Jayesh K. Gupta rejuvyesh

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

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

for fl in wgEncode*.broadPeak; do /afs/ir/class/cs273a/bin/overlapSelect -selectCoordCols=0,1,2 -inCoordCols=0,1,2 hg19.knownGene.codingExons.bed ${fl} “${fl}_observed_overlaps_coding.bed”; done for fl in wgEncode*.broadPeak; do /afs/ir/class/cs273a/bin/overlapSelect -selectCoordCols=0,1,2 -inCoordCols=0,1,2 wgEncodeAwgDnaseDukeOsteoblUniPk.narrowPeak ${fl} “${fl}_observed_overlaps_narrow.bed”; done

for hist in H3k27me3Pk blH3k36me3StdPk blH3k27acStdPk; do for i in $(seq 100); do /afs/ir/class/cs273a/bin/overlapSelect -selectCoordCols=0,1,2 -inCoordCols=0,1,2 hg19.knownGene.codingExons.bed “wgEncodeBroadHistoneOsteo${hist}.broadPeak_shuffle_${i}.bed” “${hist}_shuffle_${i}_coding_overlap.bed”; /afs/ir/class/cs273a/bin/overlapSelect -selectCoordCols=0,1,2 -inCoordCols=0,1,2 wgEncodeAwgDnaseDukeOsteoblUniPk.narrowPeak “wgEncodeBroadHistoneOsteo${hist}.broadPeak_shuffle_${i}.bed” “${hist}_shuffle_${i}_narrow_overlap.bed”; done; done

centralized-gru centralized-mlp decentralized-gru decentralized-mlp concurrent-gru concurrent-mlp heuristic centralized-gru None 0.003187 0.214810 7.582445e-09 None 1.323825e-07 1.440084e-02 centralized-mlp None NaN 0.000644 3.366814e-09 None 1.265880e-08 9.346047e-01 decentralized-gru None NaN NaN 8.029683e-09 None 1.549680e-07 4.337083e-03 decentralized-mlp None NaN NaN NaN None 2.739982e-02 1.774222e-08 concurrent-gru None NaN NaN NaN None NaN NaN concurrent-mlp None NaN NaN NaN None NaN 1.011512e-06 heuristic None NaN NaN

centralized-gru centralized-mlp decentralized-gru decentralized-mlp concurrent-gru concurrent-mlp heuristic centralized-gru None 0.000001 1.244561e-04 3.725950e-07 None 2.741967e-07 7.556929e-10 centralized-mlp None NaN 9.068058e-10 1.913996e-03 None 2.822655e-09 7.745546e-02 decentralized-gru None NaN NaN 4.429615e-06 None 1.242145e-03 8.031091e-10 decentralized-mlp None NaN NaN NaN None 9.002403e-09 1.067955e-08 concurrent-gru None NaN NaN NaN None NaN NaN concurrent-mlp None NaN NaN NaN None NaN 8.534227e-10 heuristic None NaN NaN N

	[general]
	accounts = rejuvyesh, iitk, cse, gmail
	maxsyncaccounts = 4

	[Account rejuvyesh]
	localrepository = rejuvyeshlocal
	remoterepository = rejuvyeshremote

	[Repository rejuvyeshlocal]
	type = Maildir

	#!/usr/bin/env python
	#
	# File: amc.py
	#
	# Created: Friday, December 18 2015 by rejuvyesh <[email protected]>
	# License: GNU GPL 3 <http://www.gnu.org/copyleft/gpl.html>
	#

	from __future__ import print_function

	// ==UserScript==
	// @name GoodReads Review Management
	// @namespace [email protected]
	// @description Show/Hide reviews. State stored between site loads
	// @include /www.goodreads.com/
	// @version 1
	// @grant none
	// @require https://ajax.googleapis.com/ajax/libs/jquery/3.1.1/jquery.min.js
	// ==/UserScript==

	agents:
	- idx: 0
	status: 1
	rate: 1.0
	learner:
	cls: SharedFFA3CLearner
	lidx: 0
	- idx: 1
	status: 1
	rate: 1.0

	\newcommand{\ba}{\mathbf{a}}
	\newcommand{\bb}{\mathbf{b}}
	\newcommand{\bc}{\mathbf{c}}
	\newcommand{\bd}{\mathbf{d}}
	\newcommand{\be}{\mathbf{e}}
	\newcommand{\bg}{\mathbf{g}}
	\newcommand{\bh}{\mathbf{h}}
	\newcommand{\bi}{\mathbf{i}}
	\newcommand{\bj}{\mathbf{j}}
	\newcommand{\bk}{\mathbf{k}}