Geometry of Program Synthesis

03/30/2021
by   James Clift, et al.
0

We re-evaluate universal computation based on the synthesis of Turing machines. This leads to a view of programs as singularities of analytic varieties or, equivalently, as phases of the Bayesian posterior of a synthesis problem. This new point of view reveals unexplored directions of research in program synthesis, of which neural networks are a subset, for example in relation to phase transitions, complexity and generalisation. We also lay the empirical foundations for these new directions by reporting on our implementation in code of some simple experiments.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/08/2016

Theoretical Robopsychology: Samu Has Learned Turing Machines

From the point of view of a programmer, the robopsychology is a synonym ...
research
08/19/2021

Programming-By-Example by Programming-By-Example: Synthesis of Looping Programs

Program synthesis has seen many new applications in recent years, in lar...
research
07/24/2018

Bounded Synthesis of Reactive Programs

Most algorithms for the synthesis of reactive systems focus on the const...
research
08/14/2023

Modular System Synthesis

This paper describes a way to improve the scalability of program synthes...
research
07/12/2019

Augmenting Type Signatures for Program Synthesis

Effective program synthesis requires a way to minimise the number of can...
research
11/18/2019

Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Test

Despite remarkable advances in automated visual recognition by machines,...
research
02/07/2018

Recent Advances in Neural Program Synthesis

In recent years, deep learning has made tremendous progress in a number ...

Please sign up or login with your details

Forgot password? Click here to reset