Local search and the evolution of world models
An open question regarding how people develop their models of the world is how new
candidates are generated for consideration out of infinitely many possibilities. We discuss …
candidates are generated for consideration out of infinitely many possibilities. We discuss …
Learning to Infer Generative Template Programs for Visual Concepts
People grasp flexible visual concepts from a few examples. We explore a neurosymbolic
system that learns how to infer programs that capture visual concepts in a domain-general …
system that learns how to infer programs that capture visual concepts in a domain-general …
How to Think About Benchmarking Neurosymbolic AI?
J Ott, A Ledaguenel, C Hudelot… - … International Workshop on …, 2023 - hal.science
Neurosymbolic artificial intelligence is a growing field of research aiming at combining
neural networks with symbolic systems, including their respective learning and reasoning …
neural networks with symbolic systems, including their respective learning and reasoning …
Abstracted Gaussian Prototypes for One-Shot Concept Learning
C Zou, KJ Kurtz - arXiv preprint arXiv:2408.17251, 2024 - arxiv.org
We introduce a cluster-based generative image segmentation framework to encode higher-
level representations of visual concepts based on one-shot learning inspired by the …
level representations of visual concepts based on one-shot learning inspired by the …
Understanding Boolean Function Learnability on Deep Neural Networks: PAC Learning Meets Neurosymbolic Models
Computational learning theory states that many classes of boolean formulas are learnable in
polynomial time. This paper addresses the understudied subject of how, in practice, such …
polynomial time. This paper addresses the understudied subject of how, in practice, such …