Show HN: Deep Learning for Program Synthesis
microsoft.com
Show HN: Deep Learning for Program Synthesis
1–10 of 24 posts
Re: Show HN: Deep Learning for Program Synthesis
#2One of the authors here -- would love to answer any questions about the work! :)
Re: Show HN: Deep Learning for Program Synthesis
#3One of the authors here -- would love to answer any questions about the work! :)
The first thing I thought of when reading this article was genetic programming.
Is this a significant improvement over evolutionary computation methods? Has that been attempted in the past?
Re: Show HN: Deep Learning for Program Synthesis
#4One of the authors here -- would love to answer any questions about the work! :)
Are there any difficulties in generating a program in standard languages in Python? Did you choose a DSL because neural network is sensitive to the output programming language?
Re: Show HN: Deep Learning for Program Synthesis
#5One of the authors here -- would love to answer any questions about the work! :)
Are you going to publish the source code for reproduction?
Re: Show HN: Deep Learning for Program Synthesis
#6One of the authors here -- would love to answer any questions about the work! :)
Any chance this could be implemented for automated proof synthesis? Would love to see this used in F* or Lean.
Re: Show HN: Deep Learning for Program Synthesis
#7@suryabhupa How similar is this work to the Grammatical Inference field? There has been a lot of work over the years in specification inference which feels similar. Many of the studies in specification inference learn automata representations of object interactions. I know there have been other application grammatical inference in Software Engineering as well.
Re: Show HN: Deep Learning for Program Synthesis
#8One of the authors here -- would love to answer any questions about the work! :)
Why does the final example in figure 14 fail completely? The outputs are correct as far as they go, but they're all incomplete.
Is it because the scoring metric has a point where enough of a good start outscores an alternative in the beam search that could lead to a more complete solution? In non-trivial real-world examples, would the be a major problem?
Re: Show HN: Deep Learning for Program Synthesis
#9Do you ever mess with the system and feed it crazy to see what it does?
aardvark
gorilla
orangutan
elephant
select list and extend
Re: Show HN: Deep Learning for Program Synthesis
#10@suryabhupa How similar is this work to the Grammatical Inference field? There has been a lot of work over the years in specification inference which feels similar. Many of the studies in specification inference learn automata representations of object interactions. I know there have been other application grammatical inference in Software Engineering as well.
Program synthesis is grammatical inference grown up, and statistical approaches are being experimented w/ for modern synthesis just as they were for the genetic programming & grammatical inference era. (I believe even now at the SAT solver level today.)
At a quick skim, this seems fun more as (1) an experience report of jumping on the DNN train instead of other ML algs and (2) more intriguing to me, the training formulation (irrespective of neural nets). Dawn Song's recent explorations here also sounded pretty interesting in terms of bridging logical synthesis of general programs with statistical..