Advances in neural information processing systems最新文献_第9页

Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses. 用于视觉和其他感觉神经假体刺激编码的混合神经自编码器。

Advances in neural information processing systems Pub Date : 2022-12-01

Jacob Granley, Lucas Relic, Michael Beyeler

{"title":"Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses.","authors":"Jacob Granley, Lucas Relic, Michael Beyeler","doi":"","DOIUrl":"","url":null,"abstract":"Sensory neuroprostheses are emerging as a promising technology to restore lost sensory function or augment human capabilities. However, sensations elicited by current devices often appear artificial and distorted. Although current models can predict the neural or perceptual response to an electrical stimulus, an optimal stimulation strategy solves the inverse problem: what is the required stimulus to produce a desired response? Here, we frame this as an end-to-end optimization problem, where a deep neural network stimulus encoder is trained to invert a known and fixed forward model that approximates the underlying biological system. As a proof of concept, we demonstrate the effectiveness of this hybrid neural autoencoder (HNA) in visual neuroprostheses. We find that HNA produces high-fidelity patient-specific stimuli representing handwritten digits and segmented images of everyday objects, and significantly outperforms conventional encoding strategies across all simulated patients. Overall this is an important step towards the long-standing challenge of restoring high-quality vision to people living with incurable blindness and may prove a promising solution for a variety of neuroprosthetic technologies.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"22671-22685"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10504858/pdf/nihms-1928640.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10652408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Harmonizing the object recognition strategies of deep neural networks with humans. 协调深度神经网络与人类的物体识别策略。

Advances in neural information processing systems Pub Date : 2022-12-01

Thomas Fel, Ivan Felipe, Drew Linsley, Thomas Serre

{"title":"Harmonizing the object recognition strategies of deep neural networks with humans.","authors":"Thomas Fel, Ivan Felipe, Drew Linsley, Thomas Serre","doi":"","DOIUrl":"","url":null,"abstract":"The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we explore if these trends have also carried concomitant improvements in explaining the visual strategies humans rely on for object recognition. We do this by comparing two related but distinct properties of visual strategies in humans and DNNs: where they believe important visual features are in images and how they use those features to categorize objects. Across 84 different DNNs trained on ImageNet and three independent datasets measuring the where and the how of human visual strategies for object recognition on those images, we find a systematic trade-off between DNN categorization accuracy and alignment with human visual strategies for object recognition. State-of-the-art DNNs are progressively becoming less aligned with humans as their accuracy improves. We rectify this growing issue with our neural harmonizer: a general-purpose training routine that both aligns DNN and human visual strategies and improves categorization accuracy. Our work represents the first demonstration that the scaling laws [1-3] that are guiding the design of DNNs today have also produced worse models of human vision. We release our code and data at https://serre-lab.github.io/Harmonization to help the field build more human-like DNNs.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"9432-9446"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10353762/pdf/nihms-1856760.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9850565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Amortized Inference for Heterogeneous Reconstruction in Cryo-EM. 低温电子显微镜中异质重建的摊销推理。

Advances in neural information processing systems Pub Date : 2022-12-01

Axel Levy, Gordon Wetzstein, Julien Martel, Frédéric Poitevin, Ellen D Zhong

{"title":"Amortized Inference for Heterogeneous Reconstruction in Cryo-EM.","authors":"Axel Levy, Gordon Wetzstein, Julien Martel, Frédéric Poitevin, Ellen D Zhong","doi":"","DOIUrl":"","url":null,"abstract":"Cryo-electron microscopy (cryo-EM) is an imaging modality that provides unique insights into the dynamics of proteins and other building blocks of life. The algorithmic challenge of jointly estimating the poses, 3D structure, and conformational heterogeneity of a biomolecule from millions of noisy and randomly oriented 2D projections in a computationally efficient manner, however, remains unsolved. Our method, cryoFIRE, performs ab initio heterogeneous reconstruction with unknown poses in an amortized framework, thereby avoiding the computationally expensive step of pose search while enabling the analysis of conformational heterogeneity. Poses and conformation are jointly estimated by an encoder while a physics-based decoder aggregates the images into an implicit neural representation of the conformational space. We show that our method can provide one order of magnitude speedup on datasets containing millions of images without any loss of accuracy. We validate that the joint estimation of poses and conformations can be amortized over the size of the dataset. For the first time, we prove that an amortized method can extract interpretable dynamic information from experimental datasets.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"13038-13049"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10392957/pdf/nihms-1918889.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9928759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning dynamics of deep linear networks with multiple pathways. 多通道深度线性网络的学习动力学

Advances in neural information processing systems Pub Date : 2022-12-01

Jianghong Shi, Eric Shea-Brown, Michael A Buice

{"title":"Learning dynamics of deep linear networks with multiple pathways.","authors":"Jianghong Shi, Eric Shea-Brown, Michael A Buice","doi":"","DOIUrl":"","url":null,"abstract":"Not only have deep networks become standard in machine learning, they are increasingly of interest in neuroscience as models of cortical computation that capture relationships between structural and functional properties. In addition they are a useful target of theoretical research into the properties of network computation. Deep networks typically have a serial or approximately serial organization across layers, and this is often mirrored in models that purport to represent computation in mammalian brains. There are, however, multiple examples of parallel pathways in mammalian brains. In some cases, such as the mouse, the entire visual system appears arranged in a largely parallel, rather than serial fashion. While these pathways may be formed by differing cost functions that drive different computations, here we present a new mathematical analysis of learning dynamics in networks that have parallel computational pathways driven by the same cost function. We use the approximation of deep linear networks with large hidden layer sizes to show that, as the depth of the parallel pathways increases, different features of the training set (defined by the singular values of the input-output correlation) will typically concentrate in one of the pathways. This result is derived analytically and demonstrated with numerical simulation with both linear and non-linear networks. Thus, rather than sharing stimulus and task features across multiple pathways, parallel network architectures learn to produce sharply diversified representations with specialized and specific pathways, a mechanism which may hold important consequences for codes in both biological and artificial systems.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"34064-34076"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10824491/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139576898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality. 高维回归的信息瓶颈理论:相关性、效率和最优性。

Advances in neural information processing systems Pub Date : 2022-12-01

Vudtiwat Ngampruetikorn, David J Schwab

引用次数: 0

Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative. 超图对比学习中的增强:合成与生成。

Advances in neural information processing systems Pub Date : 2022-12-01

Tianxin Wei, Yuning You, Tianlong Chen, Yang Shen, Jingrui He, Zhangyang Wang

{"title":"Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative.","authors":"Tianxin Wei, Yuning You, Tianlong Chen, Yang Shen, Jingrui He, Zhangyang Wang","doi":"","DOIUrl":"","url":null,"abstract":"This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (we refer to it as HyperGCL). We focus on the following question: How to construct contrastive views for hypergraphs via augmentations? We provide the solutions in two folds. First, guided by domain knowledge, we fabricate two schemes to augment hyperedges with higher-order relations encoded, and adopt three vertex augmentation strategies from graph-structured data. Second, in search of more effective views in a data-driven manner, we for the first time propose a hypergraph generative model to generate augmented views, and then an end-to-end differentiable pipeline to jointly learn hypergraph augmentations and model parameters. Our technical innovations are reflected in designing both fabricated and generative augmentations of hypergraphs. The experimental findings include: (i) Among fabricated augmentations in HyperGCL, augmenting hyperedges provides the most numerical gains, implying that higher-order information in structures is usually more downstream-relevant; (ii) Generative augmentations do better in preserving higher-order information to further benefit generalizability; (iii) HyperGCL also boosts robustness and fairness in hypergraph representation learning. Codes are released at https://github.com/weitianxin/HyperGCL.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"1909-1922"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10168651/pdf/nihms-1893780.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9625815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis. 用于纵向一致神经图像分析的局部时空表征学习

Advances in neural information processing systems Pub Date : 2022-12-01

Mengwei Ren, Neel Dey, Martin A Styner, Kelly N Botteron, Guido Gerig

{"title":"Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis.","authors":"Mengwei Ren, Neel Dey, Martin A Styner, Kelly N Botteron, Guido Gerig","doi":"","DOIUrl":"","url":null,"abstract":"Recent self-supervised advances in medical computer vision exploit the global and local anatomical self-similarity for pretraining prior to downstream tasks such as segmentation. However, current methods assume i.i.d. image acquisition, which is invalid in clinical study designs where follow-up longitudinal scans track subject-specific temporal changes. Further, existing self-supervised methods for medically-relevant image-to-image architectures exploit only spatial or temporal self-similarity and do so via a loss applied only at a single image-scale, with naive multi-scale spatiotemporal extensions collapsing to degenerate solutions. To these ends, this paper makes two contributions: (1) It presents a local and multi-scale spatiotemporal representation learning method for image-to-image architectures trained on longitudinal images. It exploits the spatiotemporal self-similarity of learned multi-scale intra-subject image features for pretraining and develops several feature-wise regularizations that avoid degenerate representations; (2) During finetuning, it proposes a surprisingly simple self-supervised segmentation consistency regularization to exploit intra-subject correlation. Benchmarked across various segmentation tasks, the proposed framework outperforms both well-tuned randomly-initialized baselines and current self-supervised techniques designed for both i.i.d. and longitudinal datasets. These improvements are demonstrated across both longitudinal neurodegenerative adult MRI and developing infant brain MRI and yield both higher performance and longitudinal consistency.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"13541-13556"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10445502/pdf/nihms-1922049.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10458647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning low-dimensional generalizable natural features from retina using a U-net. 使用U-net从视网膜学习低维可概括的自然特征。

Advances in neural information processing systems Pub Date : 2022-12-01

Siwei Wang, Benjamin Hoshal, Elizabeth A de Laittre, Olivier Marre, Michael J Berry, Stephanie E Palmer

{"title":"Learning low-dimensional generalizable natural features from retina using a U-net.","authors":"Siwei Wang, Benjamin Hoshal, Elizabeth A de Laittre, Olivier Marre, Michael J Berry, Stephanie E Palmer","doi":"","DOIUrl":"","url":null,"abstract":"Much of sensory neuroscience focuses on presenting stimuli that are chosen by the experimenter because they are parametric and easy to sample and are thought to be behaviorally relevant to the organism. However, it is not generally known what these relevant features are in complex, natural scenes. This work focuses on using the retinal encoding of natural movies to determine the presumably behaviorally-relevant features that the brain represents. It is prohibitive to parameterize a natural movie and its respective retinal encoding fully. We use time within a natural movie as a proxy for the whole suite of features evolving across the scene. We then use a task-agnostic deep architecture, an encoder-decoder, to model the retinal encoding process and characterize its representation of \"time in the natural scene\" in a compressed latent space. In our end-to-end training, an encoder learns a compressed latent representation from a large population of salamander retinal ganglion cells responding to natural movies, while a decoder samples from this compressed latent space to generate the appropriate future movie frame. By comparing latent representations of retinal activity from three movies, we find that the retina has a generalizable encoding for time in the natural scene: the precise, low-dimensional representation of time learned from one movie can be used to represent time in a different movie, with up to 17 ms resolution. We then show that static textures and velocity features of a natural movie are synergistic. The retina simultaneously encodes both to establishes a generalizable, low-dimensional representation of time in the natural scene.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"11355-11368"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10289798/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9719857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Class-Aware Adversarial Transformers for Medical Image Segmentation. 用于医学图像分割的类感知对抗变换器

Advances in neural information processing systems Pub Date : 2022-12-01

Chenyu You, Ruihan Zhao, Fenglin Liu, Siyuan Dong, Sandeep Chinchali, Ufuk Topcu, Lawrence Staib, James S Duncan

{"title":"Class-Aware Adversarial Transformers for Medical Image Segmentation.","authors":"Chenyu You, Ruihan Zhao, Fenglin Liu, Siyuan Dong, Sandeep Chinchali, Ufuk Topcu, Lawrence Staib, James S Duncan","doi":"","DOIUrl":"","url":null,"abstract":"Transformers have made remarkable progress towards modeling long-range dependencies within the medical image analysis domain. However, current transformer-based models suffer from several disadvantages: (1) existing methods fail to capture the important features of the images due to the naive tokenization scheme; (2) the models suffer from information loss because they only consider single-scale feature representations; and (3) the segmentation label maps generated by the models are not accurate enough without considering rich semantic contexts and anatomical textures. In this work, we present CASTformer, a novel type of adversarial transformers, for 2D medical image segmentation. First, we take advantage of the pyramid structure to construct multi-scale representations and handle multi-scale variations. We then design a novel class-aware transformer module to better learn the discriminative regions of objects with semantic structures. Lastly, we utilize an adversarial training strategy that boosts segmentation accuracy and correspondingly allows a transformer-based discriminator to capture high-level semantically correlated contents and low-level anatomical features. Our experiments demonstrate that CASTformer dramatically outperforms previous state-of-the-art transformer-based approaches on three benchmarks, obtaining 2.54%-5.88% absolute improvements in Dice over previous models. Further qualitative experiments provide a more detailed picture of the model's inner workings, shed light on the challenges in improved transparency, and demonstrate that transfer learning can greatly improve performance and reduce the size of medical image datasets in training, making CASTformer a strong starting point for downstream medical image analysis tasks.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"29582-29596"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10395073/pdf/nihms-1912996.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9999038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Harmonizing the object recognition strategies of deep neural networks with humans 将深度神经网络的对象识别策略与人类相协调

Advances in neural information processing systems Pub Date : 2022-11-08 DOI: 10.48550/arXiv.2211.04533

Thomas Fel, Ivan Felipe, Drew A. Linsley, Thomas Serre

{"title":"Harmonizing the object recognition strategies of deep neural networks with humans","authors":"Thomas Fel, Ivan Felipe, Drew A. Linsley, Thomas Serre","doi":"10.48550/arXiv.2211.04533","DOIUrl":"https://doi.org/10.48550/arXiv.2211.04533","url":null,"abstract":"The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we explore if these trends have also carried concomitant improvements in explaining the visual strategies humans rely on for object recognition. We do this by comparing two related but distinct properties of visual strategies in humans and DNNs: where they believe important visual features are in images and how they use those features to categorize objects. Across 84 different DNNs trained on ImageNet and three independent datasets measuring the where and the how of human visual strategies for object recognition on those images, we find a systematic trade-off between DNN categorization accuracy and alignment with human visual strategies for object recognition. State-of-the-art DNNs are progressively becoming less aligned with humans as their accuracy improves. We rectify this growing issue with our neural harmonizer: a general-purpose training routine that both aligns DNN and human visual strategies and improves categorization accuracy. Our work represents the first demonstration that the scaling laws [1-3] that are guiding the design of DNNs today have also produced worse models of human vision. We release our code and data at https://serre-lab.github.io/Harmonization to help the field build more human-like DNNs.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 1","pages":"9432-9446"},"PeriodicalIF":0.0,"publicationDate":"2022-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45022068","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: 26