GATE DA 2024 — Question 43

Supervised Learningmulti-layer perceptron, feed-forward neural networkMCQ2 marks · −2/3 if wrongMedium

Consider the two neural networks (NNs) shown in Figures 1 and 2, with \(ReLU\) activation (\(ReLU(z) = \max\{0, z\}, \forall z \in \mathbb{R}\)). \(\mathbb{R}\) denotes the set of real numbers. The connections and their corresponding weights are shown in the Figures. The biases at every neuron are set to 0. For what values of \(p, q, r\) in Figure 2 are the two NNs equivalent, when \(x_1, x_2, x_3\) are positive?
Question image
  1. A
    \(p = 36, q = 24, r = 24\)
  2. B
    \(p = 24, q = 24, r = 36\)
  3. C
    \(p = 18, q = 36, r = 24\)
  4. D
    \(p = 36, q = 36, r = 36\)
Practise the full 2024 paper
Challenge a friend: WhatsApp Telegram
Recommended book · affiliate linkComputer Networks (Tanenbaum)Layers, routing, TCP/IP and error control, explained clearly.
Practise more on multi-layer perceptron, feed-forward neural networkTimed, in the real exam interface · free to start

A GATE question every morning

One real past-paper question every morning for your branch, answer hidden until you tap. Free on Telegram.

Join
Stuck? Ask in the student group