Abhishek Das abhshkdz

The Batch Normalization paper describes a method to address the various issues related to training of Deep Neural Networks. It makes normalization a part of the architecture itself and reports significant improvements in terms of the number of iterations required to train the network.

Issues With Training Deep Neural Networks

Internal Covariate shift

Covariate shift refers to the change in the input distribution to a learning system. In the case of deep networks, the input to each layer is affected by parameters in all the input layers. So even small changes to the network get amplified down the network. This leads to change in the input distribution to internal layers of the deep network and is known as internal covariate shift.

It is well established that networks converge faster if the inputs have been whitened (ie zero mean, unit variances) and are uncorrelated and internal covariate shift leads to just the opposite.

##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

Frontend Development

Attention: the list was moved to

https://github.com/dypsilon/frontend-dev-bookmarks

This page is not maintained anymore, please update your bookmarks.

I'm having trouble understanding the benefit of require.js. Can you help me out? I imagine other developers have a similar interest.

From Require.js - Why AMD:

The AMD format comes from wanting a module format that was better than today's "write a bunch of script tags with implicit dependencies that you have to manually order"

I don't quite understand why this methodology is so bad. The difficult part is that you have to manually order dependencies. But the benefit is that you don't have an additional layer of abstraction.

This is the backup plan I'm using for my newly-won 1 TB HDD (Thanks Yahoo!).

Partitions

On the Internal HDD (320GB)

50GB / (primary OS) (ext4)
220 GB /home (ext4)

Locate the section for your github remote in the .git/config file. It looks like this:

[remote "origin"]
	fetch = +refs/heads/*:refs/remotes/origin/*
	url = [email protected]:joyent/node.git

Now add the line fetch = +refs/pull/*/head:refs/remotes/origin/pr/* to this section. Obviously, change the github url to match your project's URL. It ends up looking like this:

	# author: Aaditya Prakash

	# NVIDIA-SMI does not show the full command, and when it was launched and its RAM usage.
	# PS does but it does but you need PIDs for that
	# lsof /dev/nvidia gives PIDs but only for the user invoking it

	# usage:
	# python programs_on_gpu.py

	# Sample Output

	#include "ofMain.h"
	#include "ofxTiming.h"

	class ofApp : public ofBaseApp {
	public:
	ofVideoGrabber grabber;
	DelayTimer delay;
	ofTrueTypeFont font;
	string description;

	<?
	/////////////////////
	// slack2html
	// by @levelsio
	/////////////////////
	//
	/////////////////////
	// WHAT DOES THIS DO?
	/////////////////////
	//

	"""
	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)