saikswaroop

Vision & Language

• Ask Your Neurons: A Neural-Based Approach to Answering Questions About Images

  • Mateusz Malinowski, Marcus Rohrbach, Mario Fritz

• Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books

  • Yukun Zhu, Ryan Kiros, Rich Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler

• Learning Query and Image Similarities With Ranking Canonical Correlation Analysis

• Wah Ngo

saikswaroop

# Usage: curl -H 'Cache-Control: no-cache' -s https://gist.githubusercontent.com/tsaqib/737607e64a1fba4d4562f2de21fd16d8/raw/ | sudo sh
# Works on: https://azure.microsoft.com/en-us/marketplace/partners/canonicalandmsopentech/dockeronubuntuserver1404lts/
# 'Docker on Ubuntu 15.04 LTS' works flawlessly on Azure's classical port mapping. If you map port 20001 from docker,
# you may easily map at Azure's Endpoints, for example public port = private port = 20001.

apt-get update -y
apt-get install apt-transport-https ca-certificates -y
apt-key adv --keyserver hkp://p80.pool.sks-keyservers.net:80 --recv-keys 58118E89F3A912897C070ADBF76221572C52609D
rm -rf /etc/apt/sources.list.d/docker.list
touch /etc/apt/sources.list.d/docker.list

saikswaroop

# List unique values in a DataFrame column
pd.unique(df.column_name.ravel())

# Convert Series datatype to numeric, getting rid of any non-numeric values
df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

# Grab DataFrame rows where column has certain values
valuelist = ['value1', 'value2', 'value3']
df = df[df.column.isin(valuelist)]

saikswaroop

Keybase proof

I hereby claim:

• I am roycoding on github.
• I am roycoding (https://keybase.io/roycoding) on keybase.
• I have a public key ASCG1vUl8yOBMIxO_ZbxVQMM_o4o82YhmpLQ7lhGZiqtHAo

To claim this, I am signing this object:

saikswaroop

#-*- coding: utf-8 -*-

"""
GIBBS SAMPLING IMPLEMENTATION FOR LATENT DIRICHLET ALLOCATION (2003)
IMPLEMENTED BY CHANG-UK, PARK
DATA FORMAT: "DocID\t WordID\t FREQUENCY\n"
"""

import sys
import random

saikswaroop

"""
(C) Mathieu Blondel - 2010
License: BSD 3 clause

Implementation of the collapsed Gibbs sampler for
Latent Dirichlet Allocation, as described in

Finding scientifc topics (Griffiths and Steyvers)
"""

saikswaroop

IASNLP-2016 Project list

LTRC, IIIT-Hyderabad

Treebanking

#####1. Shallow Parsers for different languages#####

• Description - POS Tagging and Chunking for Gujarati,Odia, Hindi, Bengali, Marathi, Telugu (individual project for each language)
• We will implement many supervised algorithms including CRF, HMM, MaxEnt, SVM, some semi-supervised classification methods, finally an unsupervised one. Will try to implement Morph Analyzer if time permits. students need to annotate data, understand the challenges, compare results given by multiple
• Mentor: Pruthwik M

saikswaroop

Automating news discovery in real-time

Talk outline

• How media works
  • There's a difference in positioning: in-depth vs breaking news
  • Crunch in talent, margin pressures. Not enough staff to 'break news'
  • Sources of breaking news: agencies, in-house, competition, social media
  • Increasingly, social media is a dominant source
• How can we source social media data at scale

saikswaroop

1. General Background and Overview

• Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
• Models and Issues in Data Stream Systems
• Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
• Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
• [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep