1,280,571 Hits in 4.6 sec

Learning from Human-Generated Lists

Kwang-Sung Jun, Xiaojin (Jerry) Zhu, Burr Settles, Timothy T. Rogers
2013 International Conference on Machine Learning  
Human-generated lists are a form of non-iid data with important applications in machine learning and cognitive psychology.  ...  healthy people vs. patients from the lists they generate.  ...  Learning from human-generated lists opens up several lines of future work.  ... 
dblp:conf/icml/JunZSR13 fatcat:p2jh33ii6zbcnbn552qitxajgy

Enhancement of Single Document Text Summarization using Reinforcement Learning with Non-Deterministic Rewards

K. Karpagam, Dr. Mahalingam College of Engineering & Technology, Pollachi, A. Saradha, K. Manikandan, K. Madusudanan
2020 International Journal of Information Technology and Computer Science  
This research article proposes a novel framework for generating machine generated summaries using reinforcement learning techniques with Non-deterministic reward function.  ...  The machine generated summaries uses information retrieval techniques for searching relevant answers from large corpus.  ...  The answers rated by the users are collected as a list. From the list generated, more likely answers are chosen from the user's perspective.  ... 
doi:10.5815/ijitcs.2020.04.03 fatcat:6abml35ea5blrlpbaa4bvsiybq

Motivated Learning In Human-Machine Improvisation

Peter Beyls
2018 Zenodo  
A variation of Q-learning is used featuring a self-optimizing variable length state-action-reward list.  ...  In an attempt to avoid explicit mapping of user actions to machine responses, an experimental machine learning strategy is suggested where rewards are derived from the implied motivation of the human interactor  ...  Learning in Pock Learning is coordinated from the SAR-list, a variable length collection of State-Action-Reward entries.  ... 
doi:10.5281/zenodo.1302564 fatcat:zyrzkrg3qfc3dafj5b6okrcadm

Remaking memories: Reconsolidation updates positively motivated spatial memory in rats

B. Jones, E. Bukoski, L. Nadel, J.-M. Fellous
2012 Learning & memory (Cold Spring Harbor, N.Y.)  
In this study we investigated reactivation-dependent updating using a new positively motivated spatial task in rodents that was designed specifically to model a human list-learning paradigm.  ...  Finally, the level of intrusions was highest when retrieval took place immediately after List 2 learning, and generally declined when retrieval occurred 1-4 h later, indicating that the List 2 memory competed  ...  On Day 2, the Reminder group was asked to recall the general procedure (but not the actual list) from Day 1 (the "reminder question"), and then learned a second list (List 2) of objects in the same room  ... 
doi:10.1101/lm.023408.111 pmid:22345494 pmcid:PMC3293515 fatcat:fkddm4ksxraarptldgee52yqmq

An Evolutionary Algorithm to Learn SPARQL Queries for Source-Target-Pairs [chapter]

Jörn Hees, Rouven Bauer, Joachim Folz, Damian Borth, Andreas Dengel
2016 Lecture Notes in Computer Science  
Given a training list of source-target node-pair examples our algorithm can learn patterns (SPARQL queries) from a SPARQL endpoint.  ...  Further, we use the resulting SPARQL queries to mimic human associations with a Mean Average Precision (MAP) of 39.9 % and a Recall@10 of 63.9 %.  ...  It is unique in that it can learn a set of SPARQL graph patterns for a given input list of source-target-pairs directly from a given SPARQL endpoint.  ... 
doi:10.1007/978-3-319-49004-5_22 fatcat:nv7wyssivbcwzihnfgr5egorri

Sequential learning in non-human primates

Christopher M. Conway, Morten H. Christiansen
2001 Trends in Cognitive Sciences  
In this article, we investigate sequential learning in non-human primates from a comparative perspective, focusing on three areas: the learning of arbitrary, fixed sequences; statistical learning; and  ...  that limitations in sequential learning may help explain why non-human primates lack human-like language. al. (1994) Practice-related changes in human brain functional anatomy during nonmotor learning  ...  The pattern of performance differences across species might suggest that human sequential learning derives from evolutionarily old cognitive substrates, from which the sequential learning abilities of  ... 
doi:10.1016/s1364-6613(00)01800-3 pmid:11728912 fatcat:3zzl3msd65evvf2zgz5v6gsjxm

Predicting Human Associations with Graph Patterns Learned from Linked Data

Jörn Hees, Rouven Bauer, Joachim Folz, Damian Borth, Andreas Dengel
2017 International Semantic Web Conference  
Given a training list of source-targetpairs, our algorithm learns a predictive model, which given a new source entity predicts target entities analogously to the training examples.  ...  In this demo paper we present a high level overview over our graph pattern learner and show its application to simulate human associations (e.g., "fish -water").  ...  source variable In order to fuse such resulting target-lists for a provided new source node, the graph pattern learner includes a fusion training component that generates late fusion machine learning  ... 
dblp:conf/semweb/HeesBFBD17 fatcat:wqbypyidfrdrvbaxz3yult63ha

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning [article]

Kevin Ellis, Catherine Wong, Maxwell Nye, Mathias Sable-Meyer, Luc Cary, Lucas Morales, Luke Hewitt, Armando Solar-Lezama, Joshua B. Tenenbaum
2020 arXiv   pre-print
Concepts are built compositionally from those learned earlier, yielding multi-layered symbolic representations that are interpretable and transferrable to new tasks, while still growing scalably and flexibly  ...  Acquiring expertise means learning these languages -- systems of concepts, alongside the skills to use them. We present DreamCoder, a system that learns to solve problems by writing programs.  ...  While machine learning is data hungry, typically generalizing weakly from experience, human learners can often generalize strongly from only modest experience.  ... 
arXiv:2006.08381v1 fatcat:kr23wn42wzakbpqjqxqnbbhnne

Page 435 of Behavior Research Methods Vol. 33, Issue 3 [page]

2001 Behavior Research Methods  
W'e have examined mouse, rat. and human list acquisition of patterns ranging from 12 to 48 items in length.  ...  MINER We.slegan College, Macon, Georgia We have developed a method for studying list learning in animals and humans, and we use variants of the task to examine list learning in rats, mice, and humans.  ... 

Construction of a Dialog System for Talking Using a Topic Maps-Based Online Learning System

Shu Matsuura
2018 Forma  
This study attempts to construct a dialog system to retrieve information from an online learning system. It uses a humanoid robot, NAO, as an interface to convey information.  ...  These two models enabled an efficient dialog for retrieving information from the online learning system. However, the fluency of the dialog depends on how well the user knows the topic map ontology.  ...  This work was funded by a Grant-in-Aid for Scientific Research (C) 15K00912 from the Ministry of Education, Culture, Sports, Science and Technology of Japan.  ... 
doi:10.5047/forma.2018.s006 fatcat:mfretkmlnrhfbk77ng5e3nv64m

MINERVA 2: A simulation model of human memory

Douglas L. Hintzman
1984 Behavoir research methods, instruments & computers  
The model has been applied with success to a variety of phenomena found with human subjects in frequency and recognition judgment tasks, the schema-abstraction task, and paired-associate learning.  ...  An overview of a simulation model of human memory is presented.  ...  As with human subjects, there is a small amount of generalization from frequency of the test item in the nontarget list.  ... 
doi:10.3758/bf03202365 fatcat:xzseenoa6zh5linqzdvu7razxy

Interactive robot task training through dialog and demonstration

Paul E. Rybski, Kevin Yoon, Jeremy Stolarz, Manuela M Veloso
2007 Proceeding of the ACM/IEEE international conference on Human-robot interaction - HRI '07  
We present a framework for interactive task training of a mobile robot where the robot learns how to do various tasks while observing a human.  ...  In this paper, we describe the task training framework, describe how environmental context and communicative dialog with the human help the robot learn the task, and illustrate the utility of this approach  ...  This research was supported by the National Business Center (NBC) of the Department of the Interior (DOI) under a subcontract from SRI International.  ... 
doi:10.1145/1228716.1228724 dblp:conf/hri/RybskiYSV07 fatcat:4nzmohni3zdrrjoyapx4qkvw7m

Transfer of a Serial Representation between Two Distinct Tasks by Rhesus Macaques

Greg Jensen, Drew Altschul, Erin Danly, Herbert Terrace, Johan J. Bolhuis
2013 PLoS ONE  
After learning a list in one paradigm, subjects' knowledge of that list was tested using the other paradigm. Performance was enhanced from the very start of transfer training.  ...  The patterns of error displayed by subjects in both tasks were best explained by a spatially coded representation of list items, regardless of which task was used to learn the list.  ...  It seems reasonable to conclude that our subjects ''learned each list'' in a general sense, rather than merely ''learning each task'' in the narrow sense of a circus trick.  ... 
doi:10.1371/journal.pone.0070285 pmid:23936179 pmcid:PMC3729468 fatcat:75fxivqne5ci5khq4di6cb5cdq

Leveraging Language to Learn Program Abstractions and Search Heuristics [article]

Catherine Wong and Kevin Ellis and Joshua B. Tenenbaum and Jacob Andreas
2022 arXiv   pre-print
Inductive program synthesis, or inferring programs from examples of desired behavior, offers a general paradigm for building interpretable, robust, and generalizable machine learning systems.  ...  When integrated into a state-of-the-art library learning system (DreamCoder), LAPS produces higher-quality libraries and improves search efficiency and generalization on three domains -- string editing  ...  Supported by grants from the Air Force Office of Scientific Research, the NSF under Grant No.  ... 
arXiv:2106.11053v3 fatcat:no3vln7vdjfz5lmuanfjftvzra

The Science of the Deal: Optimal Bargaining on eBay Using Deep Reinforcement Learning

Etan A. Green, E. Barry Plunkett
2022 Proceedings of the 23rd ACM Conference on Economics and Computation  
We train a reinforcement learning agent to bargain optimally in "Best Offer" listings on eBay, and we characterize its behavior in a manner that humans can use.  ...  Simple strategies derived from these agents purchase more items for lower prices than human buyers and sell more items for higher prices than human sellers.  ...  Buyer offers inform sellers about demand for their items, and sellers should learn from these signals.  ... 
doi:10.1145/3490486.3538373 fatcat:m6cdc26ikbaqdmddvcvrhjipoe
« Previous Showing results 1 — 15 out of 1,280,571 results