Skip to content

Instantly share code, notes, and snippets.

View tokestermw's full-sized avatar

Motoki Wu tokestermw

123 followers · 107 following
View GitHub Profile
@tokestermw
tokestermw / pytorch_reformer.py
Created January 22, 2020 07:29 — forked from lucidrains/pytorch_reformer.py
import torch
import torch.nn as nn
import torch.nn.functional as F
# helpers
def make_unit_length(x, epsilon=1e-6):
norm = x.norm(p=2, dim=-1, keepdim=True)
return x.div(norm + epsilon)
@tokestermw
tokestermw / Example of analyzing Annotations.ipynb
Created May 11, 2018 17:12 — forked from talolard/Example of analyzing Annotations.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@tokestermw
tokestermw / README.md
Created February 1, 2018 05:15 — forked from peterjliu/README.md
@tokestermw
tokestermw / Adversarial variational bayes toy example.ipynb
Created January 27, 2017 17:25 — forked from poolio/Adversarial variational bayes toy example.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@tokestermw
tokestermw / q.py
Created September 22, 2016 18:23 — forked from fheisler/q.py
Q-learning Tic-tac-toe
import random
class TicTacToe:
def __init__(self, playerX, playerO):
self.board = [' ']*9
self.playerX, self.playerO = playerX, playerO
self.playerX_turn = random.choice([True, False])
def play_game(self):
@tokestermw
tokestermw / KeyValueMemNN.md
Created June 30, 2016 21:01 — forked from shagunsodhani/KeyValueMemNN.md
Summary of paper "Key-Value Memory Networks for Directly Reading Documents"

Key-Value Memory Networks for Directly Reading Documents

Introduction

  • Knowledge Bases (KBs) are effective tools for Question Answering (QA) but are often too restrictive (due to fixed schema) and too sparse (due to limitations of Information Extraction (IE) systems).
  • The paper proposes Key-Value Memory Networks, a neural network architecture based on Memory Networks that can leverage both KBs and raw data for QA.
  • The paper also introduces MOVIEQA, a new QA dataset that can be answered by a perfect KB, by Wikipedia pages and by an imperfect KB obtained using IE techniques thereby allowing a comparison between systems using any of the three sources.
  • Link to the paper.

Related Work

@tokestermw
tokestermw / pg-pong.py
Created June 1, 2016 06:01 — forked from karpathy/pg-pong.py
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
@tokestermw
tokestermw / sampling_with_model.py
Created May 2, 2016 21:10 — forked from mokemokechicken/sampling_with_model.py
#!/usr/bin/env python
# coding: utf-8
"""Sampling Sequence Data from model"""
import numpy as np
import tensorflow as tf
import json
import cPickle as pickle
import itertools as it
from rnnlib import PTBModel
@tokestermw
tokestermw / ptb_lm_model.py
Created April 28, 2016 02:02 — forked from braingineer/ptb_lm_model.py
setup for ptb language model w/ keras (not a working example; missing personal libraries)
B = self.igor.batch_size
R = self.igor.rnn_size
S = self.igor.max_sequence_len
V = self.igor.vocab_size
E = self.igor.embedding_size
### loaded from glove
emb_W = self.igor.embeddings.astype(theano.config.floatX)
## dropout parameters
p_emb = self.igor.p_emb_dropout