检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data (Big Data)

作者： Keeling, Robert Chhatwal, Rishi Huber-Fliflet, Nathaniel Zhang, Jianping Wei, Fusheng Zhao, Haozhen Shi, Ye Qin, Han Sidley Austin LLP Complex Commercial Litigat Washington DC 20005 USA AT&T Serv Inc Legal Washington DC USA Ankura Data & Technol Washington DC USA

ISBN: (纸本)9781728108582

Research has shown that Convolutional Neural Networks (CNN) can be effectively applied to text classification as part of a predictive coding protocol. That said, most research to date has been conducted on data sets with short documents that do not reflect the variety of documents in real world document reviews. Using data from four actual reviews with documents of varying lengths, we compared CNN with other popular machine learning algorithms for text classification, including Logistic Regression, Support Vector Machine, and Random Forest. For each data set, classification models were trained with different training sample sizes using different learning algorithms. These models were then evaluated using a large randomly sampled test set of documents, and the results were compared using precision and recall curves. Our study demonstrates that CNN performed well, but that there was no single algorithm that performed the best across the combination of data sets and training sample sizes. These results will help advance research into the legal profession's use of machine learning algorithms that maximize performance.

关键词： text classification predictive coding CNN legal document review machine learning

来源：评论

学校读者我要写书评

暂无评论

Achieving Human-Robot Collaboration with Dynamic Goal Inference by Gradient Descent 26th

Achieving Human-Robot Collaboration with Dynamic Goal Infere...

引用

26th International Conference on Neural Information Processing (ICONIP) of the Asia-Pacific-Neural-Network-Society (APNNS)

作者： Murata, Shingo Masuda, Wataru Chen, Jiayi Arie, Hiroaki Ogata, Tetsuya Sugano, Shigeki Natl Inst Informat Principles Informat Res Div Tokyo Japan Grad Univ Adv Studies SOKENDAI Dept Informat Tokyo Japan Waseda Univ Dept Modern Mech Engn Tokyo Japan Waseda Univ Future Robot Org Tokyo Japan Waseda Univ Dept Intermedia Art & Sci Tokyo Japan

ISBN: (纸本)9783030367114;9783030367107

Collaboration with a human partner is a challenging task expected of intelligent robots. To realize this, robots need the ability to share a particular goal with a human and dynamically infer whether the goal state is changed by the human. In this paper, we propose a neural network-based computational framework with a gradient-based optimization of the goal state that enables robots to achieve this ability. The proposed framework consists of convolutional variational autoencoders (ConvVAEs) and a recurrent neural network (RNN) with a long short-term memory (LSTM) architecture that learns to map a given goal image for collaboration to visuomotor predictions. More specifically, visual and goal feature states are first extracted by the encoder of the respective ConvVAEs. Visual feature and motor predictions are then generated by the LSTM based on their current state and are conditioned according to the extracted goal feature state. During collaboration after the learning process, the goal feature state is optimized by gradient descent to minimize errors between the predicted and actual visual feature states. This enables the robot to dynamically infer situational (goal) changes of the human partner from visual observations alone. The proposed framework is evaluated by conducting experiments on a human-robot collaboration task involving object assembly. Experimental results demonstrate that a robot equipped with the proposed framework can collaborate with a human partner through dynamic goal inference even when the situation is ambiguous.

关键词： Human-robot collaboration Robot learning Deep learning predictive coding Prediction error minimization

来源：评论

学校读者我要写书评

暂无评论

The Cognitive-Evolutionary Model of Surprise: A Review of the Evidence

引用

TOPICS IN COGNITIVE SCIENCE 2019年第1期11卷 50-74页

作者： Reisenzein, Rainer Horstmann, Gernot Schuetzwohl, Achim Univ Greifswald Inst Psychol Franz Mehring Str 47 D-17487 Greifswald Germany Univ Bielefeld Inst Psychol Bielefeld Germany Brunel Univ London Dept Life Sci London England

Research on surprise relevant to the cognitive-evolutionary model of surprise proposed by Meyer, Reisenzein, and Schutzwohl (1997) is reviewed. The majority of the assumptions of the model are found empirically supported. Surprise is evoked by unexpected (schema-discrepant) events and its intensity is determined by the degree if schema-discrepancy, whereas the novelty and the valence of the eliciting events probably do not have an independent effect. Unexpected events cause an automatic interruption of ongoing mental processes that is followed by an attentional shift and attentional binding to the events, which is often followed by causal and other event analysis processes and by schema revision. The facial expression of surprise postulated by evolutionary emotion psychologists has been found to occur rarely in surprise, for as yet unknown reasons. A physiological orienting response marked by skin conductance increase, heart rate deceleration, and pupil dilation has been observed to occur regularly in the standard version of the repetition-change paradigm of surprise induction, but the specificity of these reactions as indicators of surprise is controversial. There is indirect evidence for the assumption that the feeling of surprise consists of the direct awareness of the schema-discrepancy signal, but this feeling, or at least the self-report of surprise, is also influenced by experienced interference. In contrast, facial feedback probably does contribute substantially to the feeling of surprise and the evidence for the hypothesis that surprise is affected by the difficulty of explaining an unexpected event is, in our view, inconclusive. Regardless of how the surprise feeling is constituted, there is evidence that it has both motivational and informational effects. Finally, the prediction failure implied by unexpected events sometimes causes a negative feeling, but there is no convincing evidence that this is always the case, and we argue that even if it were so, t

关键词： Surprise Unexpectedness Schema-updating Cognitive-evolutionary model Emotion predictive coding Review

来源：评论

学校读者我要写书评

暂无评论

Individual differences in the effects of priors on perception: A multi-paradigm approach

引用

COGNITION 2019年 187卷 167-177页

作者： Tulver, Kadi Aru, Jaan Rutiku, Renate Bachmann, Talis Univ Tartu Inst Psychol Tartu Estonia Univ Tartu Inst Penal Law Tartu Estonia Univ Tartu Inst Comp Sci Tartu Estonia Humboldt Univ Inst Biol Berlin Germany

The present study investigated individual differences in how much subjects rely on prior information, such as expectations or knowledge, when faced with perceptual ambiguity. The behavioural performance of forty-four participants was measured on four different visual paradigms (Mooney face recognition, illusory contours, blur detection and representational momentum) in which priors have been shown to affect perception. In addition, questionnaires were used to measure autistic and schizotypal traits in the non-clinical population. We hypothesized that someone who in the face of ambiguous or noisy perceptual input relies heavily on priors, would exhibit this tendency across a variety of tasks. This general pattern would then be reflected in high pairwise correlations between the behavioural measures and an emerging common factor. On the contrary, our results imply that there is no single factor that explains the individual differences present in the aforementioned tasks, as further evidenced by the overall lack of robust correlations between the separate paradigms. Instead, a two factor structure reflecting differences in the hierarchy of perceptual processing was the best fit for explaining the individual variance in these tasks. This lends support to the notion that mechanisms underlying the effects of priors likely originate from several independent sources and that it is important to consider the role of specific tasks and stimuli more carefully when reporting effects of priors on perception.

关键词： Visual perception predictive coding Individual differences Priors Autistic traits Schizotypy

来源：评论

学校读者我要写书评

暂无评论

Increased subcortical neural responses to repeating auditory stimulation in children with autism spectrum disorder

引用

BIOLOGICAL PSYCHOLOGY 2020年第0期149卷 107807-000页

作者： Font-Alaminos, Marta Cornella, Miriam Costa-Faidella, Jordi Hervas, Amaia Leung, Sumie Rueda, Isabel Escera, Carles Univ Barcelona Inst Neurosci Barcelona 08035 Catalonia Spain Univ Barcelona Dept Clin Psychol & Psychobiol Brainlab Cognit Neurosci Res Grp P Vall dHebron 171 Barcelona 08035 Catalonia Spain Hosp St Joan de Deu UETD Barcelona 08950 Catalonia Spain IRSJD Barcelona 08950 Catalonia Spain Hosp Univ Mutua Terrassa Barcelona Catalonia Spain IGAIN Barcelona Catalonia Spain

Recent research has highlighted atypical reactivity to sensory stimulation as a core symptom in children with autism spectrum disorder (ASD). However, little is known about the dysfunctional neurological mechanisms underlying these aberrant sensitivities. Here we tested the hypothesis that the ability to filter out auditory repeated information is deficient in children with ASD already from subcortical levels, yielding to auditory sensitivities. We recorded the frequency-following response (FFR), a non-invasive measure of the neural tracking of the periodic characteristics of a sound in the subcortical auditory system, to compare repetition-related effects in children with ASD and typically developing children. Results revealed an increase of the FFR with stimulus repetition in children with ASD compared to their peers. Moreover, such defective early sensory encoding of stimulus redundancy was associated with sensory overload. These results highlight that auditory sensitivities in ASD emerge already at the level of the subcortical auditory system.

关键词： Frequency-following response Autism spectrum disorder predictive coding Auditory processing

来源：评论

学校读者我要写书评

暂无评论

The Power of Predictions: An Emerging Paradigm for Psychological Research

引用

CURRENT DIRECTIONS IN PSYCHOLOGICAL SCIENCE 2019年第3期28卷 280-291页

作者： Hutchinson, J. Benjamin Barrett, Lisa Feldman Univ Oregon Dept Psychol Eugene OR 97403 USA Northeastern Univ Dept Psychol 360 Huntington Ave Boston MA 02115 USA Massachusetts Gen Hosp Dept Psychiat Boston MA 02114 USA Harvard Med Sch Boston MA 02115 USA Massachusetts Gen Hosp Athinoula A Martinos Ctr Biomed Imaging Charlestown MA USA

In the last two decades, neuroscience studies have suggested that various psychological phenomena are produced by predictive processes in the brain. When considered together, these studies form a coherent, neurobiologically inspired program for guiding psychological research about the mind and behavior. In this article, we consider the common assumptions and hypotheses that unify an emerging framework and discuss the ramifications of such a framework, both for improving the replicability and robustness of psychological research and for renewing psychological theory by suggesting an alternative ontology of the human mind.

关键词： predictive coding active inference allostasis memory emotion perception concepts social cognition metabolism energetics

来源：评论

学校读者我要写书评

暂无评论

The Role of the Anterior Cingulate Cortex in Prediction Error and Signaling Surprise

引用

TOPICS IN COGNITIVE SCIENCE 2019年第1期11卷 119-135页

作者： Alexander, William H. Brown, Joshua W. Univ Ghent Dept Expt Psychol Ghent Belgium Indiana Univ Dept Psychol & Brain Sci 1101 E Tenth St Bloomington IN 47401 USA

In the past two decades, reinforcement learning (RL) has become a popular framework for understanding brain function. A key component of RL models, prediction error, has been associated with neural signals throughout the brain, including subcortical nuclei, primary sensory cortices, and prefrontal cortex. Depending on the location in which activity is observed, the functional interpretation of prediction error may change: Prediction errors may reflect a discrepancy in the anticipated and actual value of reward, a signal indicating the salience or novelty of a stimulus, and many other interpretations. Anterior cingulate cortex (ACC) has long been recognized as a region involved in processing behavioral error, and recent computational models of the region have expanded this interpretation to include a more general role for the region in predicting likely events, broadly construed, and signaling deviations between expected and observed events. Ongoing modeling work investigating the interaction between ACC and additional regions involved in cognitive control suggests an even broader role for cingulate in computing a hierarchically structured surprise signal critical for learning models of the environment. The result is a predictive coding model of the frontal lobes, suggesting that predictive coding may be a unifying computational principle across the neocortex. This paper reviews the brain mechanisms responsible for surprise;focusing on the Anterior Cingulate Cortex (ACC), long-known to play a role in behavioral-error, with a recently-expanded role in predicting likely' events and signaling deviations between expected and observed events. It argues for ACC's role in in surprise and learning, based on recent modelling work. As such, the paper provides the neuroscience complement to the psychological and computational proposals of other papers in the volume.

关键词： Surprise Prediction error Reinforcement learning Anterior cingulate Prefrontal cortex predictive coding

来源：评论

学校读者我要写书评

暂无评论

Sensory sensitivity in autism mostly depends on contextual predictions

引用

COGNITIVE NEUROSCIENCE 2019年第3期10卷 162-164页

作者： Sapey-Triomphe, Laurie-Anne Costa, Thiago Leiros Wagemans, Johan Katholieke Univ Leuven Dept Brain & Cognit Lab Expt Psychol Leuven Brain Inst Leuven Belgium

A signal detection theory was elaborated in order to account for three types of sensory sensitivity (subjective, behavioral and neural) in neurotypical individuals and in autism. Here, we argue that the predictive coding framework could better account for the atypical pattern of sensory sensitivity in autism. We review the idea that sensory sensitivity should be considered as mostly depending on contextual predictions and that these account for the heterogeneous pattern of neural responses.

关键词： Autism spectrum disorder predictive coding sensory sensitivity hypersensitivity predictions inflexibility

来源：评论

学校读者我要写书评

暂无评论

Self-control and interoception: Linking the neural substrates of craving regulation and the prediction of aversive interoceptive states induced by inspiratory breathing restriction

引用

NEUROIMAGE 2020年 215卷 116841-116841页

作者： Walter, Henrik Kausch, Anne Dorfschmidt, Lena Waller, Lea Chinichian, Narges Veer, Ilya Hilbert, Kevin Lueken, Ulrike Paulus, Martin P. Goschke, Thomas Kruschwitz, Johann D. Charite Univ Med Berlin Dept Psychiat & Psychotherapy Div Mind & Brain Res D-10117 Berlin Germany Tech Univ Dresden Dept Psychol Dresden Germany Laureate Inst Brain Res Tulsa OK USA Tech Univ Dresden Collaborat Res Ctr SFB Volit & Cognit Control 940 D-01069 Dresden Germany Humboldt Univ Dept Psychol Berlin Germany

Following the interoceptive inference framework, we set out to replicate our previously reported association of self-control and interoceptive prediction and strived to investigate the neural underpinnings subserving the relationship between self-control and aversive interoceptive predictive models. To this end, we used fMRI and a within-subject design including an inspiratory breathing-load task to examine the prediction of aversive interoceptive perturbation and a craving-regulation for palatable foods task to measure self-control. In this current study, we could successfully replicate previous effects with an independent sample (n = 39) and observed that individuals who ‘over-estimated’ their upcoming interoceptive state with respect to experienced dyspnea (i.e., anticipated versus experienced) were more effective in the down-regulation of craving using negative future-thinking strategies. These individuals, again, obtained higher scores on a measure of trait self-control, i.e. self-regulation to achieve long-term goals. On a neural level, we found evidence that the anterior insula (AI) and the presupplementary motor area (preSMA), which were recruited in both tasks, partly accounted for these effects. Specifically, levels of AI activation during the anticipation of the aversive interoceptive state (breathing restriction) were associated with self-controlled behavior in the craving task, whereas levels of interoceptive prediction during the breathing task were conversely associated with activation in preSMA during the down-regulation of craving, whose anticipatory activity was correlated with self-control success. Moreover, during the self-control task, levels of interoceptive prediction were associated with connectivity in a spatially distributed network including among other areas the insula and regions of cognitive control, while during the interoceptive prediction task, levels of self-control were associated with connectivity in a spatially distributed netw

关键词： fMRI Self-control Craving-regulation Inspiratory breathing load Interoception Interoceptive inference predictive coding Embodied cognition Anterior insula

来源：评论

学校读者我要写书评

暂无评论

Bistable Perception in Conceptor Networks 28th

Bistable Perception in Conceptor Networks

引用

28th International Conference on Artificial Neural Networks (ICANN)

作者： Driehausen, Felix Meyer Zu Busche, Ruediger Leugering, Johannes Pipa, Gordon Osnabruck Univ Inst Cognit Sci Wachsbleiche 27 D-49076 Osnabruck Germany AIM Agile IT Management GmbH Habichtshorststr 1 D-30655 Hannover Germany

ISBN: (纸本)9783030304935;9783030304928

Bistable perception describes the phenomenon of perception alternating between stable states when a subject is presented two incompatible stimuli. Besides intensive research in the last century many open questions remain. As a phenomenon occurring across different perceptual domains, understanding bistable perception can help to reveal properties of information processing in the human brain. It becomes apparent that bistable perception involves multiple distributed processes and several layers in the hierarchy of sensory processing. This observation directs research towards general models of perceptual inference and to the question whether these models can account for the spontaneous subjective changes in percepts that subjects experience when shown rivalling stimuli. We implemented a recurrent generative model based on hierarchical conceptors to investigate its behaviour when fed an ambiguous signal as input. With this model we can show that (1) it is possible to obtain precise predictions about the properties of bistable perception using a general model for perceptual inference, (2) hierarchical processes allow for reduction in prediction error, (3) random switches in the percept of the network are due to noise in the input and (4) dominance times exhibit a gamma distribution of stimulus dominance times compatible with experimental findings in psychophysics. Code for the experiments is available at https://***/felixmzd/Conceptors.

关键词： Bistable perception predictive coding Conceptors

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：