karpathy

"""
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)

honnibal

"""A stripped-down MLP example, using Theano.

Based on the tutorial here: http://deeplearning.net/tutorial/mlp.html

This example trims away some complexities, and makes it easier to see how Theano works.

Design changes:

* Model compiled in a distinct function, so that symbolic variables are not in run-time scope.
* No classes. Network shown by chained function calls.

kastnerkyle

# Author: Kyle Kastner
# License: BSD 3-clause
# THEANO_FLAGS="optimizer=None,compute_test_value=raise" python tanh_rnn.py
import numpy as np
import theano
import theano.tensor as T
from scipy import linalg


class sgd(object):

karpathy

--[[ 
Efficient LSTM in Torch using nngraph library. This code was optimized 
by Justin Johnson (@jcjohnson) based on the trick of batching up the 
LSTM GEMMs, as also seen in my efficient Python LSTM gist.
--]]

function LSTM.fast_lstm(input_size, rnn_size)
  local x = nn.Identity()()
  local prev_c = nn.Identity()()
  local prev_h = nn.Identity()()

chantastic

Hi Nicholas,

I saw you tweet about JSX yesterday. It seemed like the discussion devolved pretty quickly but I wanted to share our experience over the last year. I understand your concerns. I've made similar remarks about JSX. When we started using it Planning Center, I led the charge to write React without it. I don't imagine I'd have much to say that you haven't considered but, if it's helpful, here's a pattern that changed my opinion:

The idea that "React is the V in MVC" is disingenuous. It's a good pitch but, for many of us, it feels like in invitation to repeat our history of coupled views. In practice, React is the V and the C. Dan Abramov describes the division as Smart and Dumb Components. At our office, we call them stateless and container components (view-controllers if we're Flux). The idea is pretty simple: components can't

josephspurrier

/*
********************************************************************************
Golang - Asterisk and Ampersand Cheatsheet
********************************************************************************

Also available at: https://play.golang.org/p/lNpnS9j1ma

Allowed:
--------
p := Person{"Steve", 28} 	stores the value

prakhar1989

Rich Hickey on becoming a better developer

Rich Hickey • 3 years ago

Sorry, I have to disagree with the entire premise here.

A wide variety of experiences might lead to well-roundedness, but not to greatness, nor even goodness. By constantly switching from one thing to another you are always reaching above your comfort zone, yes, but doing so by resetting your skill and knowledge level to zero.

Mastery comes from a combination of at least several of the following:

debasishg

1. Feature Learning

• Learning Feature Representations with K-means by Adam Coates and Andrew Y. Ng
• The devil is in the details: an evaluation of recent feature encoding methods by Chatfield et. al.
• Emergence of Object-Selective Features in Unsupervised Feature Learning by Coates, Ng
• Scaling Learning Algorithms towards AI Benjio & LeCun
• A Theory of Feature Learning by Brendan van Rooyen, Robert C. Williamson

2. Deep Learning

• Dropout: A Simple Way to Prevent Neural Networks from Overfitting by Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov
• [Understanding

shobhit6993

--sample input
--dijkstra source dest [(n1,n2,e1),(n3,n4,e2)...] [(source,0)]
--dijkstra 1 4 [(1,2,5),(1,3,10),(2,4,100),(3,4,20)] [(1,0)]
--dijkstra 1 5 [(1,2,2), (2,3,1), (3,5,3), (4,5,4), (1,4,5), (1,3,8)] [(1,0)]

--ouput
-- a list of tuples with each tuple (n1,d1) representing the min. dist d1 of node n1 from source

inf = 100000

syhw

"""
A deep neural network with or w/o dropout in one file.
"""

import numpy
import theano
import sys
import math
from theano import tensor as T
from theano import shared