检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Garimella, Manjulata Pak, Denizhan Wood, Justin N. Wood, Samantha M.W. Department of Informatics School of Informatics Computing & Engineering Department of Psychological & Brain Sciences Cognitive Science Program Program in Neuroscience

Newborn brains rapidly learn to solve challenging object perception tasks, including segmenting objects from backgrounds and recognizing objects across new viewing situations. Conversely, modern machine learning (ML) algorithms are "data hungry," requiring more training data than brains to reach similar performance levels. How do we close this learning gap between brains and machines? Here, we introduce a new benchmark-a Newborn Embodied Turing Test (NETT) for object segmentation-in which newborn animals and machines are raised in the same environments and tested with the same tasks, permitting direct comparison of their learning. First, newborn chicks were raised in controlled environments containing a single object rotating on a single background, then their recognition performance was tested across new backgrounds and viewpoints. Second, we performed "digital twin" experiments in which artificial agents were reared and tested in virtual environments that mimicked the rearing and testing conditions of the chicks. We inserted a variety of ML "brains" into the artificial agents and measured whether those algorithms learned common object recognition behavior as chicks. All newborn chicks solved this one-shot object segmentation task, successfully learning background-invariant object representations that generalized across new backgrounds and viewpoints. In contrast, none of the artificial agents solved the task, instead learning background-dependent representations that failed to generalize across new backgrounds and viewpoints. This digital twin design exposes core limitations in current ML algorithms in developing brain-like object perception. Our NETT is publicly available for comparing ML algorithms with newborn chicks. We argue that NETT benchmarks can help researchers build embodied AI systems that learn as efficiently and robustly as newborn brains. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

What does functional connectivity tell us about the behaviorally-functional connectivity of a multifunctional neural circuit?

What does functional connectivity tell us about the behavior...

引用

2022 Conference on Artificial Life, ALIFE 2022

作者： Izquierdo, Eduardo J. Candadai, Madhavun Cognitive Science Program Indiana University Luddy School of Informatics Computing and Engineering Indiana University United States

What insights can statistical analysis of the time series recordings of neurons and brain regions during behavior give about the neural basis of behavior? With the increasing amount of whole-brain imaging data becoming available, the importance of addressing this unanswered theoretical challenge has become increasingly urgent. We propose a computational neuroethology approach to begin to address this challenge. We evolve dynamical recurrent neural networks to be capable of performing multiple tasks. We then analyze the neural activity using popular network neuroscience tools, specifically functional connectivity using Pearson’s correlation, mutual information, and transfer entropy. We compare the results from these tools against a series of informational lesions, as a way to reveal their degree of approximation to the ground-truth. Our initial analysis reveals an overwhelming large gap between the insights gained from statistical inference of the functionality of the circuits based on neural activity and the actual functionality of the circuits as revealed by mechanistic interventions. © Artificial Life Conference Proceedings 2022.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Perpetual Crossers without Sensory Delay: Revisiting the Perceptual Crossing Simulation Studies

Perpetual Crossers without Sensory Delay: Revisiting the Per...

引用

2022 Conference on Artificial Life, ALIFE 2022

作者： Izquierdo, Eduardo J. Severino, Gabriel J. Merritt, Haily Cognitive Science Program Indiana University Bloomington Luddy School of Informatics Computing and Engineering Indiana University Bloomington United States

We revisit the perceptual crossing simulation studies, which are aimed at challenging methodological individualism in the analysis of social cognition by studying multi-agent real-time interactions. To date, all of these simulation studies have reported that it is practically impossible to evolve artificially a robust behavioral strategy without introducing temporal delays into the simulation. Also, all of the studies report on a single strategy: a perpetually crossing agent pair. Here, we systematically report on the evolutionary success of neural circuits on the perceptual crossing task, with and without sensory delay. We also report on two different strategies in the ensemble of successful solutions, only one of which had been discussed in the literature previously. © Artificial Life Conference Proceedings 2022.

关键词： Delay circuits

来源：评论

学校读者我要写书评

暂无评论

Dogs or Not Dogs? Examining ACI Authors' Reporting on Animal Participants' Willingness to Engage in Research: A Spotlight on Mediated and Contingent Consent 23

Dogs or Not Dogs? Examining ACI Authors' Reporting on Animal...

引用

Proceedings of the Tenth International Conference on Animal-Computer Interaction

作者： Eli B. McGraw Cristina Bosco Lisa Brey Christena Nippert-Eng Department of Informatics Luddy School of Informatics Computing and Engineering and the Cognitive Science Program Indiana University USA Department of Informatics Luddy School of Informatics Computing and Engineering Indiana University USA

ISBN: (纸本)9798400716560

How do Animal-Computer Interaction (ACI) researchers working with live animal participants assess the animals’ willingness to participate in their research? In this paper we present the results of a systematic literature review designed to answer this question by examining the Proceedings of the ACM International Animal Computer Interaction Conference. From 2016-2022, these proceedings included 38 full papers that reported results from research with live animal participants. We found 1) only 74% or 28/38 of the papers reported how they assessed animal participants’ willingness to engage during their research, 2) the authors of papers focused on species other than dogs had a much higher rate of providing this information than did the authors of dog-based studies (100% or 12/12 non-dog papers v 62% or 16/26 of dog-based papers), 3) most researchers who addressed the issue of an animal participant’s willingness to engage in the research relied on some form of mediated consent, informed by behavioral observation methods, to do so. However, the researchers focused on non-dog species were much more likely than researchers focused on dogs to include elements of contingent consent in their protocols (75% (9/12) of the non-dog studies v 12% (3/26) of the dog-related studies). We argue that providing each other with more details about our research methods and possibly more fully embracing the principles of contingent consent would further ACI researchers’ existing ethical commitment to our animal participants, increase our adherence to standard scientific research practice, and accelerate the continued development of the field of Animal-Computer Interaction.

关键词： Animal-Computer Interaction animal behavior animal well-being animal-centered design animal-centered ethics contingent consent dogs mediated consent multi-species interaction design reporting practices research methods scientific transparency voluntary engagement

来源：评论

学校读者我要写书评

暂无评论

Getting Situated: Comparative Analysis of Language Models With Experimental Categorization Tasks 44

Getting Situated: Comparative Analysis of Language Models Wi...

引用

44th Annual Meeting of the cognitive science Society: cognitive Diversity, CogSci 2022

作者： Edinger, Andy Goldstone, Robert L. Program in Cognitive Science & Luddy School of Informatics Computing and Engineering Indiana University 1101 E. 10th Street BloomingtonIN47405 United States Program in Cognitive Science Department of Psychological and Brain Sciences Indiana University 1101 E. 10th Street BloomingtonIN47405 United States

Common critiques of natural language processing (NLP) methods cite their lack of multimodal sensory information, claiming an inability to learn situated, action-oriented relations through language alone. Barsalou's (1983) theory of ad hoc categories, which are formed from to achieve goals in real-world scenarios, correspond theoretically to those types of relations with which language models ought to have great difficulty. Recent NLP models have developed dynamic approaches to word representations, where the same word can have different encodings depending on the context in which it appears. Testing these models using categorization tasks with human response data demonstrates that situated properties may be partially captured through semantic analysis. We discuss possible ways in which different notions of situatedness may be distinguished for future development and testing of NLP models. © 2022 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Generating reward structures on a parameterized distribution of dynamics tasks

Generating reward structures on a parameterized distribution...

引用

2021 Conference on Artificial Life, ALIFE 2021

作者： Leite, Abe Izquierdo, Eduardo J. Cognitive Science Program Indiana University Bloomington United States Luddy School of Informatics Computing and Engineering Indiana University Bloomington United States

In order to make lifelike, versatile learning adaptive in the artificial domain, one needs a very diverse set of behaviors to learn. We propose a parameterized distribution of classic control-style tasks with minimal information shared between tasks. We discuss what makes a task trivial and offer a basic metric, time in convergence, that measures triviality. We then investigate analytic and empirical approaches to generating reward structures for tasks based on their dynamics in order to minimize triviality. Contrary to our expectations, populations evolved on reward structures that incentivized the most stable locations in state space spend the least time in convergence as we have defined it, because of the outsized importance our metric assigns to behavior fine-tuning in these contexts. This work paves the way towards an understanding of which task distributions enable the development of learning. © 2021 ALIFE. All Rights Reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Word formation supports efficient communication: The case of compounds 44

Word formation supports efficient communication: The case of...

引用

44th Annual Meeting of the cognitive science Society: cognitive Diversity, CogSci 2022

作者： Xu, Aotao Kemp, Charles Frermann, Lea Xu, Yang Department of Computer Science University of Toronto Canada School of Computing and Information Systems University of Melbourne Australia School of Psychological Sciences University of Melbourne Australia Cognitive Science Program University of Toronto Canada

Compounding is a common type of word formation extensively studied in linguistics and cognitive psychology. A growing line of research suggests that the lexicon supports efficient communication by balancing informativeness and simplicity. We propose that the formation of novel compounds reflects a similar tradeoff between informativeness and word length. We formalize this hypothesis in information-theoretic terms and develop a computational procedure to evaluate our hypothesis on English noun compounds that emerged over the past century. We find that attested compounds achieve more efficient tradeoffs between informativeness and word length than do alternative word forms. Our work demonstrates how word formation and compositionality can be connected with information-theoretic approaches to the design of the lexicon. © 2022 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Classification Based on Texture Analysis for Synthetic Hazy Image from Mount Kelud Haze Image Density 8

Classification Based on Texture Analysis for Synthetic Hazy ...

引用

8th International Conference on Electrical, Electronics and Information Engineering, ICEEIE 2023

作者： Nugroho, Fresy Basid, Puspa Miladin Safitri A. Arif, Yunifa Miftachul Diah, Norizan Mat Bahtiar, Firma Sahrul Nurhayati, Hani Kurniawan, Fachrul Priandani, Nurizal Dwi Dermawan, Dodik Arwin Universitas Islam Negeri Maulana Malik Ibrahim Informatics Engineering Faculty of Science and Technology Malang Indonesia School of Computing Sciences College of Computing Informatics and Media Universiti Teknologi Mara Shah Alam Malaysia Library and Information Science Universitas Islam Negeri Maulana Malik Ibrahim Faculty of Science and Technology Malang Indonesia Manajemen Informatika Program Vokasi Universitas Negeri Surabaya Surabaya Indonesia

ISBN: (纸本)9798350340501

This paper classifies the simulations of homogeneous synthetic images, heterogeneous synthetic hazy images, and original hazy images taken from CCTV (Close Circuit Television) of Mt. Kelud crater using the GLCM (Gray Level Co-Occurrence Matrix) method. The average feature values obtained using the GLCM (Gray Level Co-Occurrence Matrix) method are used to compare the similarity of gray feature values of the three and then classify thin, medium, and thick images. The results for classifying thin haze, medium haze, and thick haze on the homogeneous synthetic hazy image test data obtained an accuracy value of 50%, a precision value of 46%, and a sensitivity value of 65%. As for the classification of thin, medium, and thick fog on heterogeneous synthetic hazy images, test data obtained an accuracy value of 42%, a precision value of 32%, and a sensitivity value of 48%. © 2023 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Maternal Health Risk Classification - A Comparison between Algorithm Decision Tree and k-Nearest Neighbor (kNN)

Maternal Health Risk Classification - A Comparison between A...

引用

2023 International Conference on Sustainable Emerging Innovations in Engineering and Technology, ICSEIET 2023

作者： Fatmawati, Maylia Novita, Mega Saputro, Nugroho Dwi Chauhan, Alok Singh Nada, Noora Qotrun Sinha, Amit Herlambang, Bambang Agus Gupta, Shruti Universitas Pgri Semarang Faculty of Engineering and Informatics Department of Informatics Semarang Indonesia Universitas Pgri Semarang Postgraduate Program of Science Education Semarang Indonesia School of Computing Science & Engineering Galgotias University Greater Noida India ABES Engineering College Department of Computer Science & Engineering Uttar Pradesh Ghaziabad201009 India

ISBN: (纸本)9798350329186

Maternal health is a critical concern, particularly for individuals who are pregnant and will shape the future generations. However, not all expectant mothers receive tailored attention and care for their unique health needs. Consequently, many mothers face high levels of health risks during pregnancy, highlighting the importance of classifying maternal health risks. Classification can help identify influential factors affecting maternal health and predict risk levels for individual mothers. In the field of data mining, various classification methods exist for analyzing complex datasets. This study focuses on two widely used algorithms: decision tree and k-Nearest Neighbor (kNN). By employing these algorithms, we aim to classify a dataset comprising 1,014 records of maternal health risk levels. Through cross-validation and T-tests, we rigorously evaluate the performance of the decision tree and kNN algorithms in this context. Our findings indicate that the kNN algorithm is more suitable for classifying maternal health risks, achieving a significantly higher accuracy of 71.50% compared to the decision tree algorithm's accuracy of 70.71%. This result establishes the superiority of the kNN algorithm in accurately classifying maternal health risks. These findings have implications for developing targeted interventions and tailored healthcare strategies to mitigate identified risks. © 2023 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Cultivating the Garden of Eden

arXiv

引用

arXiv 2022年

作者： Beer, Randall D. Cognitive Science Program Informatics Dept Luddy School of Informatics Computing and Engineering Indiana University United States Cognitive Science Program Indiana University 3052 Geology Building BloomingtonIN47405 United States

Garden of Eden (GOE) states in cellular automata are grid configurations which have no precursors, that is, they can only occur as initial conditions. Finding individual configurations that minimize or maximize some criterion of interest (e.g., grid size, density, etc.) has been a popular sport in recreational mathematics, but systematic studies of the set of GOEs for a cellular automaton have been rare. This paper presents the current results of an ongoing computational study of GOE configurations in Conway’s Game of Life (GoL) cellular automaton. Specifically, we describe the current status of a map of the layout of GOEs and nonGOEs in density/size space, characterize how the density-dependent structure of the number of precursors varies with increasing grid size as we approach the point where GOEs begin to occur, provide a catalog of all known GOE configurations up to a grid size of 11 × 11, and initiate a study of the structure of the network of constraints that characterize GOE vs. nonGOE configurations. © 2022, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：