Skip to content

Instantly share code, notes, and snippets.

View Alfo5123's full-sized avatar
🐨

Alfredo De La Fuente Alfo5123

🐨
99 followers · 140 following
View GitHub Profile
@wdphy16
wdphy16 / Proposal for complex-valued optimization in Optax.md
Last active November 1, 2023 07:15

[RFC] Proposal for complex-valued optimization in Optax

Motivation

Complex-valued neural networks have been widely used in various science fields, such as the complex-valued wave functions in quantum physics and molecular chemistry, the complex-valued Fourier coefficients in signal processing, and manifold learning on torii that carry the complex structure. A recent survey is J. Bassey et al., arXiv:2101.12249.

One of the differences between complex- and real-valued neural networks is optimization. There is not yet a widely accepted way to generalize most optimizers to the complex domain, and most machine learning (ML) frameworks have not properly implemented them.

In the JAX community, Optax is the only actively maintained package dedicated to optimization, used in companion with other packages dedicated to neural network construction like Flax and Haiku. In particular, Flax developers have

@Bleuje
Bleuje / curvetutgif2.pde
Last active December 18, 2018 22:48
int[][] result;
float t, c;
float ease(float p) {
return 3*p*p - 2*p*p*p;
}
float ease(float p, float g) {
if (p < 0.5)
return 0.5 * pow(2*p, g);
@Pocuston
Pocuston / Cartpole-v0.py
Created September 3, 2017 15:51
Cartpole-v0 using Pytorch and DQN
# Solution of Open AI gym environment "Cartpole-v0" (https://gym.openai.com/envs/CartPole-v0) using DQN and Pytorch.
# It is is slightly modified version of Pytorch DQN tutorial from
# http://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html.
# The main difference is that it does not take rendered screen as input but it simply uses observation values from the \
# environment.
import gym
from gym import wrappers
import random
import math
@kevinzakka
kevinzakka / data_loader.py
Last active April 19, 2024 23:42
Train, Validation and Test Split for torchvision Datasets
"""
Create train, valid, test iterators for CIFAR-10 [1].
Easily extended to MNIST, CIFAR-100 and Imagenet.
[1]: https://discuss.pytorch.org/t/feedback-on-pytorch-for-kaggle-competitions/2252/4
"""
import torch
import numpy as np
@santi-pdp
santi-pdp / Generative Adversarial Networks toy example.ipynb
Created February 16, 2017 18:36
A toy example on Generative Adversarial Networks
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@monikkinom
monikkinom / rnn-lstm.py
Last active September 3, 2019 04:44
Tensorflow RNN-LSTM implementation to count number of set bits in a binary string
#Source code with the blog post at http://monik.in/a-noobs-guide-to-implementing-rnn-lstm-using-tensorflow/
import numpy as np
import random
from random import shuffle
import tensorflow as tf
# from tensorflow.models.rnn import rnn_cell
# from tensorflow.models.rnn import rnn
NUM_EXAMPLES = 10000
@karpathy
karpathy / pg-pong.py
Created May 30, 2016 22:50
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym
# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward
@reza-ryte-club
reza-ryte-club / stdc++.h
Created May 3, 2016 10:14
// C++ includes used for precompiling -*- C++ -*-
// Copyright (C) 2003-2013 Free Software Foundation, Inc.
//
// This file is part of the GNU ISO C++ Library. This library is free
// software; you can redistribute it and/or modify it under the
// terms of the GNU General Public License as published by the
// Free Software Foundation; either version 3, or (at your option)
// any later version.
@parmentf
parmentf / GitCommitEmoji.md
Last active September 19, 2024 17:12
Git Commit message Emoji
@lamosty
lamosty / how-to-code-vim-commands.md
Last active October 20, 2018 13:32
How to code in Vim — Commands, a video tutorial on Youtube: https://www.youtube.com/watch?v=hax7BEobOJQ

Command (normal) mode:

File

  • :w - save file
  • :q - close file
  • :q! - close file without saving
  • :x - save and close

Navigation

  • h - left