Advances in neural information processing systems最新文献_第7页

Neural Information Processing: 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part VI 神经信息处理:第29届国际会议，ICONIP 2022，虚拟事件，11月22日至26日，2022，会议录，第六部分

Advances in neural information processing systems Pub Date : 2023-01-01 DOI: 10.1007/978-981-99-1645-0

引用次数: 0

Neural Information Processing: 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part I 神经信息处理:第29届国际会议，ICONIP 2022，虚拟事件，11月22日至26日，2022，会议录，第一部分

Advances in neural information processing systems Pub Date : 2023-01-01 DOI: 10.1007/978-3-031-30105-6

引用次数: 0

Directed Cyclic Graph for Causal Discovery from Multivariate Functional Data. 多元函数数据因果发现的有向循环图。

Advances in neural information processing systems Pub Date : 2023-01-01 Epub Date: 2024-05-30

Saptarshi Roy, Raymond K W Wong, Yang Ni

引用次数: 0

Sequential Memory with Temporal Predictive Coding. 使用时序预测编码的顺序存储器

Advances in neural information processing systems Pub Date : 2023-01-01

Mufeng Tang, Helen Barron, Rafal Bogacz

{"title":"Sequential Memory with Temporal Predictive Coding.","authors":"Mufeng Tang, Helen Barron, Rafal Bogacz","doi":"","DOIUrl":"","url":null,"abstract":"Forming accurate memory of sequential stimuli is a fundamental function of biological agents. However, the computational mechanism underlying sequential memory in the brain remains unclear. Inspired by neuroscience theories and recent successes in applying predictive coding (PC) to static memory tasks, in this work we propose a novel PC-based model for sequential memory, called temporal predictive coding (tPC). We show that our tPC models can memorize and retrieve sequential inputs accurately with a biologically plausible neural implementation. Importantly, our analytical study reveals that tPC can be viewed as a classical Asymmetric Hopfield Network (AHN) with an implicit statistical whitening process, which leads to more stable performance in sequential memory tasks of structured inputs. Moreover, we find that tPC exhibits properties consistent with behavioral observations and theories in neuroscience, thereby strengthening its biological relevance. Our work establishes a possible computational mechanism underlying sequential memory in the brain that can also be theoretically interpreted using existing memory model frameworks.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"36 ","pages":"44341-44355"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7615819/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140874998","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

Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes. 绕过尖峰排序：基于密度的解码使用密集多电极探针的尖峰定位。

Advances in neural information processing systems Pub Date : 2023-01-01

Yizi Zhang, Tianxiao He, Julien Boussard, Charlie Windolf, Olivier Winter, Eric Trautmann, Noam Roth, Hailey Barrell, Mark Churchland, Nicholas A Steinmetz, Erdem Varol, Cole Hurwitz, Liam Paninski

{"title":"Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes.","authors":"Yizi Zhang, Tianxiao He, Julien Boussard, Charlie Windolf, Olivier Winter, Eric Trautmann, Noam Roth, Hailey Barrell, Mark Churchland, Nicholas A Steinmetz, Erdem Varol, Cole Hurwitz, Liam Paninski","doi":"","DOIUrl":"","url":null,"abstract":"Neural decoding and its applications to brain computer interfaces (BCI) are essential for understanding the association between neural activity and behavior. A prerequisite for many decoding approaches is spike sorting, the assignment of action potentials (spikes) to individual neurons. Current spike sorting algorithms, however, can be inaccurate and do not properly model uncertainty of spike assignments, therefore discarding information that could potentially improve decoding performance. Recent advances in high-density probes (e.g., Neuropixels) and computational methods now allow for extracting a rich set of spike features from unsorted data; these features can in turn be used to directly decode behavioral correlates. To this end, we propose a spike sorting-free decoding method that directly models the distribution of extracted spike features using a mixture of Gaussians (MoG) encoding the uncertainty of spike assignments, without aiming to solve the spike clustering problem explicitly. We allow the mixing proportion of the MoG to change over time in response to the behavior and develop variational inference methods to fit the resulting model and to perform decoding. We benchmark our method with an extensive suite of recordings from different animals and probe geometries, demonstrating that our proposed decoder can consistently outperform current methods based on thresholding (i.e. multi-unit activity) and spike sorting. Open source code is available at https://github.com/yzhang511/density_decoding.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"36 ","pages":"77604-77631"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12227127/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144577101","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

Neural Information Processing: 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part VII 神经信息处理:第29届国际会议，ICONIP 2022，虚拟事件，11月22日至26日，2022，会议录，第七部分

Advances in neural information processing systems Pub Date : 2023-01-01 DOI: 10.1007/978-981-99-1648-1

引用次数: 0

Scaling laws for language encoding models in fMRI. fMRI 中语言编码模型的缩放定律。

Advances in neural information processing systems Pub Date : 2023-01-01

Richard J Antonello, Aditya R Vaidya, Alexander G Huth

{"title":"Scaling laws for language encoding models in fMRI.","authors":"Richard J Antonello, Aditya R Vaidya, Alexander G Huth","doi":"","DOIUrl":"","url":null,"abstract":"Representations from transformer-based unidirectional language models are known to be effective at predicting brain responses to natural language. However, most studies comparing language models to brains have used GPT-2 or similarly sized language models. Here we tested whether larger open-source models such as those from the OPT and LLaMA families are better at predicting brain responses recorded using fMRI. Mirroring scaling results from other contexts, we found that brain prediction performance scales logarithmically with model size from 125M to 30B parameter models, with ~15% increased encoding performance as measured by correlation with a held-out test set across 3 subjects. Similar logarithmic behavior was observed when scaling the size of the fMRI training set. We also characterized scaling for acoustic encoding models that use HuBERT, WavLM, and Whisper, and we found comparable improvements with model size. A noise ceiling analysis of these large, high-performance encoding models showed that performance is nearing the theoretical maximum for brain areas such as the precuneus and higher auditory cortex. These results suggest that increasing scale in both models and data will yield incredibly effective models of language processing in the brain, enabling better scientific understanding as well as applications such as decoding.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"36 ","pages":"21895-21907"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11258918/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141735836","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

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations 从专家论证看kl正则化强化学习中的病态

Advances in neural information processing systems Pub Date : 2022-12-28 DOI: 10.48550/arXiv.2212.13936

Tim G. J. Rudner, Cong Lu

引用次数: 16

Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks 探索卷积神经网络的未探索张量网络分解

Advances in neural information processing systems Pub Date : 2022-12-05 DOI: 10.3902/jnns.29.193

K. Hayashi, Taiki Yamaguchi, Yohei Sugawara, S. Maeda

引用次数: 2

Distinguishing Learning Rules with Brain Machine Interfaces. 用脑机接口区分学习规则。

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

Jacob P Portes, Christian Schmid, James M Murray

{"title":"Distinguishing Learning Rules with Brain Machine Interfaces.","authors":"Jacob P Portes, Christian Schmid, James M Murray","doi":"","DOIUrl":"","url":null,"abstract":"Despite extensive theoretical work on biologically plausible learning rules, clear evidence about whether and how such rules are implemented in the brain has been difficult to obtain. We consider biologically plausible supervised- and reinforcement-learning rules and ask whether changes in network activity during learning can be used to determine which learning rule is being used. Supervised learning requires a credit-assignment model estimating the mapping from neural activity to behavior, and, in a biological organism, this model will inevitably be an imperfect approximation of the ideal mapping, leading to a bias in the direction of the weight updates relative to the true gradient. Reinforcement learning, on the other hand, requires no credit-assignment model and tends to make weight updates following the true gradient direction. We derive a metric to distinguish between learning rules by observing changes in the network activity during learning, given that the mapping from brain to behavior is known by the experimenter. Because brain-machine interface (BMI) experiments allow for precise knowledge of this mapping, we model a cursor-control BMI task using recurrent neural networks, showing that learning rules can be distinguished in simulated experiments using only observations that a neuroscience experimenter would plausibly have access to.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"25937-25950"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10129057/pdf/nihms-1843275.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9391634","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