In normal neural network (perceptron): Suppose I have given a vector x and I want predict y with perceptron. Here, our basic assumption is y = W^{t}*x i.e, we assume y will be a linear combination of the x components, which is a natural thinking. In convolutional neural network: Here in case of i…

Hi, @Soumitra_Das ! To answer that, I’ll highlight the main differences between both approaches. Convolutions are not densely connected, so not all input nodes affect all output nodes. This gives convolutional layers more flexibility in learning. In addition, fully-connected layers become depende…

Why convolution operation?

Course Q&A Deep Learning Specialization Convolutional Neural Networks

Christian_Simonis September 25, 2022, 4:25pm 4

In addition, also with respect to other learners who read this and want more information on convolution.

You might wanna take a look at this thread: How to Calculate the Convolution?

Best regards
Christian

Topic		Replies	Views
C2W1 Graded Quiz Convolutional Neural Networks in TensorFlow week-module-1	2	526	February 16, 2023
Convolutional Neural Network, Activation functions AI Discussions	6	421	May 12, 2022
Pooling operations: why not adjust parameters through gradient descent? Convolutional Neural Networks week-module-1 , coursera-platform	2	34	August 2, 2024
Question on the benefit of CNN: sparsity? Convolutional Neural Networks coursera-platform	3	581	December 12, 2022
Convolution in CNN vs Convolution Operator Convolutional Neural Networks coursera-platform	3	754	June 7, 2022

Why convolution operation?

Related topics