Learn how to determine the weight dimensions in a deep neural network. Understand the calculation for the 3rd layer weights with a clear explanation and example.
Table of Contents
Question
Given a deep neural network shown in the figure, what is the dimension of weight at the 3rd layer?
A. 5 x 4
B. 4 x 5
C. 4 x 3
D. 3 x 4
Answer
D. 3 x 4
Explanation
In a neural network, the weight dimensions between two layers are determined by the number of neurons in the current layer (input layer) and the next layer (output layer). Specifically:
- Rows of the weight matrix correspond to the number of neurons in the current (input) layer.
- Columns correspond to the number of neurons in the next (output) layer.
From the diagram:
- Third Layer (Input): The third layer has 3 neurons.
- Fourth Layer (Output): The fourth layer has 4 neurons.
Thus, the weight matrix connecting these layers will have dimensions 3 rows x 4 columns .
Why Option D Is Correct:
The weight matrix for the 3rd layer is determined by its connection to the next layer, which has 4 neurons. Therefore, its dimensions are 3×4.
Convolutional Neural Network CNN certification exam assessment practice question and answer (Q&A) dump including multiple choice questions (MCQ) and objective type questions, with detail explanation and reference available free, helpful to pass the Convolutional Neural Network CNN exam and earn Convolutional Neural Network CNN certification.