The GATE Grind

GATE Machine Learning: Multi-layer perceptron and feed-forward neural networks – Previous Year Questions

4 GATE previous year questions on Multi-layer perceptron and feed-forward neural networks (Machine Learning, Data Science and Artificial Intelligence) with answers and explanations, from every paper.

  1. GATE 2024 DA Q43 (2 marks, Multiple choice) – Consider the two neural networks (NNs) shown in Figures 1 and 2, with ReLU activation (ReLU(z) = \0, z\, z R). R denotes the set of real numbers. The…
  2. GATE 2025 DA Q42 (2 marks, Multiple choice) – Consider the neural network shown in the figure with inputs: u, v weights: a, b, c, d, e, f output: y R denotes the ReLU function, R(x) = (0, x).…
  3. GATE 2025 DA Q48 (2 marks, Multiple select) – Which of the following statements is/are correct about the rectified linear unit (ReLU) activation function defined as ReLU(x) = (x, 0), where x R?
  4. GATE 2026 DA Q56 (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…