Fan Yang fanyangxyz

fanyangxyz / min-char-rnn.py

Created September 15, 2016 20:25 — forked from karpathy/min-char-rnn.py

Minimal character-level language model with a Vanilla Recurrent Neural Network, in Python/numpy

	"""
	Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
	BSD License
	"""
	import numpy as np

	# data I/O
	data = open('input.txt', 'r').read() # should be simple plain text file
	chars = list(set(data))
	data_size, vocab_size = len(data), len(chars)

fanyangxyz / bayes_by_backprop.py

Created September 14, 2016 17:10 — forked from rocknrollnerd/bayes_by_backprop.py

Theano implementation of Bayes-by-Backprop algorithm from "Weight uncertainty in neural networks" paper

	import theano
	import theano.tensor as T
	from theano.tensor.shared_randomstreams import RandomStreams
	from theano.sandbox.rng_mrg import MRG_RandomStreams
	from lasagne.updates import adam
	from lasagne.utils import collect_shared_vars

	from sklearn.datasets import fetch_mldata
	from sklearn.cross_validation import train_test_split
	from sklearn import preprocessing

fanyangxyz / pg-pong.py

Created August 17, 2016 15:32 — 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