GATE 2026 DA – Question 56

Machine Learning · Multi-layer perceptron and feed-forward neural networks · 2 marks · Numerical answer

Consider a fully-connected feed-forward multi-layer perceptron. It has 30 neurons in the input layer, followed by two hidden layers and an output layer. The first hidden layer has 4 neurons and the second hidden layer has 3 neurons. The output layer has only one neuron. Assume that no bias parameters are used.

The number of learnable parameters in the multi-layer perceptron is __________ . (*Answer in integer*)

Practise this question in The GATE Grind →

Show answer and explanation

Correct answer: 135

Explanation

A fully connected layer has one weight for every pair of neurons in consecutive layers. So the weights are $30 \times 4 = 120$ between the input and the first hidden layer, $4 \times 3 = 12$ between the hidden layers and $3 \times 1 = 3$ into the output. The total is $120 + 12 + 3 = 135$.