arrow
Return

Distilling data into code

delete2024-02-19
delete0
PRE
AI
J
Joseph Bakarji *
DOI:10.1038/s43588-024-00598-4delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
One of the greatest limitations of deep neural networks is the difficulty of interpreting what they learn from the data. Deep distilling addresses this problem by extracting human-comprehensible and executable code from observations.

Journal

Nature Computational Science cover
Nature Computational Science
IF:
18.3
Papers:
3.1K
Citations:
4.0K

Organization

A
American University of Beirut
Scholars:
8.3K
Papers: 6.0K
Citations: 1.1W
Cited Papers

Cited Papers

Automated discovery of algorithms from data
err2024-02-19
err3
PREAI
errBlazek, Paul J.; Venkatesh, Kesavan; Lin, Milo M.
errShare
errSave
Cu-Ni Thin Films Electrodeposited on Si: Composition and Current Efficiency
err2001-09-01
err0
PREAI
errM.L. Sartorelli; A.Q. Schervenski; R.G. Delatorre; P. Klauss; A.M. Maliska; A.A. Pasa
errShare
errSave
errShare
errSave
Seed coats: Structure, development, composition, and biotechnology
err2005-09-01
err0
PREAI
errJaimie A. Moïse; Shuyou Han; Loreta Gudynaitę-Savitch; Douglas A. Johnson; Brian L. A. Miki
errShare
errSave
Stress in Puberty Unmasks Latent Neuropathological Consequences of Prenatal Immune Activation in Mice
err2013-03-01
err0
errOAAI
errSandra Giovanoli; Harald Engler; Andrea Engler; Juliet Richetto; Mareike Voget; Roman Willi; Christine Winter; Marco A. Riva; Preben B. Mortensen; Joram Feldon; Manfred Schedlowski; Urs Meyer
errShare
errSave
no more