乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:35:47Z","timestamp":1740184547344,"version":"3.37.3"},"reference-count":55,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T00:00:00Z","timestamp":1724112000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T00:00:00Z","timestamp":1724112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"AgileNeuRobot","award":["ANR-20-CE23-0021"]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"Abstract<\/jats:title>\n Both biological and artificial neural networks inherently balance their performance with their operational cost, which characterizes their computational abilities. Typically, an efficient neuromorphic neural network is one that learns representations that reduce the redundancies and dimensionality of its input. For instance, in the case of sparse coding (SC), sparse representations derived from natural images yield representations that are heterogeneous, both in their sampling of input features and in the variance of those features. Here, we focused on this notion, and sought correlations between natural images\u2019 structure, particularly oriented features, and their corresponding sparse codes. We show that representations of input features scattered across multiple levels of variance substantially improve the sparseness and resilience of sparse codes, at the cost of reconstruction performance. This echoes the structure of the model\u2019s input, allowing to account for the heterogeneously aleatoric structures of natural images. We demonstrate that learning kernel from natural images produces heterogeneity by balancing between approximate and dense representations, which improves all reconstruction metrics. Using a parametrized control of the kernels\u2019 heterogeneity of a convolutional SC algorithm, we show that heterogeneity emphasizes sparseness, while homogeneity improves representation granularity. In a broader context, this encoding strategy can serve as inputs to deep convolutional neural networks. We prove that such variance-encoded sparse image datasets enhance computational efficiency, emphasizing the benefits of kernel heterogeneity to leverage naturalistic and variant input structures and possible applications to improve the throughput of neuromorphic hardware.<\/jats:p>","DOI":"10.1088\/2634-4386\/ad5d0f","type":"journal-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T08:39:30Z","timestamp":1724143170000},"page":"034008","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Kernel heterogeneity improves sparseness of natural images representations"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7999-3751","authenticated-orcid":true,"given":"Hugo J","family":"Ladret","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1494-8391","authenticated-orcid":false,"given":"Christian","family":"Casanova","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9536-010X","authenticated-orcid":true,"given":"Laurent","family":"Udo Perrinet","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,8,20]]},"reference":[{"key":"ncead5d0fbib1","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1146\/annurev.neuro.24.1.1193","article-title":"Natural image statistics and neural representation","volume":"24","author":"Simoncelli","year":"2001","journal-title":"Annu. Rev. Neurosci."},{"key":"ncead5d0fbib2","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/381607a0","article-title":"Emergence of simple-cell receptive field properties by learning a sparse code for natural images","volume":"381","author":"Olshausen","year":"1996","journal-title":"Nature"},{"key":"ncead5d0fbib3","doi-asserted-by":"publisher","first-page":"3311","DOI":"10.1016\/S0042-6989(97)00169-7","article-title":"Sparse coding with an overcomplete basis set: a strategy employed by v1?","volume":"37","author":"Olshausen","year":"1997","journal-title":"Vis. Res."},{"key":"ncead5d0fbib4","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1515\/znc-1981-9-1040","article-title":"A simple coding procedure enhances a neuron\u2019s information capacity","volume":"36","author":"Laughlin","year":"1981","journal-title":"Z. Naturforschung C"},{"key":"ncead5d0fbib5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008629","article-title":"Sparse deep predictive coding captures contour integration capabilities of the early visual system","volume":"17","author":"Boutin","year":"2020","journal-title":"PLoS Comput. Biol."},{"key":"ncead5d0fbib6","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10994-021-05946-3","article-title":"Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods","volume":"110","author":"H\u00fcllermeier","year":"2021","journal-title":"Mach. Learn."},{"key":"ncead5d0fbib7","first-page":"pp 4840","article-title":"Robot audition based acoustic event identification using a bayesian model considering spectral and temporal uncertainties","author":"Nakamura","year":"2015"},{"key":"ncead5d0fbib8","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1007\/s00221-009-2101-1","article-title":"Integration of haptic and visual size cues in perception and action revealed through cross-modal conflict","volume":"201","author":"Pettypiece","year":"2010","journal-title":"Exp. Brain Res."},{"key":"ncead5d0fbib9","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1088\/0954-898X_5_4_006","article-title":"The statistics of natural images","volume":"5","author":"Ruderman","year":"1994","journal-title":"Netw., Comput. Neural Syst."},{"key":"ncead5d0fbib10","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1137\/S0036141000371150","article-title":"Are natural images of bounded variation?","volume":"33","author":"Gousseau","year":"2001","journal-title":"SIAM J. Math. Anal."},{"key":"ncead5d0fbib11","doi-asserted-by":"publisher","first-page":"754","DOI":"10.3389\/fnins.2019.00754","article-title":"Sparse coding using the locally competitive algorithm on the truenorth neurosynaptic system","volume":"13","author":"Fair","year":"2019","journal-title":"Front. Neurosci."},{"article-title":"Treatise on Physiological Optics","year":"1867","author":"Helmholtz","key":"ncead5d0fbib12"},{"key":"ncead5d0fbib13","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1098\/rstb.2005.1622","article-title":"A theory of cortical responses","volume":"360","author":"Friston","year":"2005","journal-title":"Phil. Trans. R. Soc. B"},{"key":"ncead5d0fbib14","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1016\/j.neuron.2016.09.038","article-title":"Neural variability and sampling-based probabilistic representations in the visual cortex","volume":"92","author":"Orb\u00e1n","year":"2016","journal-title":"Neuron"},{"key":"ncead5d0fbib15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-020-15533-0","article-title":"Representation of visual uncertainty through neural gain variability","volume":"11","author":"H\u00e9naff","year":"2020","journal-title":"Nat. Commun."},{"key":"ncead5d0fbib16","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1038\/s42003-023-05042-3","article-title":"Cortical recurrence supports resilience to sensory variance in the primary visual cortex","volume":"6","author":"Ladret","year":"2023","journal-title":"Commun. Biol."},{"key":"ncead5d0fbib17","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1016\/j.neuron.2015.10.009","article-title":"Origin and function of tuning diversity in macaque visual cortex","volume":"88","author":"Goris","year":"2015","journal-title":"Neuron"},{"key":"ncead5d0fbib18","article-title":"Efficient sparse coding algorithms","volume":"vol 19","author":"Lee","year":"2006","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ncead5d0fbib19","first-page":"pp 319","article-title":"Sparse Models for Computer Vision","author":"Perrinet","year":"2015"},{"key":"ncead5d0fbib20","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1137\/S003614450037906X","article-title":"Atomic decomposition by basis pursuit","volume":"43","author":"Chen","year":"2001","journal-title":"SIAM Rev."},{"key":"ncead5d0fbib21","article-title":"Coding time-varying signals using sparse, shift-invariant representations","volume":"vol 11","author":"Lewicki","year":"1998","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ncead5d0fbib22","doi-asserted-by":"publisher","first-page":"6424","DOI":"10.1073\/pnas.0700622104","article-title":"A feedforward architecture accounts for rapid categorization","volume":"104","author":"Serre","year":"2007","journal-title":"Proc. Natl Acad. Sci."},{"key":"ncead5d0fbib23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1010270","article-title":"Pooling strategies in V1 can account for the functional and structural diversity across species","volume":"18","author":"Boutin","year":"2022","journal-title":"PLOS Comput. Biol."},{"key":"ncead5d0fbib24","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/TIP.2015.2495260","article-title":"Efficient algorithms for convolutional sparse representations","volume":"25","author":"Wohlberg","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ncead5d0fbib25","first-page":"pp 1","article-title":"Sporco: a python package for standard and convolutional sparse representations","author":"Wohlberg","year":"2017"},{"key":"ncead5d0fbib26","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/s10915-018-0757-z","article-title":"Global convergence of admm in nonconvex nonsmooth optimization","volume":"78","author":"Wang","year":"2019","journal-title":"J. Sci. Comput."},{"key":"ncead5d0fbib27","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1113\/jphysiol.1962.sp006837","article-title":"Receptive fields, binocular interaction and functional architecture in the cat\u2019s visual cortex","volume":"160","author":"Hubel","year":"1962","journal-title":"J. Physiol."},{"key":"ncead5d0fbib28","first-page":"1","article-title":"Sparse approximation of images inspired from the functional architecture of the primary visual areas","volume":"2007","author":"Fischer","year":"2007","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ncead5d0fbib29","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s11263-006-0026-8","article-title":"Self-invertible 2d log-gabor wavelets","volume":"75","author":"Fischer","year":"2007","journal-title":"Int. J. Comput. Vis."},{"key":"ncead5d0fbib30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2007\/90727","article-title":"Sparse Approximation of Images Inspired from the Functional Architecture of the Primary Visual Areas","volume":"2007","author":"Fischer","year":"2006","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ncead5d0fbib31","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s004220050411","article-title":"Orientation tuning curves: empirical description and estimation of parameters","volume":"78","author":"Swindale","year":"1998","journal-title":"Biol. Cybern."},{"key":"ncead5d0fbib32","doi-asserted-by":"publisher","first-page":"e453","DOI":"10.7717\/peerj.453","article-title":"scikit-image: image processing in python","volume":"2","author":"Van der Walt","year":"2014","journal-title":"PeerJ"},{"article-title":"Hd natural images database for sparse coding FigShare","year":"2023","author":"Ladret","key":"ncead5d0fbib33"},{"article-title":"Adam: a method for stochastic optimization","year":"2014","author":"Kingma","key":"ncead5d0fbib34"},{"key":"ncead5d0fbib35","first-page":"pp 770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ncead5d0fbib36","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1037\/h0033117","article-title":"Perception and discrimination as a function of stimulus orientation: the \u2018oblique effect\u2019 in man and animals","volume":"78","author":"Appelle","year":"1972","journal-title":"Psychol. Bull."},{"key":"ncead5d0fbib37","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1364\/josaa.4.002379","article-title":"Relations between the statistics of natural images and the response properties of cortical cells","volume":"4","author":"Field","year":"1987","journal-title":"J. Opt. Soc. Am. A"},{"key":"ncead5d0fbib38","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1038\/s41586-019-1346-5","article-title":"High-dimensional geometry of population responses in visual cortex","volume":"571","author":"Stringer","year":"2019","journal-title":"Nature"},{"key":"ncead5d0fbib39","doi-asserted-by":"publisher","first-page":"4002","DOI":"10.1073\/pnas.95.7.4002","article-title":"The distribution of oriented contours in the real world","volume":"95","author":"Coppola","year":"1998"},{"key":"ncead5d0fbib40","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1167\/4.12.5","article-title":"A horizontal bias in human visual processing of orientation and its correspondence to the structural components of natural scenes","volume":"4","author":"Hansen","year":"2004","journal-title":"J. Vis."},{"key":"ncead5d0fbib41","first-page":"pp 309","article-title":"Full reference video quality assessment metric on base human visual system consistent with psnr","author":"Mozhaeva","year":"2021"},{"key":"ncead5d0fbib42","doi-asserted-by":"publisher","DOI":"10.1101\/407007","article-title":"Brain-score: which artificial neural network for object recognition is most brain-like?","author":"Schrimpf","year":"2020"},{"key":"ncead5d0fbib43","doi-asserted-by":"publisher","first-page":"5791","DOI":"10.1038\/s41467-021-26022-3","article-title":"Neural heterogeneity promotes robust learning","volume":"12","author":"Perez-Nieves","year":"2021","journal-title":"Nat. Commun."},{"key":"ncead5d0fbib44","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-96745-2","article-title":"Optimal responsiveness and information flow in networks of heterogeneous neurons","volume":"11","author":"Di Volo","year":"2021","journal-title":"Sci. Rep."},{"key":"ncead5d0fbib45","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1162\/neco.2008.03-07-486","article-title":"Sparse coding via thresholding and local competition in neural circuits","volume":"20","author":"Rozell","year":"2008","journal-title":"Neural Comput."},{"key":"ncead5d0fbib46","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/S0893-6080(05)80006-1","article-title":"A cortical model of winner-take-all competition via lateral inhibition","volume":"5","author":"Coultrip","year":"1992","journal-title":"Neural Netw."},{"key":"ncead5d0fbib47","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.1162\/neco_a_01325","article-title":"Effect of top-down connections in hierarchical sparse coding","volume":"32","author":"Boutin","year":"2020","journal-title":"Neural Comput."},{"key":"ncead5d0fbib48","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MNANO.2022.3141443","article-title":"Memristor-based binarized spiking neural networks: challenges and applications","volume":"16","author":"Eshraghian","year":"2022","journal-title":"IEEE Nanotechnol. Mag."},{"key":"ncead5d0fbib49","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.201900189","article-title":"Complementary metal-oxide semiconductor and memristive hardware for neuromorphic computing","volume":"2","author":"Rahimi Azghadi","year":"2020","journal-title":"Adv. Intell. Syst."},{"article-title":"An image is worth 16\u00d716 words: transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ncead5d0fbib50"},{"key":"ncead5d0fbib51","first-page":"pp 124","article-title":"Sparse coding: a deep learning using unlabeled data for high-level representation","author":"Vidya","year":"2014"},{"key":"ncead5d0fbib52","first-page":"pp 902","article-title":"Unsupervised feature learning by deep sparse coding","author":"He","year":"2014"},{"key":"ncead5d0fbib53","first-page":"pp 594","article-title":"Deep neural network for face recognition based on sparse autoencoder","author":"Zhang","year":"2015"},{"key":"ncead5d0fbib54","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1167\/jov.20.12.10","article-title":"Selectivity and robustness of sparse coding networks","volume":"20","author":"Paiton","year":"2020","journal-title":"J. Vis."},{"key":"ncead5d0fbib55","first-page":"pp 7173","article-title":"Efficient convolutional sparse coding","author":"Wohlberg","year":"2014"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad5d0f","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad5d0f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad5d0f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad5d0f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T08:39:38Z","timestamp":1724143178000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad5d0f"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,20]]},"references-count":55,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,8,20]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ad5d0f","relation":{},"ISSN":["2634-4386"],"issn-type":[{"type":"electronic","value":"2634-4386"}],"subject":[],"published":{"date-parts":[[2024,8,20]]},"assertion":[{"value":"Kernel heterogeneity improves sparseness of natural images representations","name":"article_title","label":"Article Title"},{"value":"Neuromorphic Computing and Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-12-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-06-28","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-20","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}