10.1: Introduction to Neural Networks - The Nature of Code
Why Stack Overflow recommends it
Stack Overflow users link it as the starting point of a playlist for people who want to build a neural network from scratch in plain code instead of using TensorFlow.
Recommended by 2 people across 2 different months, 2018 to 2019.
What it is
The first video in Daniel Shiffman's Coding Train neural networks series. It gives a short introduction to neural networks, covering Tariq Rashid's book Make Your Own Neural Network, a basic neuron model, and the perceptron, then previews upcoming videos.
What people said
Recommends Wulf · 2018-04 · Stack Overflow · on “How does a Neural Network calculate the sum of the weights?”
Look this playlist. You learn how to implement your on nn. Shiffmann Coding Train Neurol Network [this video] , Feedforward Algorithm Part 1 [LINK]
Recommends BeastCoder · 2019-12 · Stack Overflow · on “How much freedom does TensorFlow take away from pure Python?”
For anyone reading this I am going to share my thoughts. I chose to take the route of pure python with nothing like TensorFlow. I heard from other people that TensorFlow could take away an understanding that beginners need. At first, it was really hard for me to find anything that could help, but then I found everything all at once. The following links are the resources I used. Theory: The first 2-4 videos of this series by 3blue1brown: [LINK] All of the videos in this series by 3blue1brown: [LINK] Implementation: This video by the coding train: [LINK] Additional links for the calculus are: [LINK] , [LINK] And this entire series by the coding train: [this video] Summary And that is it, that is al
Cites eyal mazuz · 2018-02 · Stack Overflow · on “NN don't evaluate well with back propagation algorithm”
I've tried to create a basic NN using the book "Make Your Own Neural Network" by Tariq Rashid and using the coding train videos: [this video] and the nn.js class on the coding train git as a reference [LINK] I writing the NN network in java, and I tried just like in the playlist to train the network on XOR after I succeeded in doing a single perceptron. but for some reason, even though my code is similar to what the book is doing and same in the videos (except in the videos he using JS). when I train the network for around 500000 times with randomized data set of XOR inputs (total of 4 input [1,0] [0,1] [0,0] [1,1]). when I giving it to guess after the training the all the 4 options I get results