I seek talented grad students for AI+SE. Is that you?
Ask me how to innovate. On time. On budget. Case studies:
My FundingOver $8M. From many sources, e.g.:
My current graduate students (at the RAISE lab- real-world AI for SE):
My prior graduates:
I challenge my students as follows:
Here are a few examples of their "Less, but better" results:
2007Surprisingly effective defect predictors can be built from simple static code attributes.
2010Static code defect predictors have inherent limitations. But these limits can fixed via a new learner, very simple learner, that better understand the business goals.
2012Very simple social metrics can generate near-optimal predictors for software quality.
2015A simple feature and instance selectors let software projects share privatized data, without missing important patterns.
2002Search-based SE methods can easily and readily and critically assess long held SE truisms.
2013Active learners can simplify and reduce the cost of search-based SE by orders of magnitude.
2016Very simple optimizers can dramatically improve the performance of data miners learning software quality predictors.
2009A simple nearest neighbor relevancy filtering resulted in one of the first general results in software analytics: defect predictor learned from Turkish toasters could be successfully applied to NASA flight software (and vice versa).
2013How to transfer lessons learned from past projects? Easy! Clustering tools enable transferring lessons learned between software projects.
2016Ultra-simple transfer learning methods (called "bellwethers") enable effective transfer of lessons learned.
2002Contrast set learners find simple controllers in requirements models.
2003Contrast set learners can explain enormous decision trees (6000 node) learned from complex requirements models just 6 rules.
2013Active learners can easily estimate large software projects after just a few samples.
2016The effort to build complex software can be estimated by very simple equations.
1990The lesson of decades of expert systems research is that, for specific domains, human expertise can be readily captured in just a few rules.
2010Simple contrast-set learners out-perform state-of-the-art optimizers for spacecraft control;
2015Data miners can greatly simplify and reduce the effort involved in data collection for community health studies.
2016Text miners can succinctly summarize thousands of technical papers about SE.
BTW: for the origins of the "Less, but better" mantra, see Dieter Rams' 10 principles for good design.
Mail: Computer Science, NC State University, 890 Oval Dr, Raleigh, NC, 27695-8206.
Dec 1: Invited to the program committee of the 2017 Automated Software Engineering conference. More...
Nov 26: $75K gift from Lexix Nexis for advanced analytics
Nov 22: Journal article published: 'Negative results about Effort Estimation'. More...
Nov 17: 3 NSF submissions in one month is more than enough. !!
Nov 14: Journal article published: 'Are delayed issues harder to resolve? Revisitingcost-to-fix of defects throughout the lifecycle'. More...
Now 13: Gave keynote, International Workshop on Software Analytics More...
Oct 30: Invited to the program committee of the Systems and Software Project Line conference, 2017.
Oct 27: Most-cited research at NCSU CS, 2 months in a row. More...
Oct 26: Invited to MSR'17 program committee More...
Oct 19: Two NSF medium proposals submitted. Now crossing all fingers+toes.