Problem 58882. Neural Nets: Activation functions

• Created by Richard Zapor
• Appears in Guess the Logic! II

×

Like (1)

Difficulty:

(161)

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

21.43% Correct | 78.57% Incorrect

• 56 Solutions
• 11 Solvers

Last Solution submitted on Aug 14, 2025

Last 200 Solutions

Solution Comments

Problem Recent Solvers11

Suggested Problems

• Implement a ROT13 cipher

  1697 Solvers

• middleAsColumn: Return all but first and last element as a column vector

  626 Solvers

• Unique values without using UNIQUE function

  399 Solvers

• Close MATLAB with keyboard

  311 Solvers

• calculate linear convolution two vectors

  141 Solvers

More from this Author308

• Slitherlink IV: Recursive (medium size)

  1 Solvers

• ICFP 2023:Orchestra Solve all X Linear Stage Problems (23:27)

  1 Solvers

• AZPC Oddly Triangular: N=10/11/13/14 Digits 3/7/9 Part 3 of 5

  5 Solvers

• USC Fall 2012 ACM: Driving the Rover

  7 Solvers

• GJam 2014 China Rd B: Dragon Maze

  7 Solvers