权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Expeditions: Collaborative Research: Understanding the World Through Code

探险：合作研究：通过代码了解世界

基本信息

批准号：
1918651
负责人：
Christopher Jermaine
金额：
$ 123.72万
依托单位：
William Marsh Rice University
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2020
资助国家：
美国
起止时间：
2020-04-01 至 2025-03-31
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1918651&HistoricalAwards=false
关键词：
Expeditions Collaborative Research Understanding World

项目摘要

In almost every field of science, it is now possible to capture large amounts of data. This has led machine learning to play an increasingly important role in scientific discovery, for example sifting through large amounts of data to identify interesting events. But modern machine learning techniques are less well suited for the critical tasks of devising hypotheses consistent with the data or imagining new experiments to test those hypotheses. The goal of this Expeditions project is to develop new learning techniques that can help automate this process of generating scientific theories from data. In order to ground this research in real applications, the project focuses on four domains where these techniques can have the most significant impact: organic chemistry, RNA splicing, cognitive and behavioral science, and computing systems. Machine learning is already demonstrating value in all of these domains, including predicting properties of organic compounds, recognizing complex social activities, and modeling the performance of computer systems. However, the proposed techniques could have a transformative impact in all of these domains by helping scientists gain a deeper understanding of the processes that give rise to their data. This deeper understanding could lead to important contributions ranging from more efficient drug discovery to improved teaching methods grounded on a better understanding of cognition. To realize this vision, the project will develop new methods for learning neurosymbolic models that combine neural elements capable of identifying complex patterns in data with symbolic constructs that are able to represent higher level concepts. The approach is based on the observation that programming languages provide a uniquely expressive formalism to describe complex models. The aim is therefore to develop learning techniques that can produce models that look more like the models that scientists already write by hand in code. These neurosymbolic techniques will more easily incorporate prior knowledge about the phenomena being modeled, and produce interpretable models that can be analyzed to devise new experiments or to infer causal relations. By developing these techniques and building them into tools that can be used by scientists in a variety of fields, this project has the potential to revolutionize the way scientific knowledge is derived from data. More broadly, these new techniques will be useful in any setting that requires learning more interpretable models with strong requirements on their desired behavior.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

在几乎每一个科学领域，现在都有可能捕获大量数据。这导致机器学习在科学发现中发挥着越来越重要的作用，例如筛选大量数据来识别有趣的事件。但现代机器学习技术不太适合设计与数据一致的假设或想象新的实验来检验这些假设的关键任务。这个探险项目的目标是开发新的学习技术，帮助自动化这个从数据生成科学理论的过程。为了使这项研究在实际应用中站稳脚跟，该项目将重点放在这些技术可能产生最重大影响的四个领域：有机化学、RNA剪接、认知和行为科学以及计算系统。机器学习已经在所有这些领域展示了价值，包括预测有机化合物的性质，识别复杂的社会活动，以及对计算机系统的性能进行建模。然而，拟议的技术可以帮助科学家更深入地了解产生他们数据的过程，从而在所有这些领域产生变革性的影响。这种更深入的理解可能会带来重要的贡献，从更有效的药物发现到基于对认知的更好理解的改进教学方法。为了实现这一愿景，该项目将开发学习神经符号模型的新方法，该模型将能够识别数据中复杂模式的神经元素与能够表示更高级别概念的符号结构相结合。该方法基于这样一种观察，即编程语言提供了一种独特的表达形式来描述复杂的模型。因此，目标是开发学习技术，能够产生看起来更像科学家已经用代码手工编写的模型的模型。这些神经符号技术将更容易地纳入关于被建模现象的先验知识，并产生可解释的模型，这些模型可以被分析以设计新的实验或推断因果关系。通过开发这些技术并将其打造成可供科学家在各种领域使用的工具，该项目有可能彻底改变从数据中获取科学知识的方式。更广泛地说，这些新技术在任何需要学习更多可解释的模型和对其期望行为有强烈要求的环境中都将是有用的。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

期刊论文数量（11）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Learning Differentiable Programs with Admissible Neural Heuristics

使用可接受的神经启发式学习可微程序

DOI：
发表时间：
2020
期刊：
Advances in neural information processing systems
影响因子：
0
作者：
Shah, Ameesh;Zhan, Eric;Sun, Jennifer;Verma, Abhinav;Yue, Yisong;Chaudhuri, Swarat
通讯作者：
Chaudhuri, Swarat

Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier

少量图像分类：只需使用预先训练的特征提取器库和简单的分类器

DOI：
10.1109/iccv48922.2021.00931
发表时间：
2021
期刊：
ICCV 2021
影响因子：
0
作者：
Chowdhury, Arkabandhu;Jiang, Mingchao;Chaudhuri, Swarat;Jermaine, Chris
通讯作者：
Jermaine, Chris

Guiding Safe Exploration with Weakest Preconditions

DOI：
10.48550/arxiv.2209.14148
发表时间：
2022-09
期刊：
ArXiv
影响因子：
0
作者：
Greg Anderson;Swarat Chaudhuri;Işıl Dillig
通讯作者：
Greg Anderson;Swarat Chaudhuri;Işıl Dillig

Neurosymbolic Reinforcement Learning with Formally Verified Exploration

DOI：
发表时间：
2020-09
期刊：
ArXiv
影响因子：
0
作者：
Greg Anderson;Abhinav Verma;Işıl Dillig;Swarat Chaudhuri
通讯作者：
Greg Anderson;Abhinav Verma;Işıl Dillig;Swarat Chaudhuri

Tensor Relational Algebra for Distributed Machine Learning System Design

DOI：
10.14778/3457390.3457399
发表时间：
2020-09
期刊：
Proc. VLDB Endow.
影响因子：
0
作者：
Binhang Yuan;Dimitrije Jankov;Jia Zou;Yu-Shuen Tang;Daniel Bourgeois;C. Jermaine
通讯作者：
Binhang Yuan;Dimitrije Jankov;Jia Zou;Yu-Shuen Tang;Daniel Bourgeois;C. Jermaine