scholarly journals Information Shaping for Enhanced Goal Recognition of Partially-Informed Agents

2020 ◽  
Vol 34 (06) ◽  
pp. 9908-9915
Author(s):  
Sarah Keren ◽  
Haifeng Xu ◽  
Kofi Kwapong ◽  
David Parkes ◽  
Barbara Grosz
Keyword(s):  
Incomplete Information ◽  
Recognition Task ◽  
Search Space ◽  
Perfect Information ◽  
Suggested Method ◽  
Information Revelation ◽  
Goal Recognition ◽  
Effectiveness And Efficiency

We extend goal recognition design to account for partially informed agents. In particular, we consider a two-agent setting in which one agent, the actor, seeks to achieve a goal but has only incomplete information about the environment. The second agent, the recognizer, has perfect information and aims to recognize the actor's goal from its behavior as quickly as possible. As a one-time offline intervention and with the objective of facilitating the recognition task, the recognizer can selectively reveal information to the actor. The problem of selecting which information to reveal, which we call information shaping, is challenging not only because the space of information shaping options may be large, but also because more information revelation need not make it easier to recognize an agent's goal. We formally define this problem, and suggest a pruning approach for efficiently searching the search space. We demonstrate the effectiveness and efficiency of the suggested method on standard benchmarks.

scholarly journals What Do Cows Drink? A Systems Factorial Technology Account of Processing Architecture in Memory Intersection Problems

2019 ◽  
Author(s):  
Zachary L Howard ◽  
Bianca Belevski ◽  
Ami Eidels ◽  
Simon Dennis
Keyword(s):  
Recognition Task ◽  
Search Space ◽  
Memory Recall ◽  
Improve Performance ◽  
Essential Information ◽  
Systems Factorial Technology ◽  
Memory Problems ◽  
Processing Architecture ◽  
Model Mimicry ◽  
Parallel Strategy

It has long been known that cues can be used to improve performance on memory recall tasks. There is evidence to suggest additional cues provide further benefit, presumably by narrowing the search space. Problems that require integration of two or more cues, alternately referred to as memory intersections or multiply constrained memory problems, could be approached using several strategies, namely serial or parallel consideration of cues. The type of strategy implicated is essential information for the development of theories of memory, yet evidence to date has been inconclusive. Using a novel application of the powerful Systems Factorial Technology (Townsend & Nozawa, 1995) we find strong evidence that participants use two cues in parallel in free recall tasks - a finding that contradicts two recent publications in this area. We then provide evidence from a related recognition task showing that while most participants also use a parallel strategy in that paradigm, a reliable subset of participants used a serial strategy. Our findings suggest a theoretically meaningful distinction between participants strategies in recall and recognition based intersection memory tasks, and also highlight the importance of tightly controlled methodological and analytic frameworks to overcome issues of serial/parallel model mimicry.

scholarly journals A Sequence-to-Set Network for Nested Named Entity Recognition

2021 ◽  
Author(s):  
Zeqi Tan ◽  
Yongliang Shen ◽  
Shuai Zhang ◽  
Weiming Lu ◽  
Yueting Zhuang
Keyword(s):  
Language Processing ◽  
Named Entity Recognition ◽  
Recognition Task ◽  
Search Space ◽  
Entity Recognition ◽  
Bipartite Matching ◽  
Named Entity ◽  
Proposed Model ◽  
Fixed Set ◽  
Sequence Method

Named entity recognition (NER) is a widely studied task in natural language processing. Recently, a growing number of studies have focused on the nested NER. The span-based methods, considering the entity recognition as a span classification task, can deal with nested entities naturally. But they suffer from the huge search space and the lack of interactions between entities. To address these issues, we propose a novel sequence-to-set neural network for nested NER. Instead of specifying candidate spans in advance, we provide a fixed set of learnable vectors to learn the patterns of the valuable spans. We utilize a non-autoregressive decoder to predict the final set of entities in one pass, in which we are able to capture dependencies between entities. Compared with the sequence-to-sequence method, our model is more suitable for such unordered recognition task as it is insensitive to the label order. In addition, we utilize the loss function based on bipartite matching to compute the overall training loss. Experimental results show that our proposed model achieves state-of-the-art on three nested NER corpora: ACE 2004, ACE 2005 and KBP 2017. The code is available at https://github.com/zqtan1024/sequence-to-set.

scholarly journals Quantum-Inspired Evolutionary Algorithm for Continuous Space Optimization Based on Multiple Chains Encoding Method of Quantum Bits

2014 ◽  
Vol 2014 ◽  
pp. 1-16 ◽  
Author(s):  
Rui Zhang ◽  
Zhiteng Wang ◽  
Hongjun Zhang
Keyword(s):  
Evolutionary Algorithms ◽  
Evolutionary Algorithm ◽  
Evolutionary Rate ◽  
Search Space ◽  
Performance Comparison ◽  
Rotational Angle ◽  
Continuous Space ◽  
Quantum Bits ◽  
Effectiveness And Efficiency ◽  
Encoding Method

This study proposes a novel quantum evolutionary algorithm called four-chain quantum-inspired evolutionary algorithm (FCQIEA) based on the four gene chains encoding method. In FCQIEA, a chromosome comprises four gene chains to expand the search space effectively and promote the evolutionary rate. Different parameters, including rotational angle and mutation probability, have been analyzed for better optimization. Performance comparison with other quantum-inspired evolutionary algorithms (QIEAs), evolutionary algorithms, and different chains of QIEA demonstrates the effectiveness and efficiency of FCQIEA.

scholarly journals Inferring Agents’ Goals from Observing Successful Traces

2021 ◽  
Vol 11 (9) ◽  
pp. 4116
Author(s):  
Guillaume Lorthioir ◽  
Katsumi Inoue ◽  
Gauvain Bourgne
Keyword(s):  
Concept Learning ◽  
Propositional Logic ◽  
Learning Algorithm ◽  
Search Space ◽  
Plan Recognition ◽  
Goal Recognition

Goal recognition is a sub-field of plan recognition that focuses on the goals of an agent. Current approaches in goal recognition have not yet tried to apply concept learning to a propositional logic formalism. In this paper, we extend our method for inferring an agent’s possible goal by observing this agent in a series of successful attempts to reach its goal and using concept learning on these observations. We propose an algorithm, LFST (Learning From Successful Traces), to produce concise hypotheses about the agent’s goal. We show that if such a goal exists, our algorithm always provides a possible goal for the agent, and we evaluate the performance of our algorithm in different settings. We compare it to another concept-learning algorithm that uses a formalism close to ours, and we obtain better results at producing the hypotheses with our algorithm. We introduce a way to use assumptions about the agent’s behavior and the dynamics of the environment, thus improving the agent’s goal deduction by optimizing the potential goals’ search space.

scholarly journals Comparison of Histogram Feature Based Thresholding with 3S Multi-Thresholding and Fuzzy C-Means

2019 ◽  
Vol 8 (1) ◽  
pp. 15
Author(s):  
Mostafa Langarizadeh ◽  
Rozi Mahmud
Keyword(s):  
Clustering Algorithm ◽  
Search Space ◽  
Suggested Method ◽  
Lesion Area ◽  
Thresholding Method ◽  
Segmentation Quality ◽  
Feature Based ◽  
Mammogram Image ◽  
Contrast Stretching ◽  
Histogram Feature

Introduction: Thresholding is one of the most important parts of segmentation whenever we want to detect a specific part of image. There are several thresholding methods that previous researchers used them frequently as bi-level techniques such as DBT or multilevel such as 3S. New histogram feature thresholding method is implemented to detect lesion area in digital mammograms and compared with 3S (Shrinking-Search-Space) multithresholding and FCM method in terms of segmentation quality and segmentation time as a benchmark in thresholding.Materials and Methods: These algorithms have been tested on 188 digital mammograms. Digital mammogram image used after preprocessing which was including crop the unnecessary area, resize the image into 1024 by 1024 pixel and then normalize pixel values by using simple contrast stretching method.Results: The results show that suggested method results are not similar with 3S and FCM methods, and it is faster than other methods. This is another superiority of suggested method with respect to others. Results of previous studies showed that FCM is not a reliable clustering algorithm and it needs several run to give us a reliable result (1). Results of this study also showed that this approach is correct.Conclusions: The suggested method may used as a reliable thresholding method in order to detection of lesion area.

Policy-Combination Oriented Optimization for Supply Chain Simulation

2013 ◽  
Vol 302 ◽  
pp. 646-651
Author(s):  
Wen Zhe Tan ◽  
Xin Li ◽  
Yue Ting Chai
Keyword(s):  
Supply Chain ◽  
Optimization Problem ◽  
Search Space ◽  
Performance Evaluations ◽  
Optimization Approach ◽  
Quantitative Performance ◽  
Alternative Approaches ◽  
Effectiveness And Efficiency ◽  
Supply Chain Simulation

Supply chain simulation is able to capture the dynamics and uncertainties in all kinds of supply chains and provide quantitative performance evaluations. In order to address the time consuming evaluation and large search space issues in supply chain simulation, this paper proposes a policy-combination oriented optimization approach to conduct decision makings. The approach begins with reducing the search space by relaxing the goal of optimization, and then refers to meta-heuristic searching methods to solve the main bi-level optimization problem. Lastly the key parameters are fine-tuned with what-if analysis. A case study demonstrates the effectiveness and efficiency of the proposed approach, and compares it with other alternative approaches available in practice.

Picture Recognition Errors in the Differential Diagnosis of Alzheimer’s Disease

2019 ◽  
Vol 30 (3) ◽  
pp. 157-168
Author(s):  
Helmut Hildebrandt ◽  
Jana Schill ◽  
Jana Bördgen ◽  
Andreas Kastrup ◽  
Paul Eling
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Differential Diagnosis ◽  
Clinical Diagnosis ◽  
Response Bias ◽  
Recognition Task ◽  
Discriminatory Power ◽  
False Alarms ◽  
Picture Recognition ◽  
Recognition Errors

Abstract. This article explores the possibility of differentiating between patients suffering from Alzheimer’s disease (AD) and patients with other kinds of dementia by focusing on false alarms (FAs) on a picture recognition task (PRT). In Study 1, we compared AD and non-AD patients on the PRT and found that FAs discriminate well between these groups. Study 2 served to improve the discriminatory power of the FA score on the picture recognition task by adding associated pairs. Here, too, the FA score differentiated well between AD and non-AD patients, though the discriminatory power did not improve. The findings suggest that AD patients show a liberal response bias. Taken together, these studies suggest that FAs in picture recognition are of major importance for the clinical diagnosis of AD.

Use It and Still Lose It?

GeroPsych ◽  
2010 ◽  
Vol 23 (3) ◽  
pp. 169-175 ◽  
Author(s):  
Adrian Schwaninger ◽  
Diana Hardmeier ◽  
Judith Riegelnig ◽  
Mike Martin
Keyword(s):  
Object Recognition ◽  
Cognitive Development ◽  
Recognition Test ◽  
Cognitive Aging ◽  
Recognition Task ◽  
Airport Security ◽  
Visual Object ◽  
Long Term Effects ◽  
Object Recognition Test ◽  
X Ray

In recent years, research on cognitive aging increasingly has focused on the cognitive development across middle adulthood. However, little is still known about the long-term effects of intensive job-specific training of fluid intellectual abilities. In this study we examined the effects of age- and job-specific practice of cognitive abilities on detection performance in airport security x-ray screening. In Experiment 1 (N = 308; 24–65 years), we examined performance in the X-ray Object Recognition Test (ORT), a speeded visual object recognition task in which participants have to find dangerous items in x-ray images of passenger bags; and in Experiment 2 (N = 155; 20–61 years) in an on-the-job object recognition test frequently used in baggage screening. Results from both experiments show high performance in older adults and significant negative age correlations that cannot be overcome by more years of job-specific experience. We discuss the implications of our findings for theories of lifespan cognitive development and training concepts.

The Mere Exposure Effect and Recognition Depend on the Way You Look! *S. W. and J. D. contributed equally to this study.

2010 ◽  
Vol 57 (3) ◽  
pp. 185-192 ◽  
Author(s):  
Sylvie Willems ◽  
Jonathan Dedonder ◽  
Martial Van der Linden
Keyword(s):  
Differential Effect ◽  
Recognition Task ◽  
Mere Exposure ◽  
Perceptual Processing ◽  
Processing Strategy ◽  
Mere Exposure Effect ◽  
Exposure Effect ◽  
Processing Strategies ◽  
Explicit Recognition ◽  
Analytic Strategy

In line with Whittlesea and Price (2001) , we investigated whether the memory effect measured with an implicit memory paradigm (mere exposure effect) and an explicit recognition task depended on perceptual processing strategies, regardless of whether the task required intentional retrieval. We found that manipulation intended to prompt functional implicit-explicit dissociation no longer had a differential effect when we induced similar perceptual strategies in both tasks. Indeed, the results showed that prompting a nonanalytic strategy ensured performance above chance on both tasks. Conversely, inducing an analytic strategy drastically decreased both explicit and implicit performance. Furthermore, we noted that the nonanalytic strategy involved less extensive gaze scanning than the analytic strategy and that memory effects under this processing strategy were largely independent of gaze movement.

Sign in / Sign up

Export Citation Format

Share Document