ozansener

Cython==0.20.1
Django==1.6.5
Flask==0.10.1
Jinja2==2.7.2
Markdown==2.5.1
MarkupSafe==0.18
MySQL-python==1.2.3
PAM==0.4.2
PIL==1.1.7
Pairtree==0.5.8

ozansener

import numpy

def get_turn_off(alpha):
    cycle_cnt =  (numpy.log(0.4) / numpy.log(1 - alpha) )
    return (cycle_cnt * 50)/ (1000 * 60)

def get_alpha_from_cut_off(cut_off):
	alpha = 1 - numpy.exp(numpy.log(0.1) / ((float(cut_off) * 60 * 1000) / float(50)))
	return alpha

ozansener

#!/bin/bash
 
# Bash script to install latest version of ffmpeg and its dependencies on Ubuntu 12.04 or 14.04
# Inspired from https://gist.github.com/faleev/3435377
 
# Remove any existing packages:
sudo apt-get -y remove ffmpeg x264 libav-tools libvpx-dev libx264-dev
 
# Get the dependencies (Ubuntu Server or headless users):
sudo apt-get update

ozansener

Keybase proof

I hereby claim:

• I am ozansener on github.
• I am ozansener (https://keybase.io/ozansener) on keybase.
• I have a public key whose fingerprint is A427 ACAD 1AAC 0B74 DEB0 F20B 6394 749D 0843 4519

To claim this, I am signing this object:

ozansener

NIPS Notes

Tutorials

Variational Inference

• Simple Intro by Blei mostly going over review paper of Jordan
• Later introduce SVI (Stochastic VI) as a remedy to solve VI tractably with large dataset.
• Review the black box inference -assumption free VI- http://www.jmlr.org/proceedings/papers/v33/ranganath14.pdf
• Key idea is replacing gradient and the expectation in VI formulation. Since expectation reqiuires exponential family assumption to work replacing expectation and gradient solves this if overall method is stochastic since your samples are unbiased gradient estimates satisfying Robinson-Monroe conditions however the variance is very large and it requires even further tricks

ozansener

from pulp import *

l = open('abc').read().split('\n')
title = l[0]
ent = title.split(',')
paper_ids = ent[2:]
num_papers = len(paper_ids)
print num_papers
print paper_ids
num_reviewers = len(l)-1

ozansener

name: "ResNet-18"
layer {
  name: "resnet_18"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {

ozansener

def projection2simplex(y):
    """
    Given y, it solves argmin_z |y-z|_2 st \sum z = 1 , 1 >= z_i >= 0 for all i
    """
    m = len(y)
    sorted_y = np.flip(np.sort(y), axis=0)
    tmpsum = 0.0
    tmax_f = (np.sum(y) - 1.0)/m
    for i in range(m-1):
        tmpsum+= sorted_y[i]

ozansener

abactinally
abatements
abbreviatable
abettors
abomasusi
abreption
abrogative
absconders
absinthol
absorbancy