scholarly journals SIMULATION ANALYSIS FOR INTERACTIVE RETRIEVAL OF SPOKEN DOCUMENTS WITH KEY TERMS RANKED BY REINFORCEMENT LEARNING

2006 ◽  
Author(s):  
Yi-cheng Pan ◽  
Lin-shan Lee
Keyword(s):  
Reinforcement Learning ◽  
Simulation Analysis ◽  
Interactive Retrieval ◽  
Key Terms ◽  
Spoken Documents

scholarly journals Efficient interactive retrieval of spoken documents with key terms ranked by reinforcement learning

2006 ◽  
Author(s):  
Yi-cheng Pan ◽  
Jia-yu Chen ◽  
Yen-shin Lee ◽  
Yi-sheng Fu ◽  
Lin-shan Lee
Keyword(s):  
Reinforcement Learning ◽  
Interactive Retrieval ◽  
Key Terms ◽  
Spoken Documents

scholarly journals Actor-Critic Wavelet Neural Network based Scheduler Technique for LTE-Advanced

2020 ◽  
Vol 8 (5) ◽  
pp. 4856-4863
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Large Scale ◽  
Simulation Analysis ◽  
Resource Scheduling ◽  
Wavelet Neural Network ◽  
Time Interval ◽  
Sigmoid Function ◽  
Network Resource ◽  
Actor Network

This work presents an efficient and intelligent resource scheduling strategy for the Long Term EvolutionAdvanced (LTE-A) downlink transmission using Reinforcement learning and wavelet neural network. Resource scheduling in LTE-A suffers the problem of uncertainty and accuracy for large scale network. Also the performance of scheduling in conventional methods solely depends upon the scheduling algorithm which was fixed for the entire transmission session. This issue has been addressed and resolved in this paper through Actor-Critic architecture based reinforcement learning to provide the best suited scheduling method out of the rule set for every transmission time interval (TTI) of communication. The actor network will take the decision on scheduling and the critic network will evaluate this decision and update the actor network adaptively through the optimal tuning laws so as to get the desired performance in scheduling. Wavelet neural network(WNN) is derived here by using wavelet function as activation function in place of sigmoid function in conventional neural network to attain better learning capabilities, faster convergence and efficient decision making in scheduling. The actor and critic networks are created through these WNNs and are trained with the LTE parameters dataset. The efficacy of the presented work is evaluated through simulation analysis.

scholarly journals Surprise acts as a reducer of outcome value in human reinforcement learning

2019 ◽  
Author(s):  
Motofumi Sumiya ◽  
Kentaro Katahira
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Prediction Error ◽  
Simulation Analysis ◽  
Learning Task ◽  
Risk Averse ◽  
Choice Preference ◽  
Proposed Model ◽  
Modulation Parameter ◽  
Reinforcement Learning Models

Surprise occurs because of differences between a decision outcome and its predicted outcome (prediction error), regardless of whether the error is positive or negative. It has recently been postulated that surprise affects the reward value of the action outcome itself; studies have indicated that increasing surprise, as absolute value of prediction error, decreases the value of the outcome. However, how surprise affects the value of the outcome and subsequent decision making is unclear. We suggested that, on the assumption that surprise decreases the outcome value, agents will increase their risk averse choices when an outcome is often surprisal. Here, we propose the surprise-sensitive utility model, a reinforcement learning model that states that surprise decreases the outcome value, to explain how surprise affects subsequent decision-making. To investigate the assumption, we compared this model with previous reinforcement learning models on a risky probabilistic learning task with simulation analysis, and model selection with two experimental datasets with different tasks and population. We further simulated a simple decision-making task to investigate how parameters within the proposed model modulate the choice preference. As a result, we found the proposed model explains the risk averse choices in a manner similar to the previous models, and risk averse choices increased as the surprise-based modulation parameter of outcome value increased. The model fits these datasets better than the other models, with same free parameters, thus providing a more parsimonious and robust account for risk averse choices. These findings indicate that surprise acts as a reducer of outcome value and decreases the action value for risky choices in which prediction error often occurs.

Job Validation Studies and Physical Agility Testing: Is the Vendor Telling You What They Think You Want or Are You Telling Them What You Need?

2016 ◽  
Vol 21 (6) ◽  
pp. 5-11
Author(s):  
E. Randolph Soo Hoo ◽  
Stephen L. Demeter
Keyword(s):  
Equal Employment Opportunity Commission ◽  
Job Analysis ◽  
Specific Work ◽  
Test Protocol ◽  
Systematic Method ◽  
Technical Standards ◽  
Work Related ◽  
Physical Abilities ◽  
Specific Factors ◽  
Key Terms

Abstract Referring agents may ask independent medical evaluators if the examinee can return to work in either a normal or a restricted capacity; similarly, employers may ask external parties to conduct this type of assessment before a hire or after an injury. Functional capacity evaluations (FCEs) are used to measure agility and strength, but they have limitations and use technical jargon or concepts that can be confusing. This article clarifies key terms and concepts related to FCEs. The basic approach to a job analysis is to collect information about the job using a variety of methods, analyze the data, and summarize the data to determine specific factors required for the job. No single, optimal job analysis or validation method is applicable to every work situation or company, but the Equal Employment Opportunity Commission offers technical standards for each type of validity study. FCEs are a systematic method of measuring an individual's ability to perform various activities, and results are matched to descriptions of specific work-related tasks. Results of physical abilities/agilities tests are reported as “matching” or “not matching” job demands or “pass” or “fail” meeting job criteria. Individuals who fail an employment physical agility test often challenge the results on the basis that the test was poorly conducted, that the test protocol was not reflective of the job, or that levels for successful completion were inappropriate.

Comparative Analysis: The State of Colorado Study, Part II

2004 ◽  
Vol 9 (2) ◽  
pp. 1-16
Author(s):  
Christopher R. Brigham ◽  
Kathryn Mueller ◽  
Douglas Van Zet ◽  
Debra J. Northrup ◽  
Edward B. Whitney ◽  
...  
Keyword(s):  
Daily Living ◽  
Scientific Evidence ◽  
Pain Syndrome ◽  
Evidence Based ◽  
Clinical Assessments ◽  
Physician Judgment ◽  
History Of ◽  
Key Terms ◽  
Causation Analysis ◽  
Work Interference

Abstract [Continued from the January/February 2004 issue of The Guides Newsletter.] To understand discrepancies in reviewers’ ratings of impairments based on different editions of the AMA Guides to the Evaluation of Permanent Impairment (AMA Guides), users can usefully study the history of the revisions as successive editions attempted to provide a comprehensive, valid, reliable, unbiased, and evidence-based system. Some shortcomings of earlier editions have been addressed in the AMA Guides, Fifth Edition, but problems remain with each edition, largely because of the limited scientific evidence available. In the context of the history of the different editions of the AMA Guides and their development, the authors discuss and contextualize a number of key terms and principles including the following: definitions of impairment and normal; activities of daily living; maximum medical improvement; impairment percentages; conversion of regional impairments; combining impairments; pain and other subjective complaints; physician judgment; and causation analysis; finally, the authors note that impairment is not synonymous with disability or work interference. The AMA Guides, Fifth Edition, contrasts impairment evaluations and independent medical evaluations (this was not done in previous editions) and discusses impairment evaluations, rules for evaluations, and report standards. Upper extremity and lower extremity impairment evaluations are discussed in terms of clinical assessments and rating processes, analyzing important changes between editions and problematic areas (eg, complex regional pain syndrome).

Bayes factors for reinforcement-learning models of the Iowa gambling task.

Decision ◽  
2016 ◽  
Vol 3 (2) ◽  
pp. 115-131 ◽  
Author(s):  
Helen Steingroever ◽  
Ruud Wetzels ◽  
Eric-Jan Wagenmakers
Keyword(s):  
Reinforcement Learning ◽  
Iowa Gambling Task ◽  
Bayes Factors ◽  
Gambling Task ◽  
Learning Models ◽  
Reinforcement Learning Models
Sign in / Sign up

Export Citation Format

Share Document