Skip to content

Instantly share code, notes, and snippets.

@candh
candh / optim.py
Last active March 20, 2020 16:19
from my cs231n solution
import numpy as np
"""
This file implements various first-order update rules that are commonly used
for training neural networks. Each update rule accepts current weights and the
gradient of the loss with respect to those weights and produces the next set of
weights. Each update rule has the same interface:
def update(w, dw, config=None):
@candh
candh / guide.md
Last active November 20, 2022 10:44
Hacker's guide to Writing