Neural Nets: Activation functions - MATLAB Cody - MATLAB Central

Problem 58882. Neural Nets: Activation functions

Difficulty:
(34)
Rate
Return values of selected Activation function type for value,vector, and matrices.
y=Activation(x,id); where id is 1:4 for ReLU, sigmoid, hyperbolic_tan, Softmax
ReLU: Rectified Linear Unit, clips negatives max(0,x) Trains faster than sigmoid
Sigmoid: Exponential normalization [0:1]
HyperTan: Normalization[-1:1] tanh(x)
Softmax: Normalizes output sum to 1, individual values [0:1] Used on Output node
Working though a series of Neural Net challenges from Perceptron, Hidden Layers, Back Propogation, ..., to the Convolutional Neural Net/Training for Handwritten Digits from Mnist.
Might take a day or two to completely cover Neural Nets in a Matlab centric fashion.
Essentially Out=Softmax(ReLU(X*W)*WP)
Solve

Solution Stats

20.34% Correct | 79.66% Incorrect
Last Solution submitted on Nov 07, 2025

Problem Comments

Solution Comments

Show comments
Join Cody Contest 2025 — Have Fun and Win Prizes!
...
We’re excited to invite you to Cody Contest 2025! 🎉 Pick a team,...
Dive Into Hands-On Learning at MATLAB EXPO 2025 – Register Now!
Get ready to roll up your sleeves at MATLAB EXPO 2025 –...
Devin in MATLAB EXPO
2
View Post

Problem Recent Solvers11

Suggested Problems

More from this Author308

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!