Filters








16,114 Hits in 4.5 sec

Development of collective behavior in newborn artificial agents [article]

Donsuk Lee, Samantha M. W. Wood, Justin N. Wood
2021 arXiv   pre-print
Specifically, when we raise our artificial agents in natural visual environments with groupmates, the agents spontaneously develop ego-motion, object recognition, and a preference for groupmates, rapidly  ...  Here, we used deep reinforcement learning and curiosity-driven learning -- two learning mechanisms deeply rooted in psychological and neuroscientific research -- to build newborn artificial agents that  ...  Wood for help designing the artificial agents and virtual worlds, and Linda Smith and Zoran Tiganj for helpful comments on the manuscript.  ... 
arXiv:2111.03796v1 fatcat:gfttrauwfbbzjjokfxaowmbgru

DeepNav: Learning to Navigate Large Cities

Samarth Brahmbhatt, James Hays
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
The DeepNav agent learns to reach its destination quickly by making the correct navigation decisions at intersections.  ...  We propose 3 supervised learning approaches for the navigation task and show how A* search in the city graph can be used to generate supervision for the learning.  ...  The agent takes a step in the direction that is predicted by the CNN to have the least distance estimate.  ... 
doi:10.1109/cvpr.2017.329 dblp:conf/cvpr/BrahmbhattH17 fatcat:jy5vomudsrezvp4u37wyddxwry

Introducing Long Term Memory in an ANN based Multilevel Darwinist Brain [chapter]

F. Bellas, R. J. Duro
2003 Lecture Notes in Computer Science  
This paper deals with the introduction of long term memory in a Multilevel Darwinist Brain (MDB) structure based on Artificial Neural Networks and its implications on the capability of adapting to new  ...  The paper describes the mechanism, introduces the long term mermoy within it and provides some examples of its operation both in theoretical problems and on a real robot whose perceptual and actuation  ...  The outputs are the predicted distance given by the nearest sonar, the predicted angular position of that sonar and the predicted boolean value.  ... 
doi:10.1007/3-540-44868-3_75 fatcat:vgzfaakdsncevklulnndr3hk7y

Embedding High-Level Knowledge into DQNs to Learn Faster and More Safely

Zihang Gao, Fangzhen Lin, Yi Zhou, Hao Zhang, Kaishun Wu, Haodi Zhang
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Deep reinforcement learning has been successfully applied in many decision making scenarios. However, the slow training process and difficulty in explaining limit its application.  ...  In this framework, the rules dynamically effect the training progress, and accelerate the learning.  ...  Formally, knowledge base in Space war is R aw = {r 3 , r 4 }, where η(r 3 ) = on lef t(nearest jet, agent) and δ(r 3 ) = {move lef t}, and η(r 4 ) = on right(nearest jet, agent) and δ(r 4 ) = {move lef  ... 
doi:10.1609/aaai.v34i09.7091 fatcat:yjwz3sej5ve6hlldzxucljvtb4

CTRANSPORT: Multi-agent-based simulation

Pedro SÁNCHEZ, Denis PATO, Gabriel MARTÍN
2019 Advances in Distributed Computing and Artificial Intelligence Journal  
Big cities suffer from overcrowding which result in traffic congestion and a lot of air pollution.  ...  KEYWORD ABSTRACT Electric vehicles; Multi-agent Systems;Ecofriendly Pollution nowadays is a really important issue that must be solved.  ...  This follows the tonic of bicycle lane expansion of most cities in the world. In this case, the model has just nine stations.  ... 
doi:10.14201/adcaij2019811926 fatcat:zchdkv6lcvhppit42mgspk342m

Learning from hotlists and coldlists: towards a WWW information filtering and seeking agent

M. Pazzani, L. Nguyen, S. Mantik
1995 Proceedings of 7th IEEE International Conference on Tools with Artificial Intelligence TAI-95  
We describe a software agent that learns to find information on the World Wide Web (WWW), deciding what new pages might interest a user.  ...  By analyzing the information immediately accessible from each link, the agent learns the types of information the user is interested in.  ...  Acknowledgments The research reported here was supported in part by NSF grant IRI-9310413 and ARPA grant F49620-92-J-0430 monitored by AFOSR.  ... 
doi:10.1109/tai.1995.479848 dblp:conf/ictai/PazzaniNM95 fatcat:j55spyuwubgmflzmsfbqhiqm3e

DeepNav: Learning to Navigate Large Cities [article]

Samarth Brahmbhatt, James Hays
2017 arXiv   pre-print
The DeepNav agent learns to reach its destination quickly by making the correct navigation decisions at intersections.  ...  We propose 3 supervised learning approaches for the navigation task and show how A* search in the city graph can be used to generate supervision for the learning.  ...  The agent takes a step in the direction that is predicted by the CNN to have the least distance estimate.  ... 
arXiv:1701.09135v2 fatcat:m7pekhaqdrb67lj44n6kyugddu

Two Faces of the Framework for Analysis and Prediction, Part 2 - Research

Vladimir Kurbalija, Mirjana Ivanović, Zoltan Geler, Miloš Radovanović
2018 Information Technology and Control  
research (in psychology, medicine, emotion recognition, and agent-based distributed computing).  ...  Research applications include applications in data mining (development of a new time-series representation and various interactions between time-series distance measures and classification) and multidisciplinary  ...  In order to utilize them for calculating distance matrices relying on the FAP library, we have implemented an agent-based distributed system [42] a b This application involved the processing of real-world  ... 
doi:10.5755/j01.itc.47.3.18747 fatcat:kqd3tu7r4nd5laetlbaef6xfyy

Multi-Agent Based Diagnostic Model for Breast Tumour Classification

Yusuf Musa Malgwi, Gregory Maksha Wajiga, Etemi Joshua Garba
2019 American Journal of Data Mining and Knowledge Discovery  
This study focused on developing a multi-agent based model for diagnosis of breast tumours using the k-Nearest Neighbor (k-NN) algorithm by classifying the nature of the tumours based on their associated  ...  The experimental result of the prediction model shows a percentage accuracy score of 98.9%.  ...  Calculate the distance between the query-instance and all the training samples ii. Sort the distance and determine the Nearest Neighbour based on the K-th minimum distance. iii.  ... 
doi:10.11648/j.ajdmkd.20190401.11 fatcat:6drcqxnmengr7nlcw7yloljjse

Many paths to the same goal: metaheuristic operation of brains during natural behavior [article]

Brian J Jackson, Gusti Lulu Fatima, Sujean Oh, David Henry Gire
2019 bioRxiv   pre-print
This ability is currently an area of active investigation in artificial intelligence.  ...  findings set the foundation for new approaches to understand the neural substrates of natural behavior as well as the rational development of biologically inspired metaheuristic approaches for complex real-world  ...  by distance from the agent.  ... 
doi:10.1101/697607 fatcat:kzfwitw6c5ea7fqsxsergadqqe

Precise atom manipulation through deep reinforcement learning [article]

I-Ju Chen, Markus Aapro, Abraham Kipnis, Alexander Ilin, Peter Liljeroth, Adam S. Foster
2022 arXiv   pre-print
Atomic-scale manipulation in scanning tunneling microscopy has enabled the creation of quantum states of matter based on artificial structures and extreme miniaturization of computational circuitry based  ...  These results demonstrate that state-of-the-art deep reinforcement learning can offer effective solutions to real-world challenges in nanofabrication and powerful approaches to increasingly complex scientific  ...  In the RL training, a STM scan is performed • when the CNN prediction is positive; Figure 1 : 1 Figure 1: Atom manipulation with a DRL agent.  ... 
arXiv:2203.06975v1 fatcat:dxvfyho4fvcr7jfrzynkatfczi

Computer Prediction of Cardiovascular and Hematological Agents by Statistical Learning Methods

X. Chen, H. Li, C. Yap, C. Ung, L. Jiang, Z. Cao, Y. Li, Y. Chen
2007 Cardiovascular & Hematological Agents in Medicinal Chemistry  
These methods include partial least squares, multiple linear regressions, linear discriminant analysis, k-nearest neighbour, artificial neural networks and support vector machines.  ...  Computational methods have been explored for predicting agents that produce therapeutic or adverse effects in cardiovascular and hematological systems.  ...  k Nearest Neighbor (kNN) In kNN, the Euclidean distance between an unclassified vector x and each individual vector x i in the training set is measured [51, 52] .  ... 
doi:10.2174/187152507779315787 pmid:17266544 fatcat:hntce6ibjrew7lfc2tk37fxzrm

Crowd Anomaly Detection Using Standardized Modeled Input

Michael E. Long
2012 International Journal of Intelligent Information Systems  
Acknowledgements We wish to thank Captain Steven Siena and Deputy Chief Glenn Hoff for review and suggestions of the crowd anomaly scenarios depicted in this publication.  ...  a certain distance averaged over frames Neighbor Distance -the averaged distance between each agent and their k-Nearest Neighbors averaged Relative Speed kDistance -the speed of each agent relve to all  ...  Two basic parameters were calculated from the known position of all agents in each frame, distance and dire tion.For any given agent, their distance traveled between frame i and i+1 is given as x i+1 −  ... 
doi:10.11648/j.ijiis.20120101.11 fatcat:afn6ud4d4jgn5ge53jeeib3nji

Interface agents: A review of the field [article]

Stuart E. Middleton
2002 arXiv   pre-print
A history of agent systems from their birth in the 1960's to the current day is described, along with the issues they try to address.  ...  A taxonomy of interface agent systems is presented, and today's agent systems categorized accordingly.  ...  Results: Constructive induction was most accurate but only on an artificial domain. CIMA [28] is a text prediction agent, which suggests completions of sentences in a text editor.  ... 
arXiv:cs/0203012v1 fatcat:7nzkypnpcjbczabewdo4ltj6xe

Improving Law Enforcement Daily Deployment Through Machine Learning-Informed Optimization under Uncertainty

Jonathan Chase, Duc Thien Nguyen, Haiyang Sun, Hoong Chuin Lau
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
temporal deployment of law enforcement agents to predefined patrol regions in a real-world scenario informed by machine learning.  ...  To efficiently minimize the response times of a law enforcement agency operating in a dense urban environment with limited manpower, we consider in this paper the problem of optimizing the spatial and  ...  Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2019/806 dblp:conf/ijcai/ChaseNSL19 fatcat:b46e7m7xjnb7jimx3dzllmanfa
« Previous Showing results 1 — 15 out of 16,114 results