Skip to content
Hallway
0:00 / 0:00

#backpropagation#neuralnetworks#machinelearning

Neural network tutorial: The back-propagation algorithm (Part 2)

Ryan Harris

5K subscribers • 1 video on Hallway

YouTube
  • Recommended by 1 person: 1 on Stack Overflow and its sister sites.
  • Presented by Ryan Harris
  • May be out of date. Uploaded 14 years ago, in an area where tools change fast.

Intermediate. Assumes working knowledge.

125K views14 years ago1 recommendation

AI and machine learningComputer scienceNeural networks and deep learningMath for machine learningAlgorithms

Ryan Harris explains the mathematical derivation and implementation of the backpropagation algorithm for neural networks.

This video continues the previous tutorial and goes from delta for the hidden layer through the completed algorithm. The presentation can be found here: db.tt/yq6X4bQS

Why it's here

1 person recommends this

What people say. Recommended as a reference for the mathematical formulas of backpropagation.

Moments people linked to

Robinon Data Science Stack Exchange • Recommends

I've been struggling with Neural Networks for a while now. I get the math behind backpropagation. Still as reference I'm using the formulas from link to this video. The Network learns XOR: Prediction After Training: 0.0003508415406266712 Expected: 0.0 But basically doesn't learn anything on the MNIST dataset: Error after n trainings examples: - 0 Total Net Error: 4.3739634316135225 - 10000 Total Net Error: 0.4876292680858326 - 20000 Total Net Error: 0.39989816082272944 - 30000 Total Net Error: 0.49507443066631834 - 40000 Total Net Error: 0.5483594859079792 - 50000 Total Net Error: 0.5135921029479789 - 59000 Total Net Error: 0.4686434346776871 Prediction Expected - [0.0…
5View the answer