Data Science Weekly - Issue 20
Issue #20 April 10 2014
Editor Picks
Neural Networks, Manifolds, and Topology While it is challenging to understand the behavior of deep neural networks in general, it turns out to be much easier to explore low-dimensional deep neural networks – networks that only have a few neurons in each layer. In fact, we can create visualizations to completely understand the behavior and training of such networks. This perspective will allow us to gain deeper intuition about the behavior of neural networks and observe a connection linking neural networks to an area of mathematics called topology....
Here's how one company built its Data Science operation When Francesco Bovoli VP of Program Management and Infrastructure for Workshare, was tasked with building a new data science organization for the company, he set a clear goal. "My objective was I want to make sure this is a data driven organization. I defined that by saying I want product managers to base more than half their decisions on numbers, not guts,"...
My solution for the Galaxy Zoo challenge The Galaxy Zoo challenge on Kaggle has just finished. The goal of the competition was to predict how Galaxy Zoo users (zooites) would classify images of galaxies from the Sloan Digital Sky Survey. I finished in 1st place and in this post I’m going to explain how my solution works...
Data Science Articles & Videos
Python Multi-armed Bandits (and Beer!)
There are many prediction problems where choosing the right accuracy measurement is particularly difficult. For example, what’s the best way to know whether this version of your recommendation system is better than the prior version? [one] way to vet your recommender strategy would be to roll it out to users and watch before and after behaviors. So by the end of this blog post, you (the reader) will hopefully be helping me improve our beer recommender through your clicks and interactions...
How does NASA use Machine Learning?
Detailed Quora response...
Using Friends as Sensors to Detect Global-Scale Contagious Outbreaks
In this method, we randomly choose a small fraction of nodes in the network and then we randomly choose a friend of each node to include in a group for local monitoring. Using six months of data from most of the full Twittersphere, we show that this friend group is more central in the network and it helps us to detect viral outbreaks of the use of novel hashtags about 7 days earlier than we could with an equal-sized randomly chosen group...
Kernel-Based Nonparametric Test for Anomaly Detection over Line Networks
In this paper we are interested in the goal of detecting the existence of an anomalous object over a network...
What drives research in Self-Driving Cars? Surprisingly not Machine Learning
In this post, I will talk about my surprise at the unfulfilled yet pervasive promises of Machine Learning in Self-Driving Car research...
Using Artificial Intelligence to solve the 2048 Game (JAVA code)
By now most of you have heard/played the 2048 game by Gabriele Cirulli. It’s a simple but highly addictive board game which requires you to combine the numbers of the cells in order to reach the number 2048. Personally even though I spent a fair amount of time playing the game, I was never able to reach 2048. So the natural thing to do is to try to develop an AI solver in JAVA to beat the 2048 game...
Wolfram's Grand Plans to monetize his new Programming Language
I asked Stephen Wolfram how he could make his ambitious new Wolfram Language into a commercial success and a developer favorite. He responded by typing out code. “Let’s make a really stupid API function whose sole function in life is we give it the name of a cat, and … it will give us an image of that cat type,” he said. In an instant, Wolfram cooked up the function. Then he typed “Burmese” into a search and got a photo of a Burmese cat...
Learning and Teaching Machine Learning: A Personal Journey
Joseph Barr examines history and origins of Machine Learning and Artificial Intelligence and recounts his personal journey from statistics to industry to teaching machine learning and running R on Unix clusters...
Jobs
Engineers, Designer & Data Scientist - Sense, San Francisco, CA "At Sense we are building a cloud platform for agile data science and big data analytics that radically increases the power and productivity of teams tackling the toughest problems in science and business. We're just getting started. If you love statistics, machine learning, data visualization, and tackling tough problems, we need your help"...
Training & Resources
MLPACK: A Scalable C++ Machine Learning Library
Library, tutorials and API documentation...
Data Science Bootcamp Programs - Full TIme, Part Time and Online I've gotten a lot of inquires on options to move into Data science. This is my attempt to answer that question...
Learn Data Science
Open content for self-directed learning in Data Science...
Citi Bike NYC Releases User Data In honor of reaching 100,000 annual members—who've already taken 7 million spins about town—the bike-share operation released 8 months of trip history on March 31 for use by statisticians, developers, and graphic artists...
Books
The LION Way: Learning plus Intelligent Optimization This new Machine Learning book is getting great reviews...
"Literally, I couldn't stop reading the book after getting it"
"This is an excellent book in machine learning and optimization, written by world-experts in the field. The book is informative and lively. The authors use ample illustrations and examples. The concepts are explained thoroughly in simple terms, which makes the book easy to follow"
"I find the example applications particularly useful: Text and web mining (for studying web pages and social networks) and collaborative filtering and recommendation (as in internet shopping) are both topical. They are both important big-data applications"...
For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page.
P.S. Did you enjoy the newsletter? Do you have friends/colleagues who might like it too? If so, please forward it along - we would love to have them onboard :)