emeeks

{"nodes": [{"id":"1","module":0,"i":0},{"id":"3","module":0,"i":1},{"id":"8","module":2,"i":2},{"id":"9","module":4,"i":3},{"id":"12","module":2,"i":4},{"id":"15","module":2,"i":5},{"id":"23","module":3,"i":6},{"id":"26","module":3,"i":7},{"id":"37","module":10,"i":8},{"id":"46","module":2,"i":9},{"id":"2","module":1,"i":10},{"id":"4","module":2,"i":11},{"id":"5","module":3,"i":12},{"id":"6","module":3,"i":13},{"id":"7","module":1,"i":14},{"id":"10","module":4,"i":15},{"id":"11","module":1,"i":16},{"id":"13","module":1,"i":17},{"id":"14","module":1,"i":18},{"id":"16","module":5,"i":19},{"id":"18","module":1,"i":20},{"id":"19","module":3,"i":21},{"id":"20","module":1,"i":22},{"id":"21","module":6,"i":23},{"id":"22","module":2,"i":24},{"id":"25","module":3,"i":25},{"id":"27","module":1,"i":26},{"id":"28","module":3,"i":27},{"id":"29","module":1,"i":28},{"id":"31","module":2,"i":29},{"id":"33","module":2,"i":30},{"id":"34","module":9,"i":31},{"id":"35","module":1,"i":32},{"id":"38","module":2,"i":33},{"id":"41",

joschu

I used the cross-entropy method (an evolutionary algorithm / derivative free optimization method) to optimize small two-layer neural networks.

Code used to obtain these results can be found at the url https://github.com/joschu/modular_rl, commit 3324639f82a81288e9d21ddcb6c2a37957cdd361. The command line expression used for all the environments can be found in the text file below. Note that the same exact parameters were used for all tasks. The important parameters are:

• hid_sizes=10,5: hidden layer sizes of MLP
• extra_std=0.01: noise added to variance, see [1]

vik-y

How to Install ProR plugin into Eclipse


Open Eclipse
Go to Help->Install New Software

Click on Add new site 
Add name as : ProR
link: 
http://download.eclipse.org/rmf/updates/releases

haocong

/**
 * Karatsuba Multiplication
 * @param  {Number} x - first number
 * @param  {Number} y - second number
 * @return {Number} Multiply of x and y
 */
 
function karatsubaMulti(x, y) {

  let n = Math.min(('' + x).length, ('' + y).length);

calstad

Quick List of Resources for Topological Data Analysis with Emphasis on Machine Learning

This is just a quick list of resourses on TDA that I put together for @rickasaurus after he was asking for links to papers, books, etc on Twitter and is by no means an exhaustive list.

Survey Papers

Both Carlsson's and Ghrist's survey papers offer a very good introduction to the subject

• Topology and Data by Gunnar Carlsson
• Barcodes: The Persistent Topology of Data by Robert Ghrist

Other Papers and Web Resources

• Extracting insights from the shape of complex data using topology A good introductory paper in Nature on the Mapper algorithm.

baraldilorenzo

##VGG16 model for Keras

This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

mattes

if _, err := os.Stat("/path/to/whatever"); os.IsNotExist(err) {
	// path/to/whatever does not exist
}

if _, err := os.Stat("/path/to/whatever"); !os.IsNotExist(err) {
	// path/to/whatever exists
}

mitchwongho

# Assuming an Ubuntu Docker image
$ docker run -it <image> /bin/bash

tedmiston

/*
In the node.js intro tutorial (http://nodejs.org/), they show a basic tcp 
server, but for some reason omit a client connecting to it.  I added an 
example at the bottom.

Save the following server in example.js:
*/

var net = require('net');

alanyiu

Animation representing the Nussinov algorithm for RNA folding. Note that in this implementation, there is no restriction on pairing of neighboring bases.

You can restart the animation with a new input sequence using the input form below the diagram.