CMU Artificial Intelligence Seminar Series ^{sponsored by}

Tuesday, March 15, 2022

Time: 12:00 - 01:00 PM ET

Kevin Ellis -- What Program Synthesis Can Learn From How People Write Code

Relevant Paper(s):

• DreamCoder: bootstrapping inductive program synthesis with wake-sleep library learning
• Write, Execute, Assess: Program Synthesis with a REPL

Abstract: How can we best make systems which learn to write computer programs? Here I explore the idea that we should take insight from the techniques and tools that human coders use when building software, but that we should combine those insights with machine learning methods. I focus on two basic coding techniques: writing libraries, and using interpreters ("REPLs"). For libraries, I present a system called DreamCoder, which grows a library of reusable subroutines as it solves a range of programming problems. DreamCoder's architecture builds on the structure of wake-sleep neural network training algorithms, and combines both symbolic and neural learning. For interpreters, I present a system which learns to interact with a REPL while it writes code, showing that this can help mitigate the combinatorial search difficulties of program synthesis. At the end of the talk, I will present preliminary results on modeling another aspect of coding: creating challenging and interesting programming problems.