neural-network-from-scratch icon indicating copy to clipboard operation
neural-network-from-scratch copied to clipboard

Implementation of a neural network from scratch in python.

Results 5 neural-network-from-scratch issues
Sort by recently updated
recently updated
newest added

Made following changes: - in testing , mndata.load_training() was called , changed it to mndata.load_testing() - modularised classify_mnist.py - minor change to neuralnetwrok.py ( For readability , nothing else) -...

== EPOCH: 1 / 5 == Training with 2001 / 60000 /Users/dikshant/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:101: RuntimeWarning: divide by zero encountered in log /Users/dikshant/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:101: RuntimeWarning: invalid value encountered in multiply Training with 59951 /...

Class names are usually CamelCased, and Python code should follow PEP to maximize readability. The importance of readability is to ensure fellow programmers can better learn from code and track...

Added `requirements.txt` and `environment.yml` files in order to facilitate with creating a virtual environment for this project. I've also refactored the code in order to make it PEP8 compliant.

Add inverted dropout implementation.

enhancement