paper-with-me

Papers

Learning abstract structure for drawing by efficient motor program induction

2020-08-08 · NeurIPS 2020 12 · Lucas Y. Tian, Kevin Ellis, Marta Kryven, Joshua B. Tenenbaum

Humans flexibly solve new problems that differ qualitatively from those they were trained on. This ability to generalize is supported by learned concepts that capture structure common across different problems. Here we develop a naturalistic drawing task to study how humans rapidly acquire structured prior knowledge. The task requires drawing visual objects that share underlying structure, based on a set of composable geometric rules. We show that people spontaneously learn abstract drawing procedures that support generalization, and propose a model of how learners can discover these reusable drawing programs. Trained in the same setting as humans, and constrained to produce efficient motor actions, this model discovers new drawing routines that transfer to test objects and resemble learned features of human sequences. These results suggest that two principles guiding motor program induction in the model - abstraction (general programs that ignore object-specific details) and compositionality (recombining previously learned programs) - are key for explaining how humans learn structured internal representations that guide flexible reasoning and learning.

📄 PDF Abstract BibTeX arXiv:2008.03519

Code (0)

등록된 구현이 없습니다.

Tasks

Program induction

Similar Papers 제목 키워드 기반

Harmonic content analysis of a soft starting variable frequency motor drive based on FPGA

2023-10-28 · Yogesh Sapkota, Suman Devkota, Vamsi Borra, Pedro Cortes 외

As the demands for electric vehicles, electric aircrafts, unmanned aircraft systems, and other motor-driven systems increase, high-performance motor drives employing variable frequency control with higher efficiency and …

Using Program Induction to Interpret Transition System Dynamics

2017-07-26 · Svetlin Penkov, Subramanian Ramamoorthy

Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predicti…

Program induction

Path-dependent program induction under resource constraints explains human sequence learning

2026-05-26 · Hanqi Zhou, David G. Nagy, Peter Dayan, Charley M. Wu arxiv

How do people build abstract, reusable knowledge from sequential experience under bounded cognitive resources? To answer this question, we integrate rate-distortion theory with recent advances in program induction to des…

Explaining Transition Systems through Program Induction

2017-05-23 · Svetlin Penkov, Subramanian Ramamoorthy

Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predicti…

Program induction

Optimization of a three-phase Induction Motor for Electric Vehicles Based on Hook-Jews Optimization Method

2023-02-28 · Arash Mousaei, Sahar Aziz Mohammadabadi

In this paper, the Hook-Jews (HJ) optimization method is used to optimize a 3-phase Squirrel-Cage Induction Motor (SCIM) as an Electric Vehicle's (EV) motor. Optimal designs with different numbers of poles, different nom…