检索结果-内蒙古大学图书馆

Are spatial chromatic contrast sensitivity band-pass or lowpass functions? 28

学校读者我要写书评

暂无评论

Are spatial chromatic contrast sensitivity band-pass or lowp...

28th Color and Imaging Conference 2020, CIC 2020

作者： Xu, Qiang Westland, Stephen Lucassen, Marcel Sekulovski, Dragan Wuerger, Sophie Mantiuk, Rafal Luo, Ming Ronnier State Key Laboratory of Modern Optical Instrumentation Zhejiang University Hangzhou China School of Design University of Leeds Leeds United Kingdom Philips Lighting Research Eindhoven Netherlands Cognitive and Clinical Neuroscience Group University of Liverpool Liverpool United Kingdom Dept. of Computer Science and Technology University of Cambridge Cambrige United Kingdom School of Design Leeds University Leeds United Kingdom

ISBN: (纸本)9781713826972

The goal of this research is to generate high quality chromatic Contrast Sensitivity Function (CSF) over a wide range of spatial frequencies from 0.06 to 3.84 cycles per degree (cpd) surrounding 5 CIE proposed colour centres (white, red, yellow, green and blue) to study colour difference. At each centre, 6 colour directions at each of 7 frequencies were sampled, from 0.06 to 3.84 cycles per degree (cpd) corresponding to the number of cycles: From 2.3 to 144.4 respectively. A threshold method based on forced-choice stair-case was adopted to investigate the just noticeable (threshold) colour difference. The results revealed that the chromatic CSF under the present experimental conditions having many lower spatial frequencies covering five colour centres to be band pass, whereas previous results indicated it was low pass. However, this could be caused by the present experimental conditions such as fixed-size stimuli and constant luminance. The new chromatic CSF for R-G and Y-B channels were also developed © 2020 Society for Imaging science and Technology.

关键词： Color

Integration of Machine-Learned Force Fields for Phonon DOS in Nanoscale Heterostructures

学校读者我要写书评

暂无评论

Microscopy and Microanalysis 2024年第SUPPLEMENT_1期30卷

作者： Walker, Harrison A Hoglund, Eric R Bao, De-Liang Kamal Hussain, Md Ni, Haoyang Mamun, Abdullah Baxter, Jefferey Khan, Asif Caldwell, Joshua D Hopkins, Patrick E Hachtel, Jordan A Pantelides, Sokrates T Dept. of Physics and Astronomy Vanderbilt Univ. Nashville TN United States Interdisciplinary Materials Science Program Vanderbilt Univ. Nashville TN United States Center for Nanophase Materials Sciences Oak Ridge National Laboratory Oak Ridge TN United States Dept. of Materials Science and Engineering Univ. of Virginia Charlottesville VA United States Dept. of Electrical Engineering Univ. of South Carolina Columbia SC United States Dept. of Materials Science and Engineering Univ. of Illinois at Urbana-Champaign Urbana IL United States Materials Research Laboratory Univ. of Illinois at Urbana-Champaign Urbana IL United States Dept. of Mechanical Engineering Vanderbilt Univ. Nashville TN United States Dept. of Mechanical and Aerospace Engineering Univ. of Virginia Charlottesville VA United States Dept. of Physics Univ. of Virginia Charlottesville VA United States Dept. of Electrical and Computer Engineering Vanderbilt Univ. Nashville TN United States

Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules 22

学校读者我要写书评

暂无评论

Beyond accuracy: generalization properties of bio-plausible ...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Yuhan Helena Liu Arna Ghosh Blake A. Richards Eric Shea-Brown Guillaume Lajoie Department of Applied Mathematics University of Washington Seattle WA and Allen Institute for Brain Science Seattle WA and Computational Neuroscience Center University of Washington Seattle WA School of Computer Science McGill University Montreal QC Canada and Mila - Quebec AI Institute Montreal QC Canada School of Computer Science McGill University Montreal QC Canada and Mila - Quebec AI Institute Montreal QC Canada and Department of Neurology and Neurosurgery Montreal Neurological Institute McGill University Montreal QC Canada and Canada CIFAR AI Chair CIFAR Toronto ON Canada Mila - Quebec AI Institute Montreal QC Canada and Canada CIFAR AI Chair CIFAR Toronto ON Canada and Dept. de Mathématiques et Statistiques Université de Montréal Montreal QC Canada

ISBN: (纸本)9781713871088

To unveil how the brain learns, ongoing work seeks biologically-plausible approximations of gradient descent algorithms for training recurrent neural networks (RNNs). Yet, beyond task accuracy, it is unclear if such learning rules converge to solutions that exhibit different levels of generalization than their non-biologically-plausible counterparts. Leveraging results from deep learning theory based on loss landscape curvature, we ask: how do biologically-plausible gradient approximations affect generalization? We first demonstrate that state-of-the-art biologically-plausible learning rules for training RNNs exhibit worse and more variable generalization performance compared to their machine learning counterparts that follow the true gradient more closely. Next, we verify that such generalization performance is correlated significantly with loss landscape curvature, and we show that biologically-plausible learning rules tend to approach high-curvature regions in synaptic weight space. Using tools from dynamical systems, we derive theoretical arguments and present a theorem explaining this phenomenon. This predicts our numerical results, and explains why biologically-plausible rules lead to worse and more variable generalization properties. Finally, we suggest potential remedies that could be used by the brain to mitigate this effect. To our knowledge, our analysis is the first to identify the reason for this generalization gap between artificial and biologically-plausible learning rules, which can help guide future investigations into how the brain learns solutions that generalize.

关键词：

Tensor-based grading: A novel patch-based grading approach for the analysis of deformation fields in huntington's disease

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hett, Kilian Johnson, Hans Coupé, Pierrick Paulsen, Jane S. Long, Jeffrey D. Oguz, Ipek Vanderbilt University Dept. of Electrical Engineering and Computer Science NashvilleTN United States University of Iowa Dept. of Electrical and Computer Engineering Iowa CityIA United States CNRS University of Bordeaux Bordeaux INP LABRI UMR5800 PICTURA France University of Iowa Dept. of Neuroscience Iowa CityIA United States University of Iowa Dept. of Psychiatry Iowa CityIA United States University of Iowa Dept. of Biostatitsics Iowa CityIA United States

The improvements in magnetic resonance imaging have led to the development of numerous techniques to better detect structural alterations caused by neurodegenerative diseases. Among these, the patch-based grading framework has been proposed to model local patterns of anatomical changes. This approach is attractive because of its low computational cost and its competitive performance. Other studies have proposed to analyze the deformations of brain structures using tensorbased morphometry, which is a highly interpretable approach. In this work, we propose to combine the advantages of these two approaches by extending the patch-based grading framework with a new tensor-based grading method that enables us to model patterns of local deformation using a log-Euclidean metric. We evaluate our new method in a study of the putamen for the classification of patients with pre-manifest Huntington's disease and healthy controls. Our experiments show a substantial increase in classification accuracy (87:5 ± 0:5 vs. 81:3 ± 0:6) compared to the existing patch-based grading methods, and a good complement to putamen volume, which is a primary imaging-based marker for the study of Huntington's disease. Copyright © 2020, The Authors. All rights reserved.

关键词： Neurodegenerative diseases

Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Yuhan Helena Ghosh, Arna Richards, Blake A. Shea-Brown, Eric Lajoie, Guillaume Department of Applied Mathematics University of Washington SeattleWA United States Allen Institute for Brain Science 615 Westlake Ave N SeattleWA United States Computational Neuroscience Center University of Washington SeattleWA United States School of Computer Science McGill University MontrealQC Canada Mila - Quebec AI Institute MontrealQC Canada Department of Neurology and Neurosurgery Montreal Neurological Institute McGill University MontrealQC Canada Canada CIFAR AI Chair CIFAR TorontoON Canada Dept. de Mathématiques et Statistiques Université de Montréal MontrealQC Canada

关键词： Recurrent neural networks

Psychoacoustic calibration of loss functions for efficient end-to-end neural audio coding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhen, Kai Lee, Mi Suk Sung, Jongmo Beack, Seungkwon Kim, Minje Department of Computer Science and Cognitive Science Program Indiana University BloomingtonIN47408 United States Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Dept. of Intelligent Systems Engineering Indiana University United States

Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals. For neural audio codecs, however, the objective nature of the loss function usually leads to suboptimal sound quality as well as high run-time complexity due to the large model size. In this work, we present a psychoacoustic calibration scheme to re-define the loss functions of neural audio coding systems so that it can decode signals more perceptually similar to the reference, yet with a much lower model complexity. The proposed loss function incorporates the global masking threshold, allowing the reconstruction error that corresponds to inaudible artifacts. Experimental results show that the proposed model outperforms the baseline neural codec twice as large and consuming 23.4% more bits per second. With the proposed method, a lightweight neural codec, with only 0.9 million parameters, performs near-transparent audio coding comparable with the commercial MPEG-1 Audio Layer III codec at 112 kbps. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Unsupervised learning by a "softened" correlation game: duality and convergence

学校读者我要写书评

暂无评论

Unsupervised learning by a "softened" correlation game: dual...

Asilomar Conference on Signals, Systems & computers

作者： Kyle L. Luther Runzhe Yang H. Sebastian Seung Dept. of Physics Princeton University USA Dept. of Computer Science Princeton University USA Neuroscience Institute Princeton University USA

ISBN: (数字)9781728143002

ISBN: (纸本)9781728143019

Neural networks with Hebbian excitation and anti-Hebbian inhibition form an interesting class of biologically plausible unsupervised learning algorithms. It has recently been shown that such networks can be regarded as online gradient descent-ascent algorithms for solving min-max problems that are dual to unsupervised learning principles formulated with no explicit reference to neural networks. Here we generalize one such formulation, the correlation game, by replacing a hard constraint with a soft penalty function. Our "softened" correlation game contains the nonnegative similarity matching principle as a special case. For solving the primal problem, we derive a projected gradient ascent algorithm that achieves speed through sorting. For solving the dual problem, we derive a projected gradient descent-ascent algorithm, the stochastic online variant of which can be interpreted as a neural network algorithm. We prove strong duality when the inhibitory connection matrix is positive definite, a condition that also prohibits multistability of neural activity dynamics. We show empirically that the neural net algorithm can converge when inhibitory plasticity is faster than excitatory plasticity, and may fail to converge in the opposing case. This is intuitively interpreted using the structure of the min-max problem.

关键词： Correlation Games Unsupervised learning Transforms Optimization Convergence Neural networks

Comparison performance of decision tree classification model for spam filtering with or without the recursive feature elimination (RFE) approach 4

学校读者我要写书评

暂无评论

Comparison performance of decision tree classification model...

4th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2019

作者： Zulfikar, Ahmad Fikri Supriyadi, Dede Heryadi, Yaya Lukas University of Pamulang Faculty of Technique Program Study of Informatics South Tangerang Indonesia STMIK Eresha Program Study of Informatics South Tangerang Indonesia Bina Nusantara University Dept. of Computer Science West-Jakarta Indonesia Faculty of Enginnering Jakarta 12930 Indonesia

ISBN: (纸本)9781728151182

Spam filters have become an important tool for ISP(Internet service Provider) to address the growing spam in cyberspace. Spam filtering is a program used to detect spam, prevent it and enter users' mailboxes. With the rapid growth of Internet technology, email communication is becoming increasingly important in people's daily lives. In addition, the amount of spam contained in emails has increased considerably in recent years. In this study, the authors will compare the performance of the decision tree classification models using or not using Recursive Feature Elimination (RFE) in spam filtering. The results of this test will be compared with the results of level accuracy, recall, precision, and F1 Score using or not using the RFE method. where in the results of this level measurement, the model used can be a reference or solution to filter spam correctly, especially through the use of supervised learning data. © 2019 IEEE.

关键词： Decision trees

The neuroconnectionist research programme

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Doerig, A. Sommers, R. Seeliger, K. Richards, B. Ismael, J. Lindsay, G. Kording, K. Konkle, T. van Gerven, M.A.J. Kriegeskorte, N. Kietzmann, T.C. Donders Institute for Brain Cognition & Behaviour Nijmegen Netherlands Institute of Cognitive Science University of Osnabrück Germany Max Planck Institute for Psycholinguistics Department of Neurobiology of Language Nijmegen Netherlands Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Dept. of Neurology and Neurosurgery McGill University MontréalQC Canada School of Computer Science McGill University MontréalQC Canada Mila MontréalQC Canada Montréal Neurological Institute MontréalQC Canada Learning in Machines and Brains Program CIFAR TorontoON Canada Columbia University New York United States New York University New York United States Bioengineering Neuroscience University of Pennsylvania Pennsylvania PA United States Harvard University CambridgeMA United States Zuckerman Institute Columbia University New York United States

Artificial Neural Networks (ANNs) inspired by biology are beginning to be widely used to model behavioral and neural data, an approach we call neuroconnectionism. ANNs have been lauded as the current best models of information processing in the brain, but also criticized for failing to account for basic cognitive functions. We propose that arguing about the successes and failures of a restricted set of current ANNs is the wrong approach to assess the promise of neuroconnectionism. Instead, we take inspiration from the philosophy of science, and in particular from Lakatos, who showed that the core of scientific research programmes is often not directly falsifiable, but should be assessed by its capacity to generate novel insights. Following this view, we present neuroconnectionism as a cohesive large-scale research programme centered around ANNs as a computational language for expressing falsifiable theories about brain computation. We describe the core of the programme, the underlying computational framework and its tools for testing specific neuroscientific hypotheses. Taking a longitudinal view, we review past and present neuroconnectionist projects and their responses to challenges, and argue that the research programme is highly progressive, generating new and otherwise unreachable insights into the workings of the brain. © 2022, CC BY.

关键词： Neural networks