Debugging neural network - part 1 | Let's learn - Neural networks from scratch in Go - 27
I started to compare my implementation and python code from the book. Comparing everything step-by-step. Interesting part that model creation involves randomisation and I had to deal with this fact to have the same data in both places. So I can properly debug it. And today I checked couple of ideas and prepared everything for further troubleshooting.
We study the book http://nnfs.io and implementing all the code with Golang instead of Python. The aim is to learn how neural networks are made inside and how it looks like to build is fully from the scratch without using frameworks like pytorch or tensorflow. We’ll have to find alternative in Go or reimplement some operations fully from the ground.
🖥️ You can support my channel, subscribe for more content or write directly to me: https://ko-fi.com/roman_v
📹 Main channel: / @_romanv_
✉️ Contact: [email protected]
💻 Code: https://github.com/RomanVolkov/nnfs_go
🎞️ Timestamps:
0:00 - Testing the dataset
9:34 - Mocking the dataset for both versions
32:00 - Mocking weights
👀 Disclaimer:
Views and opinions are my own and do not represent or reflect the opinions of my current or past employer(s).
#learncoding #softwareengineering #neuralnetwork #machinelearning #ai #golang