Skip to main content
OverflowAI is here! AI power for your Stack Overflow for Teams knowledge community. Learn more

New answers tagged

0 votes

MNIST data shape

Convolutional Neural Networks (CNNs) typically require 3D (28 * 28 * 1) images rather than 2D (28 * 28) because they are designed to work with images that have spatial information across multiple ...
Khairul Bashar's user avatar
0 votes

how to include context / additional information in a NN

You can put an additional neuron in the first layer, but since you are using a CNN, it feels more natural to include this additional info via a neuron closer to the output of your network. ...
picky_porpoise's user avatar
1 vote

how to include context / additional information in a NN

what about an additional neuron in the 1st layer Yes, that's a sensible approach. But you probably want to take those values, {marine, fresh, unknown}, and one-hot encode them. Think of it as ...
J_H's user avatar
  • 1,110
0 votes

How will weights learn in CNN for multi class classification?

The learning happens as the weights are adjusted to minimize a loss function. In case of multiclass classification the output is C numbers where ...
Avi T's user avatar
  • 56

Top 50 recent answers are included