Statistical Relational Artificial Intelligence
By Dr. Sriraam Natarajan,UT Dallas, Audio Interview with TWiML & AI
In this episode of TWiML & AI, I speak with Dr. Sriraam Natarajan, Associate Professor in the Department of Computer Science at UT Dallas.
While at NIPS a few months back, Sriraam and I sat down to discuss his work on Statistical Relational Artificial Intelligence. StarAI is the combination of probabilistic & statistical machine learning techniques with relational databases. We cover systems learning on top of relational databases and making predictions with relational data, with quite a few examples from the healthcare field. Sriraam and his collaborators have also developed BoostSRL, a gradient-boosting based approach to learning different types of statistical relational models. We briefly touch on this, along with other implementation approaches. Read More
Digital Forensics to Reveal The Unknown
By Dr. Ebru Cankaya, UT Dallas
In a world of rapidly developing technology, it is getting easier and more prevalent each day to conceal data in digital media. As new techniques become available, the countermeasures to recover hidden or corrupt data are becoming available as well. Digital forensics make possible the entire effort for data recovery with no- or least-loss. Forensic investigations employ various hardware as well as software products to facilitate this process.
Historically, digital forensics have been referred to as computer forensics. Today multiple forms of data are stored in various media. In general, all that was needed in the past was to recover data that were first stored and subsequently deleted on a desktop computer. In today’s world, however, more complicated cases need to be addressed, such as discovering when and with which digital camera a picture was taken, or determining what actually happened at the time of an accident by reading an event data recorder (EDR) of a vehicle, or what actual cell phone conversations at what times took place between two criminals. Consequently, this is why the more general term “digital forensics” to refer to all media involved in a data-oriented forensics examination is used. Read More
What to do after “Learning how to Code?”
By Dr. Paul Fishwick, UT Dallas
When I first learned about computers, I learned FORTRAN programming. It was the programming language that dominated the scene back in, and before, the early 70s. In today’s world, we have numerous efforts that go by monikers such as “code.” We are told, “learning how to code” is good for your career, and it is fun. While I favor the phrase “programming” because “code” is a bit too narrow (think of Morse code or the ENIGMA code), programming is not without its double meanings. When TV producers talk about programming, they are referring to listings and scheduling. Coding or programming? Either will do.
The issue I have with coding is that it really does not represent true computer science. Consider chemistry or physics lab. In such a lab, you explore the science. In chemistry lab, there are Bunsen burners, sources for gas and water, lots of differently shaped glass containers, and rubber tubing. When you engage in chemistry lab, you are doing practical chemistry but you are not learning the essence of chemistry: how atoms are defined, how reactions occur. This is how you can view coding. Coding is like going to chemistry lab. You learn practical modes of doing computer science. But, if you want to learn real computer science, you must look elsewhere. Read More
Big Data Analytics for Cyber Security: Defeating Cyber Attackers
By Dr. Murat Kantarcioglu, UT Dallas
Like many application domains, more and more data are collected for cyber security. Examples of these collected data include system logs, network packet traces, account login formation, etc. Since the amount of data collected is ever increasing, it has become impossible to analyze all collected data manually to detect and prevent attacks. Therefore, data analytics are being applied to large volumes of security monitoring data to detect cyber security incidents. For example, a report from Gartner claims that “Information security is becoming a big data analytics problem, where massive amounts of data will be correlated, analyzed and mined for meaningful patterns”. There are many companies that already offer data analytics solutions for this important problem. Of course, data analytics is a means to an end where the ultimate goal is to provide cyber security analysts with prioritized actionable insights derived from big data. Read More
Cloud Computing, Fog Computing, and Big Data: Lessons from the Fashion Industry
By Dr. Ravi Prakash, UT Dallas
Every thirty years or so corduroys become fashionable. Raid your parents’ old suitcases and grandparents’ trunks. You will find that the clothes that were fashionable when they were young are in, once again. One can either attribute this to a lack of imagination on the part of the fashion industry when it comes to designing new clothes, or a genius on their part in terms of marketing the same old ideas generation after generation, or (and this is the more likely explanation) both. The field of computing seems to have paid close attention to this subterfuge.The earliest modern computers had all necessary components in one place: the processor, primary and secondary memory and I/O devices. As technology advanced, a key I/O device, the terminal, was moved into another room, with a rather simple wired connection to the computer. When personal computers and workstations came along, we marveled at how powerful they were and wanted to perform all computation and data storage locally. But, soon, our computation and storage needs exceeded the capabilities of these desktop devices. So, we moved computation and storage to machines in other parts of the building, using our desktop devices as clients: thus was born client-server computing. Not content with just one marketable term, we came up with other impressive terms to inhabit this ecosystem: network file systems, thin clients, thick clients, storage area networks, etc. Read More
