Learning Neurosymbolic Generative Models via Program Synthesis

01/24/2019
by   Halley Young, et al.
10

Significant strides have been made toward designing better generative models in recent years. Despite this progress, however, state-of-the-art approaches are still largely unable to capture complex global structure in data. For example, images of buildings typically contain spatial patterns such as windows repeating at regular intervals; state-of-the-art generative methods can't easily reproduce these structures. We propose to address this problem by incorporating programs representing global structure into the generative model---e.g., a 2D for-loop may represent a configuration of windows. Furthermore, we propose a framework for learning these models by leveraging program synthesis to generate training data. On both synthetic and real-world data, we demonstrate that our approach is substantially better than the state-of-the-art at both generating and completing images that contain global structure.

READ FULL TEXT

page 2

page 3

page 4

page 7

page 8

page 12

page 13

research
03/02/2023

Counterfactual Edits for Generative Evaluation

Evaluation of generative models has been an underrepresented field despi...
research
09/17/2020

ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis

Manually authoring 3D shapes is difficult and time consuming; generative...
research
05/22/2018

EgoCoder: Intelligent Program Synthesis with Hierarchical Sequential Neural Network Model

Programming has been an important skill for researchers and practitioner...
research
07/10/2018

Deep Structured Generative Models

Deep generative models have shown promising results in generating realis...
research
05/17/2023

Bridging the Gap: Enhancing the Utility of Synthetic Data via Post-Processing Techniques

Acquiring and annotating suitable datasets for training deep learning mo...
research
05/23/2019

Augmenting correlation structures in spatial data using deep generative models

State-of-the-art deep learning methods have shown a remarkable capacity ...
research
07/06/2020

Learning to learn generative programs with Memoised Wake-Sleep

We study a class of neuro-symbolic generative models in which neural net...

Please sign up or login with your details

Forgot password? Click here to reset