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)
ANSWER
The network has 135 learnable parameters.
Official answer: 135Source: Official answer key, GATE 2026 DA (IIT Guwahati)
With no bias parameters, the learnable parameters are only the weights on the connections between consecutive layers.
In a fully-connected layer pair, every neuron of one layer connects to every neuron of the next, so a pair with and neurons has weights.
Input to hidden layer 1: .
Hidden layer 1 to hidden layer 2: .
Hidden layer 2 to output: .
Total:
KEY IDEA
With no biases, count one weight per connection between adjacent layers: the sum of the products of consecutive layer sizes, .
WATCH OUT FOR
Adding a bias for each neuron out of habit (which would give ), or adding the layer sizes instead of multiplying consecutive pairs.
From the GATE 2026 DA paper. Every question of this paper · Download the full paper · All 5 Neural networks questions, with notes
