − y) xᵢ

where η is the learning rate (0 < η ≤ 1). The bias is updated as b = b + η(t − y).
- If the output is correct (t = y), weights do not change.
- If wrong, weights move toward (t > y) or away from (t < y) the input.

Training repeats over all examples (epochs) until all are classified correctly. For linearly separable data the rule converges in a finite number of steps (perceptron convergence theorem).

## Check yourself

The answer's key points as multiple-choice questions, with the correct option and why.

1. What can a single perceptron classify?
   A. XOR
   B. Any non-linear function
   C. Only linearly separable classes such as AND, OR
   D. Only unlabelled data
   Answer: C. XOR is not linearly separable. (Key point: Linear separability)

2. What is the perceptron update rule?
   A. wi(new) = wi(old) - eta xi only
   B. wi(new) = t - y
   C. wi(new) = wi(old) * eta
   D. wi(new) = wi(old) + eta (t - y) xi
   Answer: D. Weights change in proportion to the error. (Key point: Learning rule)

3. What happens to weights if the output equals the target?
   A. They do not change
   B. They are doubled
   C. They are reset to random
   D. They decrease by eta
   Answer: A. t - y = 0 so no update. (Key point: Correct output)

4. For linearly separable data the perceptron rule:
   A. Never converges
   B. Converges in a finite number of steps
   C. Converges only with a hidden layer
   D. Converges only if eta > 1
   Answer: B. This is the perceptron convergence theorem. (Key point: Convergence)

## Related in Data Mining

- [Sequential covering for rule induction](https://www.bctengineer.com/question.md?key=semester_7%2Fdata_mining%3Asequential-covering) — Data Mining, chapter 3

## Related in other subjects

- [Role of perceptron in neural network](https://www.bctengineer.com/question.md?key=semester_6%2Fartificial_intelligence%3Aperceptron-role) — Artificial Intelligence, chapter 6, asked 2×
- [Perceptron; neural network as OR gate](https://www.bctengineer.com/question.md?key=semester_6%2Fartificial_intelligence%3Aperceptron-or-gate) — Artificial Intelligence, chapter 6, asked 2×
- [Perceptron; neural network as XOR gate](https://www.bctengineer.com/question.md?key=semester_6%2Fartificial_intelligence%3Aperceptron-xor-gate) — Artificial Intelligence, chapter 6, asked 2×
- [Neural network, back-propagation, perceptron](https://www.bctengineer.com/question.md?key=semester_6%2Fartificial_intelligence%3Ann-bp-perceptron) — Artificial Intelligence, chapter 6