Problem 58882. Neural Nets: Activation functions

• Created by Richard Zapor

×

Like (0)

Difficulty:

(8)

Rate

• Solve Later   
• Add To GroupÂ

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

27.27% Correct | 72.73% Incorrect

• 44 Solutions
• 11 Solvers

Last Solution submitted on Mar 19, 2025

Last 200 Solutions

Solution Comments

ANNOUNCEMENT ×

Registration Now Open for MathWorks AUTOMOTIVE CONFERENCE 2025

Hello Community, We're excited to announce that registration is now open for the...

Problem Recent Solvers11

Suggested Problems

• Bullseye Matrix

  5979 Solvers

• Remove the polynomials that have positive real elements of their roots.

  1703 Solvers

• 2 b | ~ 2 b

  400 Solvers

• Tricky timing

  179 Solvers

• Matrix with different incremental runs

  528 Solvers

More from this Author308

• Santa's Cards

  3 Solvers

• ismember: Enhanced Performance for 'rows' and width - Speed Scoring (66% savings)

  20 Solvers

• Kaggle: Planetoid Game of Life - Solve 3000 of 50000 Puzzles

  3 Solvers

• GJam 2011 Africa Qual A: Maximum Loop Size

  15 Solvers

• ICFP 2023: Orchestra, Place Band members to maximize Audience net Happiness

  2 Solvers