Open Source DeepDive Now Available
January 14, 2015
IBM’s Watson has some open-source competition. As EE Times reports in “DARPA Offers Free Watson-Like Artificial Intelligence,” DARPA’s DeepDive is now a freely available alternative to the famous machine-learning AI. Both systems have their roots in the same DARPA-funded project. According to DeepDive’s primary programmer, Christopher Re, while Watson is built to answer questions, DeepDive’s focus is on extracting a wealth of structured data from unstructured sources. Writer R. Colin Johnson informs us:
DeepDive incorporates probability-based learning algorithms as well as open-source tools such as MADlib, Impala (from Oracle), and low-level techniques, such as Hogwild, some of which have also been included in Microsoft’s Adam. To build DeepDive into your application, you should be familiar with SQL and Python.
“Underneath the covers, DeepDive is based on a probability model; this is a very principled, academic approach to build these systems, but the question for use was, ‘Could it actually scale in practice?’ Our biggest innovations in Deep Dive have to do with giving it this ability to scale,” Re told us.
For the future, DeepDive aims to be proven in other domains. “We hope to have similar results in those domains soon, but it’s too early to be very specific about our plans here,” Re told us. “We use a RISC processor right now, we’re trying to make a compiler, and we think machine learning will let us make it much easier to program in the next generation of DeepDive. We also plan to get more data types into DeepDive.”
It sounds like the developers are just getting started. Click here to download DeepDive and for installation instructions.
Cynthia Murrell, January 14, 2015
Sponsored by ArnoldIT.com, developer of Augmentext
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
