Interview BigML.com

Here is an interview with Charlie Parker, head of large scale online algorithms at http://bigml.com

Ajay-  Describe your own personal background in scientific computing, and how you came to be involved with machine learning, cloud computing and BigML.com

Charlie- I am a machine learning Ph.D. from Oregon State University. Francisco Martin (our founder and CEO), Adam Ashenfelter (the lead developer on the tree algorithm), and myself were all studying machine learning at OSU around the same time. We all went our separate ways after that.

Francisco started Strands and turned it into a 100+ million dollar company building recommender systems. Adam worked for CleverSet, a probabilistic modeling company that was eventually sold to Cisco, I believe. I worked for several years in the research labs at Eastman Kodak on data mining, text analysis, and computer vision.

When Francisco left Strands to start BigML, he brought in Justin Donaldson who is a brilliant visualization guy from Indiana, and an ex-Googler named Jose Ortega who is responsible for most of our data infrastructure. They pulled in Adam and I a few months later. We also have Poul Petersen, a former Strands employee, who manages our herd of servers. He is a wizard and makes everyone else’s life much easier.

Ajay- You use clojure for the back end of BigML.com .Are there any other languages and packages you are considering? What makes clojure such a good fit for cloud computing ?

Charlie- Clojure is a great language because it offers you all of the benefits of Java (extensive libraries, cross-platform compatibility, easy integration with things like Hadoop, etc.) but has the syntactical elegance of a functional language. This makes our code base small and easy to read as well as powerful.

We’ve had occasional issues with speed, but that just means writing the occasional function or library in Java. As we build towards processing data at the Terabyte level, we’re hoping to create a framework that is language-agnostic to some extent. So if we have some great machine learning code in C, for example, we’ll use Clojure to tie everything together, but the code that does the heavy lifting will still be in C. For the API and Web layers, we use Python and Django, and Justin is a huge fan of HaXe for our visualizations.

 Ajay- Current support is for Decision Trees. When can we see SVM, K Means Clustering and Logit Regression?

Charlie- Right now we’re focused on perfecting our infrastructure and giving you new ways to put data in the system, but expect to see more algorithms appearing in the next few months. We want to make sure they are as beautiful and easy to use as the trees are. Without giving too much away, the first new thing we will probably introduce is an ensemble method of some sort (such as Boosting or Bagging). Clustering is a little further away but we’ll get there soon!

Ajay- How can we use the BigML.com API using R and Python.

Charlie- We have a public github repo for the language bindings. https://github.com/bigmlcom/io Right now, there there are only bash scripts but that should change very soon. The python bindings should be there in a matter of days, and the R bindings in probably a week or two. Clojure and Java bindings should follow shortly after that. We’ll have a blog post about it each time we release a new language binding. http://blog.bigml.com/

Ajay-  How can we predict large numbers of observations using a Model  that has been built and pruned (model scoring)?

Charlie- We are in the process of refactoring our backend right now for better support for batch prediction and model evaluation. This is something that is probably only a few weeks away. Keep your eye on our blog for updates!

Ajay-  How can we export models built in BigML.com for scoring data locally.

Charlie- This is as simple as a call to our API. https://bigml.com/developers/models The call gives you a JSON object representing the tree that is roughly equivalent to a PMML-style representation.

About-

You can read about Charlie Parker at http://www.linkedin.com/pub/charles-parker/11/85b/4b5 and the rest of the BigML team at

https://bigml.com/team

 

How to learn Hacking Part 2

Now that you have read the basics here at http://www.decisionstats.com/how-to-learn-to-be-a-hacker-easily/ (please do read this before reading the below)

 

Here is a list of tutorials that you should study (in order of ease)

1) LEARN BASICS – enough to get you a job maybe if that’s all you wanted.

http://www.offensive-security.com/metasploit-unleashed/Main_Page

2) READ SOME MORE-

Lena’s Reverse Engineering Tutorial-“Use Google.com  for finding the Tutorial

Lena’s Reverse Engineering tutorial. It includes 36 parts of individual cracking techniques and will teach you the basics of protection bypassing

01. Olly + assembler + patching a basic reverseme
02. Keyfiling the reverseme + assembler
03. Basic nag removal + header problems
04. Basic + aesthetic patching
05. Comparing on changes in cond jumps, animate over/in, breakpoints
06. “The plain stupid patching method”, searching for textstrings
07. Intermediate level patching, Kanal in PEiD
08. Debugging with W32Dasm, RVA, VA and offset, using LordPE as a hexeditor
09. Explaining the Visual Basic concept, introduction to SmartCheck and configuration
10. Continued reversing techniques in VB, use of decompilers and a basic anti-anti-trick
11. Intermediate patching using Olly’s “pane window”
12. Guiding a program by multiple patching.
13. The use of API’s in software, avoiding doublechecking tricks
14. More difficult schemes and an introduction to inline patching
15. How to study behaviour in the code, continued inlining using a pointer
16. Reversing using resources
17. Insights and practice in basic (self)keygenning
18. Diversion code, encryption/decryption, selfmodifying code and polymorphism
19. Debugger detected and anti-anti-techniques
20. Packers and protectors : an introduction
21. Imports rebuilding
22. API Redirection
23. Stolen bytes
24. Patching at runtime using loaders from lena151 original
25. Continued patching at runtime & unpacking armadillo standard protection
26. Machine specific loaders, unpacking & debugging armadillo
27. tElock + advanced patching
28. Bypassing & killing server checks
29. Killing & inlining a more difficult server check
30. SFX, Run Trace & more advanced string searching
31. Delphi in Olly & DeDe
32. Author tricks, HIEW & approaches in inline patching
33. The FPU, integrity checks & loader versus patcher
34. Reversing techniques in packed software & a S&R loader for ASProtect
35. Inlining inside polymorphic code
36. Keygenning

If you want more free training – hang around this website

http://www.owasp.org/index.php/Cheat_Sheets

OWASP Cheat Sheet Series

Draft OWASP Cheat Sheets

3) SPEND SOME MONEY on TRAINING

http://www.corelan-training.com/index.php/training/corelan-live/

Course overview

Module 1 – The x86 environment

  • System Architecture
  • Windows Memory Management
  • Registers
  • Introduction to Assembly
  • The stack

Module 2 – The exploit developer environment

  • Setting up the exploit developer lab
  • Using debuggers and debugger plugins to gather primitives

Module 3 – Saved Return Pointer Overwrite

  • Functions
  • Saved return pointer overwrites
  • Stack cookies

Module 4 – Abusing Structured Exception Handlers

  • Abusing exception handler overwrites
  • Bypassing Safeseh

Module 5 – Pointer smashing

  • Function pointers
  • Data/object pointers
  • vtable/virtual functions

Module 6 – Off-by-one and integer overflows

  • Off-by-one
  • Integer overflows

Module 7 – Limited buffers

  • Limited buffers, shellcode splitting

Module 8 – Reliability++ & reusability++

  • Finding and avoiding bad characters
  • Creative ways to deal with character set limitations

Module 9 – Fun with Unicode

  • Exploiting Unicode based overflows
  • Writing venetian alignment code
  • Creating and Using venetian shellcode

Module 10 – Heap Spraying Fundamentals

  • Heap Management and behaviour
  • Heap Spraying for Internet Explorer 6 and 7

Module 11 – Egg Hunters

  • Using and tweaking Egg hunters
  • Custom egghunters
  • Using Omelet egghunters
  • Egghunters in a WoW64 environment

Module 12 – Shellcoding

  • Building custom shellcode from scratch
  • Understanding existing shellcode
  • Writing portable shellcode
  • Bypassing Antivirus

Module 13 – Metasploit Exploit Modules

  • Writing exploits for the Metasploit Framework
  • Porting exploits to the Metasploit Framework

Module 14 – ASLR

  • Bypassing ASLR

Module 15 – W^X

  • Bypassing NX/DEP
  • Return Oriented Programming / Code Reuse (ROP) )

Module 16 – Advanced Heap Spraying

  • Heap Feng Shui & heaplib
  • Precise heap spraying in modern browsers (IE8 & IE9, Firefox 13)

Module 17 – Use After Free

  • Exploiting Use-After-Free conditions

Module 18 – Windows 8

  • Windows 8 Memory Protections and Bypass
TRAINING SCHEDULES AT

ALSO GET CERTIFIED http://www.offensive-security.com/information-security-training/penetration-testing-with-backtrack/ ($950 cost)

the syllabus is here at

http://www.offensive-security.com/documentation/penetration-testing-with-backtrack.pdf

4) HANG AROUND OTHER HACKERS

At http://attrition.org/attrition/

or The Noir  Hat Conferences-

http://blackhat.com/html/bh-us-12/training/bh-us-12-training_complete.html

or read this website

http://software-security.sans.org/developer-how-to/

5) GET A DEGREE

Yes it is possible

 

See http://web.jhu.edu/jhuisi/

The Johns Hopkins University Information Security Institute (JHUISI) is the University’s focal point for research and education in information security, assurance and privacy.

Scholarship Information

 

The Information Security Institute is now accepting applications for the Department of Defense’s Information Assurance Scholarship Program (IASP).  This scholarship includes full tuition, a living stipend, books and health insurance. In return each student recipient must work for a DoD agency at a competitive salary for six months for every semester funded. The scholarship is open to American citizens only.

http://web.jhu.edu/jhuisi/mssi/index.html

MASTER OF SCIENCE IN SECURITY INFORMATICS PROGRAM

The flagship educational experience offered by Johns Hopkins University in the area of information security and assurance is represented by the Master of Science in Security Informatics degree.  Over thirty courses are available in support of this unique and innovative graduate program.

———————————————————–

Disclaimer- I havent done any of these things- This is just a curated list from Quora  so I am open to feedback.

You use this at your own risk of conscience ,local legal jurisdictions and your own legal liability.

 

 

 

 

 

 

R for Predictive Modeling- PAW Toronto

A nice workshop on using R for Predictive Modeling by Max Kuhn Director, Nonclinical Statistics, Pfizer is on at PAW Toronto.

Workshop

Monday, April 23, 2012 in Toronto
Full-day: 9:00am – 4:30pm

R for Predictive Modeling:
A Hands-On Introduction

Intended Audience: Practitioners who wish to learn how to execute on predictive analytics by way of the R language; anyone who wants “to turn ideas into software, quickly and faithfully.”

Knowledge Level: Either hands-on experience with predictive modeling (without R) or hands-on familiarity with any programming language (other than R) is sufficient background and preparation to participate in this workshop.


What prior attendees have exclaimed


Workshop Description

This one-day session provides a hands-on introduction to R, the well-known open-source platform for data analysis. Real examples are employed in order to methodically expose attendees to best practices driving R and its rich set of predictive modeling packages, providing hands-on experience and know-how. R is compared to other data analysis platforms, and common pitfalls in using R are addressed.

The instructor, a leading R developer and the creator of CARET, a core R package that streamlines the process for creating predictive models, will guide attendees on hands-on execution with R, covering:

  • A working knowledge of the R system
  • The strengths and limitations of the R language
  • Preparing data with R, including splitting, resampling and variable creation
  • Developing predictive models with R, including decision trees, support vector machines and ensemble methods
  • Visualization: Exploratory Data Analysis (EDA), and tools that persuade
  • Evaluating predictive models, including viewing lift curves, variable importance and avoiding overfitting

Hardware: Bring Your Own Laptop
Each workshop participant is required to bring their own laptop running Windows or OS X. The software used during this training program, R, is free and readily available for download.

Attendees receive an electronic copy of the course materials and related R code at the conclusion of the workshop.


Schedule

  • Workshop starts at 9:00am
  • Morning Coffee Break at 10:30am – 11:00am
  • Lunch provided at 12:30 – 1:15pm
  • Afternoon Coffee Break at 2:30pm – 3:00pm
  • End of the Workshop: 4:30pm

Instructor

Max Kuhn, Director, Nonclinical Statistics, Pfizer

Max Kuhn is a Director of Nonclinical Statistics at Pfizer Global R&D in Connecticut. He has been applying models in the pharmaceutical industries for over 15 years.

He is a leading R developer and the author of several R packages including the CARET package that provides a simple and consistent interface to over 100 predictive models available in R.

Mr. Kuhn has taught courses on modeling within Pfizer and externally, including a class for the India Ministry of Information Technology.

Source-

http://www.predictiveanalyticsworld.com/toronto/2012/r_for_predictive_modeling.php

Teradata Analytics

A recent announcement showing Teradata partnering with KXEN and Revolution Analytics for Teradata Analytics.

http://www.teradata.com/News-Releases/2012/Teradata-Expands-Integrated-Analytics-Portfolio/

The Latest in Open Source Emerging Software Technologies
Teradata provides customers with two additional open source technologies – “R” technology from Revolution Analytics for analytics and GeoServer technology for spatial data offered by the OpenGeo organization – both of which are able to leverage the power of Teradata in-database processing for faster, smarter answers to business questions.

In addition to the existing world-class analytic partners, Teradata supports the use of the evolving “R” technology, an open source language for statistical computing and graphics. “R” technology is gaining popularity with data scientists who are exploiting its new and innovative capabilities, which are not readily available. The enhanced “R add-on for Teradata” has a 50 percent performance improvement, it is easier to use, and its capabilities support large data analytics. Users can quickly profile, explore, and analyze larger quantities of data directly in the Teradata Database to deliver faster answers by leveraging embedded analytics.

Teradata has partnered with Revolution Analytics, the leading commercial provider of “R” technology, because of customer interest in high-performing R applications that deliver superior performance for large-scale data. “Our innovative customers understand that big data analytics takes a smart approach to the entire infrastructure and we will enable them to differentiate their business in a cost-effective way,” said David Rich, chief executive officer, Revolution Analytics. “We are excited to partner with Teradata, because we see great affinity between Teradata and Revolution Analytics – we embrace parallel computing and the high performance offered by multi-core and multi-processor hardware.”

and

The Teradata Data Lab empowers business users and leading analytic partners to start building new analytics in less than five minutes, as compared to waiting several weeks for the IT department’s assistance.

“The Data Lab within the Teradata database provides the perfect foundation to enable self-service predictive analytics with KXEN InfiniteInsight,” said John Ball, chief executive officer, KXEN. “Teradata technologies, combined with KXEN’s automated modeling capabilities and in-database scoring, put the power of predictive analytics and data mining directly into the hands of business users. This powerful combination helps our joint customers accelerate insight by delivering top-quality models in orders of magnitude faster than traditional approaches.”

Read more at

http://www.sacbee.com/2012/03/06/4315500/teradata-expands-integrated-analytics.html

Interview Prof Benjamin Alamar , Sports Analytics

Here is an interview with Prof Benjamin Alamar, founding editor of the Journal of Quantitative Analysis in Sport, a professor of sports management at Menlo College and the Director of Basketball Analytics and Research for the Oklahoma City Thunder of the NBA.

Ajay – The movie Moneyball recently sparked out mainstream interest in analytics in sports.Describe the role of analytics in sports management

Benjamin- Analytics is impacting sports organizations on both the sport and business side.
On the Sport side, teams are using analytics, including advanced data management, predictive anlaytics, and information systems to gain a competitive edge. The use of analytics results in more accurate player valuations and projections, as well as determining effective strategies against specific opponents.
On the business side, teams are using the tools of analytics to increase revenue in a variety of ways including dynamic ticket pricing and optimizing of the placement of concession stands.
Ajay-  What are the ways analytics is used in specific sports that you have been part of?

Benjamin- A very typical first step for a team is to utilize the tools of predictive analytics to help inform their draft decisions.

Ajay- What are some of the tools, techniques and software that analytics in sports uses?
Benjamin- The tools of sports analytics do not differ much from the tools of business analytics. Regression analysis is fairly common as are other forms of data mining. In terms of software, R is a popular tool as is Excel and many of the other standard analysis tools.
Ajay- Describe your career journey and how you became involved in sports management. What are some of the tips you want to tell young students who wish to enter this field?

Benjamin- I got involved in sports through a company called Protrade Sports. Protrade initially was a fantasy sports company that was looking to develop a fantasy game based on advanced sports statistics and utilize a stock market concept instead of traditional drafting. I was hired due to my background in economics to develop the market aspect of the game.

There I met Roland Beech (who now works for the Mavericks) and Aaron Schatz (owner of footballoutsiders.com) and learned about the developing field of sports statistics. I then changed my research focus from economics to sports statistics and founded the Journal of Quantitative Analysis in Sports. Through the journal and my published research, I was able to establish a reputation of doing quality, useable work.

For students, I recommend developing very strong data management skills (sql and the like) and thinking carefully about what sort of questions a general manager or coach would care about. Being able to demonstrate analytic skills around actionable research will generally attract the attention of pro teams.

About-

Benjamin Alamar, Professor of Sport Management, Menlo College

Benjamin Alamar

Professor Benjamin Alamar is the founding editor of the Journal of Quantitative Analysis in Sport, a professor of sports management at Menlo College and the Director of Basketball Analytics and Research for the Oklahoma City Thunder of the NBA. He has published academic research in football, basketball and baseball, has presented at numerous conferences on sports analytics. He is also a co-creator of ESPN’s Total Quarterback Rating and a regular contributor to the Wall Street Journal. He has consulted for teams in the NBA and NFL, provided statistical analysis for author Michael Lewis for his recent book The Blind Side, and worked with numerous startup companies in the field of sports analytics. Professor Alamar is also an award winning economist who has worked academically and professionally in intellectual property valuation, public finance and public health. He received his PhD in economics from the University of California at Santa Barbara in 2001.

Prof Alamar is a speaker at Predictive Analytics World, San Fransisco and is doing a workshop there

http://www.predictiveanalyticsworld.com/sanfrancisco/2012/agenda.php#day2-17

2:55-3:15pm

All level tracks Track 1: Sports Analytics
Case Study: NFL, MLB, & NBA
Competing & Winning with Sports Analytics

The field of sports analytics ties together the tools of data management, predictive modeling and information systems to provide sports organization a competitive advantage. The field is rapidly developing based on new and expanded data sources, greater recognition of the value, and past success of a variety of sports organizations. Teams in the NFL, MLB, NBA, as well as other organizations have found a competitive edge with the application of sports analytics. The future of sports analytics can be seen through drawing on these past successes and the developments of new tools.

You can know more about Prof Alamar at his blog http://analyticfootball.blogspot.in/ or journal at http://www.degruyter.com/view/j/jqas. His detailed background can be seen at http://menlo.academia.edu/BenjaminAlamar/CurriculumVitae

UseR 2012 Early Registration #rstats

Early Registration Deadline Approaches for UseR 2012

http://biostat.mc.vanderbilt.edu/wiki/Main/UseR-2012

Registration

 

Deadlines

  • Early Registration: Jan 23 24 – Feb 29
  • Regular Registration: Mar 1 – May 12
  • Late Registration: May 13 – June 4
  • On-site Registration: June 12 – June 15

 

Fees

Academic Non-Academic Student/Retiree
Registration: Early $290 $440 $145
Registration: Regular $365 $560 $185
Registration: Late $435 $645 $225
Registration: On-site $720 $720 $360
Short Course $200 $300 $100

 

useR 2012

The 8th International R Users Meeting

Vanderbilt University; Nashville, Tennessee, USA

12th-15th June 2012

http://biostat.mc.vanderbilt.edu/wiki/Main/UseR-2012

Morning
Terri Scott & Frank Harrell Reproducible Research with R, LaTeX, & Sweave
Uwe Ligges Writing efficient and parallel code in R
Dirk Eddelbuettel & Romain Francois Introduction to Rcpp
Douglas Bates Fitting and evaluating mixed models using lme4
Jeremiah Rounds RHIPE: R and Hadoop Integrated Programming Environment
Jeffrey Horner Building R Web Applications with Rook
Brandon Whitcher, Jorg Polzehl, & Karsten Tabelow Medical Image Analysis in R
Richard Heiberger & Martin Maechler Emacs Speaks Statistics
Olivia Lau A Crash Course in R Programming
Afternoon
Hadley Wickham Creating effective visualisations
Josh Paulson, JJ Allaire, & Joe Cheng Getting the Most Out of RStudio
Romain Francois & Dirk Eddelbuettel Advanced Rcpp Usage
Terry Therneau Design of the Survival Packages
Martin Morgan Bioconductor for High-Throughput Sequence Analysis
Max Kuhn Predictive Modeling with R and the caret Package
Robert Muenchen Managing Data with R
Barry Rowlingson Geospatial Data in R and Beyond
Karim Chine Cloud Computing for the R environment

 

Contact

Stephania McNeal-Goddard
Assistant to the Chair
stephania.mcneal-goddard@vanderbilt.edu
Phone: 615.322.2768
Fax: 615.343.4924
Vanderbilt University School of Medicine
Department of Biostatistics
S-2323 Medical Center North
Nashville, TN 37232-2158

Statistical Theory for High Performance Analytics

A thing that strikes me when I was a student of statistics is that most theories of sampling, testing of hypothesis and modeling were built in an age where data was predominantly insufficient, computation was inherently manual and results of tests aimed at large enough differences.

I look now at the explosion of data, at the cloud computing enabled processing power on demand, and competitive dynamics of businesses to venture out my opinion-

1) We now have large , even excess data than we had before for statisticians a generation ago.

2) We now have extremely powerful computing devices, provided we can process our algorithms in parallel.

3) Even a slight uptick in modeling efficiency or mild uptick in business insight can provide huge monetary savings.

Call it High Performance Analytics or Big Data or Cloud Computing- are we sure statisticians are creating enough mathematical theory or are we just taking it easy in our statistics classrooms only to be subjected to something completely different when we hit the analytics workplace.

Do we  need more theorists as well? Is there ANY incentive for corporations with private R and D research teams to share their latest cutting edge theoretical work outside their corporate silo.

 

Related-

“a mathematician is a machine for turning coffee into theorems