2019 Conference on Cognitive Computational Neuroscience最新文献_第5页

Humans cannot decipher adversarial images: Revisiting Zhou and Firestone (2019) 人类无法解读敌对图像:重新审视周和费尔斯通(2019)

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1298-0

M. Dujmović, Gaurav Malhotra, J. Bowers

{"title":"Humans cannot decipher adversarial images: Revisiting Zhou and Firestone (2019)","authors":"M. Dujmović, Gaurav Malhotra, J. Bowers","doi":"10.32470/ccn.2019.1298-0","DOIUrl":"https://doi.org/10.32470/ccn.2019.1298-0","url":null,"abstract":"In recent years, deep convolutional neural networks (DCNNs) have shown extraordinary success in object recognition tasks. However, they can also be fooled by adversarial images (stimuli designed to fool networks) that do not appear to fool humans. This has been taken as evidence that these models work quite differently than the human visual system. However, Zhou and Firestone (2019) carried out a study where they presented adversarial images which fool DCNNs to humans and found that, in many cases, humans chose the same label for these images as DCNNs. They take these findings to support the claim that human and machine vision is more similar than commonly claimed. Here we report two experiments that show that the level of agreement between human and DCNN classification is driven by how the experimenter chooses the adversarial images and how they choose the labels given to humans for classification. Based on how one chooses these variables, humans can show a span of agreement levels with DCNNs; from well below to well above levels expected by chance. Overall, our results do not support a view of large systematic overlap between human and computer vision.","PeriodicalId":281121,"journal":{"name":"2019 Conference on Cognitive Computational Neuroscience","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130688477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning about Other Persons’ Character Traits Relies on Combining Reinforcement Learning with Representations of Trait Similarities 学习他人的性格特征依赖于强化学习与特征相似性表征的结合

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1236-0

K. Frolichs, B. Kuper-Smith, J. Gläscher, Gabriela Rosenblau, C. Korn

引用次数: 0

Configural Learning depends on Task Complexity and Temporal Structure 构形学习依赖于任务复杂度和时间结构

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1073-0

Nicholas Menghi, W. Penny

引用次数: 0

Rate-space attractors and low dimensional dynamics interact with spike-synchrony statistics in neural networks 在神经网络中，速率空间吸引子和低维动态与峰值同步统计相互作用

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1422-0

Daniel N. Scott, M. Frank

{"title":"Rate-space attractors and low dimensional dynamics interact with spike-synchrony statistics in neural networks","authors":"Daniel N. Scott, M. Frank","doi":"10.32470/ccn.2019.1422-0","DOIUrl":"https://doi.org/10.32470/ccn.2019.1422-0","url":null,"abstract":"Mechanistic models of cognitive phenomena often make use of neural networks, which allow researchers to examine relationships between neurobiology and the computations suspected to underlie cognition. These models typically make use of neural firing rates, as do analyses of in-vivo data, with the dimension of neural dynamics receiving special attention. Treating time-binned spiking activity as a sequence of binary vectors (spike-words) should prove complementary to rate-space analyses, and has been shown to provide links with statistical physics. We investigate the interaction between these two analyses using theory and simulations to show how signatures of rate-dynamics are found in spike-word distributions. We find that a global integration over the eigenvalues of linear dynamics local to attracting subspaces can modify spike-synchrony, and we quantify how this impacts informational and thermodynamic properties of these systems. The research outlined here will have implications for the interpretation of neural data, the use of population codes for tasks such as Bayesian inference, and for various resource rational models attempting to bridge the gap between computation and implementation.","PeriodicalId":281121,"journal":{"name":"2019 Conference on Cognitive Computational Neuroscience","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133581361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advantages of heterogeneity of parameters in spiking neural network training 参数异质性在脉冲神经网络训练中的优势

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1173-0

Nicolas Perez-Nieves, Vincent C. H. Leung, P. Dragotti, Dan F. M. Goodman

{"title":"Advantages of heterogeneity of parameters in spiking neural network training","authors":"Nicolas Perez-Nieves, Vincent C. H. Leung, P. Dragotti, Dan F. M. Goodman","doi":"10.32470/ccn.2019.1173-0","DOIUrl":"https://doi.org/10.32470/ccn.2019.1173-0","url":null,"abstract":"It is very common in studies of the learning capabilities of spiking neural networks (SNNs) to use homogeneous neural and synaptic parameters (time constants, thresholds, etc.). Even in studies in which these parameters are distributed heterogeneously, the advantages or disadvantages of the heterogeneity have rarely been studied in depth. By contrast, in the brain, neurons and synapses are highly diverse, leading naturally to the hypothesis that this heterogeneity may be advantageous for learning. Starting from two state-of-the-art methods for training spiking neural networks (Nicola & Clopath, 2017; Shrestha & Orchard, 2018), we found that adding parameter heterogeneity reduced errors when the network had to learn more complex patterns, increased robustness to hyperparameter mistuning, and reduced the number of training iterations required. We propose that neural heterogeneity may be an important principle for brains to learn robustly in real world environments with highly complex structure, and where task-specific hyperparameter tuning may be impossible. Consequently, heterogeneity may also be a good candidate design principle for artificial neural networks, to reduce the need for expensive hyperparameter tuning as well as for reducing training time.","PeriodicalId":281121,"journal":{"name":"2019 Conference on Cognitive Computational Neuroscience","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133123675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Implicit Scene Segmentation in Deeper Convolutional Neural Networks 基于深度卷积神经网络的隐式场景分割

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1149-0

N. Seijdel, Nikos Tsakmakidis, E. Haan, S. Bohté, S. Scholte

{"title":"Implicit Scene Segmentation in Deeper Convolutional Neural Networks","authors":"N. Seijdel, Nikos Tsakmakidis, E. Haan, S. Bohté, S. Scholte","doi":"10.32470/ccn.2019.1149-0","DOIUrl":"https://doi.org/10.32470/ccn.2019.1149-0","url":null,"abstract":"Feedforward deep convolutional neural networks (DCNNs) are matching and even surpassing human performance on object recognition. This performance suggests that activation of a loose collection of image features could support the recognition of natural object categories, without dedicated systems to solve specific visual subtasks. Recent findings in humans however, suggest that while feedforward activity may suffice for sparse scenes with isolated objects, additional visual operations ('routines') that aid the recognition process (e.g. segmentation or grouping) are needed for more complex scenes. Linking human visual processing to performance of DCNNs with increasing depth, we here explored if, how, and when object information is differentiated from the backgrounds they appear on. To this end, we controlled the information in both objects and backgrounds, as well as the relationship between them by adding noise, manipulating background congruence and systematically occluding parts of the image. Results indicated less distinction between objectand background features for more shallow networks. For those networks, we observed a benefit of training on segmented objects (as compared to unsegmented objects). Overall, deeper networks trained on natural (unsegmented) scenes seem to perform implicit 'segmentation' of the objects from their background, possibly by improved selection of relevant features.","PeriodicalId":281121,"journal":{"name":"2019 Conference on Cognitive Computational Neuroscience","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133233126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A particle filtering account of selective attention during learning 学习过程中选择性注意的粒子过滤

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1338-0

Angela Radulescu, Y. Niv, N. Daw

引用次数: 8

Neural signatures of coping with multiple tasks in mouse visual cortex 小鼠视觉皮层应对多重任务的神经特征

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1293-0

M. Hajnal, Duy T. Tran, Michael C. Einstein, Gergő Orbán, P. Golshani, Pierre-Olivier Polack

引用次数: 0

Category-selectivity together with a Normalization Model Predicts the Response to Multi-category Stimuli along the Category-Selective Cortex 类别选择性与标准化模型一起预测沿类别选择皮层对多类别刺激的反应

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1196-0

Libi Kliger, G. Yovel

{"title":"Category-selectivity together with a Normalization Model Predicts the Response to Multi-category Stimuli along the Category-Selective Cortex","authors":"Libi Kliger, G. Yovel","doi":"10.32470/ccn.2019.1196-0","DOIUrl":"https://doi.org/10.32470/ccn.2019.1196-0","url":null,"abstract":"According to the normalization framework the neural response of a single neuron to multiple stimuli is normalized by the response of its surrounding neurons. High-level visual cortex is composed of clusters of neurons that are selective to the same category. In an fMRI study, we show that the normalization model, together with the profile of category-selectivity of a given cortical area, can predict its response to multi-category stimuli. We measured the response to a face and a body (or a face and an object) presented alone or simultaneously and estimated the contribution of each category to the multicategory representation by fitting a linear model. Results show that the response to multi-category stimuli is a weighted mean of the response to each of its components. The coefficients were correlated with the selectivity profile of the cortical region. These findings suggest that the functional organization of category-selective cortex, i.e., neighboring patches of neurons, each selective to a single category, bias the response to certain categories, for which such clusters of neurons exist, and give them priority in the representation of cluttered visual scenes.","PeriodicalId":281121,"journal":{"name":"2019 Conference on Cognitive Computational Neuroscience","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115724239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Unreliable Influence of Noise Normalization on the Reliability of Neural Dissimilarity 噪声归一化对神经相似性可靠性的不可靠影响

2019 Conference on Cognitive Computational Neuroscience Pub Date : 1900-01-01 DOI: 10.32470/ccn.2019.1150-0

J. Ritchie, Haemy Lee Masson, Stefania Bracci, H. O. D. Beeck

引用次数: 0