Question

Homework 3 Suppose, you are needed to develop an image classifier to separate four classes with 3x3 images. The classes are, +, -, x, and / Develop a convolution neural net with a convolution, pooling and fully connected layer. Show the filters for each character.

          Homework 3
Suppose, you are needed to develop an image
classifier to separate four classes with 3x3 images. The
classes are, +, -, x, and /
Develop a convolution neural net with a convolution,
pooling and fully connected layer. Show the filters for
each character.

Homework 3
Suppose, you are needed to develop an image
classifier to separate four classes with 3x3 images. The
classes are, +, -, x, and /
Develop a convolution neural net with a convolution,
pooling and fully connected layer. Show the filters for
each character.

Added by Kevin P.

Computer Science and Information Technology

Trishna Knowledge Systems 2018 Edition

Instant Answer

Solved by Expert Md.Daniyal Arshad

Step 1

Since we are dealing with 3x3 images, we can create a numpy array to represent each image. Let's assign a value of 1 for the pixels that are filled and 0 for the empty pixels. Here's an example of how we can represent the images: ``` + = np.array([[0, 1, 0], Show more…

Show all steps

Thanks for your feedback!

Homework 3 Suppose you are needed to develop an image classifier to separate four classes with 3x3 images. The classes are +, -, *, and /. Develop a convolutional neural net with a convolution, pooling, and fully connected layer. Show the filters for each character.