"O’Reilly Data Show Podcast" entries
The O'Reilly Data Show Podcast: David Blei, co-creator of one of the most popular tools in text mining and machine learning.
I don’t remember when I first came across topic models, but I do remember being an early proponent of them in industry. I came to appreciate how useful they were for exploring and navigating large amounts of unstructured text, and was able to use them, with some success, in consulting projects. When an MCMC algorithm came out, I even cooked up a Java program that I came to rely on (up until Mallet came along).
I recently sat down with David Blei, co-author of the seminal paper on topic models, and who remains one of the leading researchers in the field. We talked about the origins of topic models, their applications, improvements to the underlying algorithms, and his new role in training data scientists at Columbia University.
Generating features for other machine learning tasks
Blei frequently interacts with companies that use ideas from his group’s research projects. He noted that people in industry frequently use topic models for “feature generation.” The added bonus is that topic models produce features that are easy to explain and interpret:
“You might analyze a bunch of New York Times articles for example, and there’ll be an article about sports and business, and you get a representation of that article that says this is an article and it’s about sports and business. Of course, the ideas of sports and business were also discovered by the algorithm, but that representation, it turns out, is also useful for prediction. My understanding when I speak to people at different startup companies and other more established companies is that a lot of technology companies are using topic modeling to generate this representation of documents in terms of the discovered topics, and then using that representation in other algorithms for things like classification or other things.”
The O'Reilly Data Show Podcast: Carlos Guestrin on the early days of GraphLab and the evolution of GraphLab Create.
I only really started playing around with GraphLab when the companion project GraphChi came onto the scene. By then I’d heard from many avid users and admired how their user conference instantly became a popular San Francisco Bay Area data science event. For this podcast episode, I sat down with Carlos Guestrin, co-founder/CEO of Dato, a start-up launched by the creators of GraphLab. We talked about the early days of GraphLab, the evolution of GraphLab Create, and what’s he’s learned from starting a company.
MATLAB for graphs
Guestrin remains a professor of computer science at the University of Washington, and GraphLab originated when he was still a faculty member at Carnegie Mellon. GraphLab was built by avid MATLAB users who needed to do large scale graphical computations to demonstrate their research results. Guestrin shared some of the backstory:
“I was a professor at Carnegie Mellon for about eight years before I moved to Seattle. A couple of my students, Joey Gonzales and Yucheng Low were working on large scale distributed machine learning algorithms specially with things called graphical models. We tried to implement them to show off the theorems that we had proven. We tried to run those things on top of Hadoop and it was really slow. We ended up writing those algorithms on top of MPI which is a high performance computing library and it was just a pain. It took a long time and it was hard to reproduce the results and the impact it had on us is that writing papers became a pain. We wanted a system for my lab that allowed us to write more papers more quickly. That was the goal. In other words so they could implement this machine learning algorithms more easily, more quickly specifically on graph data which is what we focused on.”
In this O'Reilly Data Show Podcast: Ion Stoica talks about the rise of Apache Spark and Apache Mesos.
Three projects from UC Berkeley’s AMPLab have been keenly adopted by industry: Apache Mesos, Apache Spark, and Tachyon. As an early user, it’s been fun to watch Spark go from an academic lab to the most active open source project in big data. In my recent travels, I’ve met Spark users from companies of all sizes and and from many industries. I’ve also spoken with companies that came of age before Spark was available or mature enough, and many are replacing homegrown tools with Spark (Full disclosure: I’m an advisor to Databricks, a start-up commercializing Apache Spark..)
A few months ago, I spoke with UC Berkeley Professor and Databricks CEO Ion Stoica about the early days of Spark and the Berkeley Data Analytics Stack. Ion noted that by the time his students began work on Spark and Mesos, his experience at his other start-up Conviva had already informed some of the design choices:
“Actually, this story started back in 2009, and it started with a different project, Mesos. So, this was a class project in a class I taught in the spring of 2009. And that was to build a cluster management system, to be able to support multiple cluster computing frameworks like Hadoop, at that time, MPI and others. To share the same cluster as the data in the cluster. Pretty soon after that, we thought about what to build on top of Mesos, and that was Spark. Initially, we wanted to demonstrate that it was actually easier to build a new framework from scratch on top of Mesos, and of course we wanted it to be also special. So, we targeted workloads for which Hadoop at that time was not good enough. Hadoop was targeting batch computation. So, we targeted interactive queries and iterative computation, like machine learning. Read more…
In this O'Reilly Data Show Podcast: Sarah Meiklejohn on analytic applications for blockchain and cryptocurrency technology.
Editor’s note: we’ll explore present and future applications of cryptocurrency and blockchain technologies at our upcoming Radar Summit: Bitcoin & the Blockchain on Jan. 27, 2015, in San Francisco.
A few data scientists are starting to play around with cryptocurrency data, and as bitcoin and related technologies start gaining traction, I expect more to wade in. As the space matures, there will be many interesting applications based on analytics over the transaction data produced by these technologies. The blockchain — the distributed ledger that contains all bitcoin transactions — is publicly available, and the underlying data set is of modest size. Data scientists can work with this data once it’s loaded into familiar data structures, but producing insights requires some domain knowledge and expertise.
I recently spoke with Sarah Meiklejohn, a lecturer at UCL, and an expert on computer security and cryptocurrencies. She was part of an academic research team that studied pseudo-anonymity (“pseudonymity”) in bitcoin. In particular, they used transaction data to compare “potential” anonymity to the “actual” anonymity achieved by users. A bitcoin user can use many different public keys, but careful research led to a few heuristics that allowed them to cluster addresses belonging to the same user:
“In theory, a user can go by many different pseudonyms. If that user is careful and keeps the activity of those different pseudonyms separate, completely distinct from one another, then they can really maintain a level of, maybe not anonymity, but again, cryptographically it’s called pseudo-anonymity. So, if they are a legitimate businessman on the one hand, they can use a certain set of pseudonyms for that activity, and then if they are dealing drugs on Silk Road, they might use a completely different set of pseudonyms for that, and you wouldn’t be able to tell that that’s the same user.
In this episode of the O'Reilly Data Show Podcast, Jay Kreps talks about data integration, event data, and the Internet of Things.
At the heart of big data platforms are robust data flows that connect diverse data sources. Over the past few years, a new set of (mostly open source) software components have become critical to tackling data integration problems at scale. By now, many people have heard of tools like Hadoop, Spark, and NoSQL databases, but there are a number of lesser-known components that are “hidden” beneath the surface.
In my conversations with data engineers tasked with building data platforms, one tool stands out: Apache Kafka, a distributed messaging system that originated from LinkedIn. It’s used to synchronize data between systems and has emerged as an important component in real-time analytics.
In my travels over the past year, I’ve met engineers across many industries who use Apache Kafka in production. A few months ago, I sat down with O’Reilly author and Radar contributor Jay Kreps, a highly regarded data engineer and former technical lead for Online Data Infrastructure at LinkedIn, and most recently CEO/co-founder of Confluent. Read more…
Rajiv Maheswaran talks about the tools and techniques required to analyze new kinds of sports data.
Many data scientists are comfortable working with structured operational data and unstructured text. Newer techniques like deep learning have opened up data types like images, video, and audio.
Other common data sources are garnering attention. With the rise of mobile phones equipped with GPS, I’m meeting many more data scientists at start-ups and large companies who specialize in spatio-temporal pattern recognition. Analyzing “moving dots” requires specialized tools and techniques.
A few months ago, I sat down with Rajiv Maheswaran founder and CEO of Second Spectrum, a company that applies analytics to sports tracking data. Maheswaran talked about this new kind of data and the challenge of finding patterns:
“It’s interesting because it’s a new type of data problem. Everybody knows that big data machine learning has done a lot of stuff in structured data, in photos, in translation for language, but moving dots is a very new kind of data where you haven’t figured out the right feature set to be able to find patterns from. There’s no language of moving dots, at least not that computers understand. People understand it very well, but there’s no computational language of moving dots that are interacting. We wanted to build that up, mostly because data about moving dots is very, very new. It’s only in the last five years, between phones and GPS and new tracking technologies, that moving data has actually emerged.”