by Swarat Chaudhuri on Nov 4, 2019 | Tags: applications, biology, machine learning, physics, program synthesis, science
Most applications of program synthesis are concerned with the engineering of software. However, because programming languages can be used to model the physical world, program synthesis can also offer a way of discovering and validating new hypotheses in the natural sciences. In this post, I elaborate on how.
Read more...
by Michael Carbin on Oct 3, 2019 | Tags: approximate computing, machine learning, overparameterization
There’s a new ecosystem of deep-learning-driven applications, occasionally titled Software 2.0, that integrates neural networks into a variety of computational tasks. Such applications include image recognition, natural language processing, and other traditional...
Read more...
by Eran Yahav on Aug 22, 2019 | Tags: code completion, machine learning, neural networks, program synthesis, programming, static analysis
The wealth of code now available on-line is fertile ground to enable machine learning to be applied to programming tasks. This post discusses the promise of and some progress on the problem “deep code.” It is the first in a series.
Read more...
by James Bornholt on Jul 31, 2019 | Tags: formal verification, machine learning, program synthesis, theorem proving
Program synthesis addresses an age-old problem in computer science: can a computer program itself? This post surveys the growing evolution of work in this exciting area.
Read more...
by Swarat Chaudhuri on Jun 24, 2019 | Tags: AI safety, formal verification, machine learning
In the last few years, there have been many anxious ruminations about AI safety. To a significant extent, these fears come from the realization that modern AI systems can be alarmingly brittle. For example, a deep neural net used for image classification can produce...
Read more...
