Advances in neural information processing systems最新文献_第2页

Towards a "universal translator" for neural dynamics at single-cell, single-spike resolution. 迈向单细胞、单尖峰分辨率的神经动力学“通用翻译器”。

Advances in neural information processing systems Pub Date : 2024-01-01

Yizi Zhang, Yanchen Wang, Donato M Jiménez-Benetó, Zixuan Wang, Mehdi Azabou, Blake Richards, Renee Tung, Olivier Winter, Eva Dyer, Liam Paninski, Cole Hurwitz

{"title":"Towards a \"universal translator\" for neural dynamics at single-cell, single-spike resolution.","authors":"Yizi Zhang, Yanchen Wang, Donato M Jiménez-Benetó, Zixuan Wang, Mehdi Azabou, Blake Richards, Renee Tung, Olivier Winter, Eva Dyer, Liam Paninski, Cole Hurwitz","doi":"","DOIUrl":"","url":null,"abstract":"Neuroscience research has made immense progress over the last decade, but our understanding of the brain remains fragmented and piecemeal: the dream of probing an arbitrary brain region and automatically reading out the information encoded in its neural activity remains out of reach. In this work, we build towards a first foundation model for neural spiking data that can solve a diverse set of tasks across multiple brain areas. We introduce a novel self-supervised modeling approach for population activity in which the model alternates between masking out and reconstructing neural activity across different time steps, neurons, and brain regions. To evaluate our approach, we design unsupervised and supervised prediction tasks using the International Brain Laboratory repeated site dataset, which is comprised of Neuropixels recordings targeting the same brain locations across 48 animals and experimental sessions. The prediction tasks include single-neuron and region-level activity prediction, forward prediction, and behavior decoding. We demonstrate that our multi-task-masking (MtM) approach significantly improves the performance of current state-of-the-art population models and enables multitask learning. We also show that by training on multiple animals, we can improve the generalization ability of the model to unseen animals, paving the way for a foundation model of the brain at single-cell, single-spike resolution. Project page and code: https://ibl-mtm.github.io/.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"80495-80521"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12228527/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144577102","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

Crafting Interpretable Embeddings for Language Neuroscience by Asking LLMs Questions. 通过问法学硕士问题来制作语言神经科学的可解释嵌入。

Advances in neural information processing systems Pub Date : 2024-01-01

Vinamra Benara, Chandan Singh, John X Morris, Richard J Antonello, Ion Stoica, Alexander G Huth, Jianfeng Gao

{"title":"Crafting Interpretable Embeddings for Language Neuroscience by Asking LLMs Questions.","authors":"Vinamra Benara, Chandan Singh, John X Morris, Richard J Antonello, Ion Stoica, Alexander G Huth, Jianfeng Gao","doi":"","DOIUrl":"","url":null,"abstract":"Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. However, their opaqueness and proliferation into scientific domains such as neuroscience have created a growing need for interpretability. Here, we ask whether we can obtain interpretable embeddings through LLM prompting. We introduce question-answering embeddings (QA-Emb), embeddings where each feature represents an answer to a yes/no question asked to an LLM. Training QA-Emb reduces to selecting a set of underlying questions rather than learning model weights. We use QA-Emb to flexibly generate interpretable models for predicting fMRI voxel responses to language stimuli. QA-Emb significantly outperforms an established interpretable baseline, and does so while requiring very few questions. This paves the way towards building flexible feature spaces that can concretize and evaluate our understanding of semantic brain representations. We additionally find that QA-Emb can be effectively approximated with an efficient model, and we explore broader applications in simple NLP tasks.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"124137-124162"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021422/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144029876","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

OccFusion: Rendering Occluded Humans with Generative Diffusion Priors. 遮蔽：用生成扩散先验渲染遮挡的人类。

Advances in neural information processing systems Pub Date : 2024-01-01

Adam Sun, Tiange Xiang, Scott Delp, Li Fei-Fei, Ehsan Adeli

引用次数: 0

EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes. EpiCare：动态治疗方案的强化学习基准。

Advances in neural information processing systems Pub Date : 2024-01-01

Mason Hargrave, Alex Spaeth, Logan Grosenick

{"title":"EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes.","authors":"Mason Hargrave, Alex Spaeth, Logan Grosenick","doi":"","DOIUrl":"","url":null,"abstract":"Healthcare applications pose significant challenges to existing reinforcement learning (RL) methods due to implementation risks, limited data availability, short treatment episodes, sparse rewards, partial observations, and heterogeneous treatment effects. Despite significant interest in using RL to generate dynamic treatment regimes for longitudinal patient care scenarios, no standardized benchmark has yet been developed. To fill this need we introduce Episodes of Care (EpiCare), a benchmark designed to mimic the challenges associated with applying RL to longitudinal healthcare settings. We leverage this benchmark to test five state-of-the-art offline RL models as well as five common off-policy evaluation (OPE) techniques. Our results suggest that while offline RL may be capable of improving upon existing standards of care given sufficient data, its applicability does not appear to extend to the moderate to low data regimes typical of current healthcare settings. Additionally, we demonstrate that several OPE techniques standard in the the medical RL literature fail to perform adequately on our benchmark. These results suggest that the performance of RL models in dynamic treatment regimes may be difficult to meaningfully evaluate using current OPE methods, indicating that RL for this application domain may still be in its early stages. We hope that these results along with the benchmark will facilitate better comparison of existing methods and inspire further research into techniques that increase the practical applicability of medical RL.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"130536-130568"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12124763/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144200954","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

Generative Adversarial Model-Based Optimization via Source Critic Regularization. 基于源批评正则化的生成对抗模型优化。

Advances in neural information processing systems Pub Date : 2024-01-01

Michael S Yao, Yimeng Zeng, Hamsa Bastani, Jacob Gardner, James C Gee, Osbert Bastani

引用次数: 0

Topology-Aware Uncertainty for Image Segmentation. 拓扑感知图像分割的不确定性

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

Saumya Gupta, Yikai Zhang, Xiaoling Hu, Prateek Prasanna, Chao Chen

{"title":"Topology-Aware Uncertainty for Image Segmentation.","authors":"Saumya Gupta, Yikai Zhang, Xiaoling Hu, Prateek Prasanna, Chao Chen","doi":"","DOIUrl":"","url":null,"abstract":"Segmentation of curvilinear structures such as vasculature and road networks is challenging due to relatively weak signals and complex geometry/topology. To facilitate and accelerate large scale annotation, one has to adopt semi-automatic approaches such as proofreading by experts. In this work, we focus on uncertainty estimation for such tasks, so that highly uncertain, and thus error-prone structures can be identified for human annotators to verify. Unlike most existing works, which provide pixel-wise uncertainty maps, we stipulate it is crucial to estimate uncertainty in the units of topological structures, e.g., small pieces of connections and branches. To achieve this, we leverage tools from topological data analysis, specifically discrete Morse theory (DMT), to first capture the structures, and then reason about their uncertainties. To model the uncertainty, we (1) propose a joint prediction model that estimates the uncertainty of a structure while taking the neighboring structures into consideration (inter-structural uncertainty); (2) propose a novel Probabilistic DMT to model the inherent uncertainty within each structure (intra-structural uncertainty) by sampling its representations via a perturb- and-walk scheme. On various 2D and 3D datasets, our method produces better structure-wise uncertainty maps compared to existing works. Code available at https://github.com/Saumya-Gupta-26/struct-uncertainty.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"36 ","pages":"8186-8207"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11526043/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142559599","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

Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT. 对比等变自监督学习提高了灵长类动物视觉区域信息技术的一致性。

Advances in neural information processing systems Pub Date : 2024-01-01

Thomas Yerxa, Jenelle Feather, Eero P Simoncelli, SueYeon Chung

{"title":"Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT.","authors":"Thomas Yerxa, Jenelle Feather, Eero P Simoncelli, SueYeon Chung","doi":"","DOIUrl":"","url":null,"abstract":"Models trained with self-supervised learning objectives have recently matched or surpassed models trained with traditional supervised object recognition in their ability to predict neural responses of object-selective neurons in the primate visual system. A self-supervised learning objective is arguably a more biologically plausible organizing principle, as the optimization does not require a large number of labeled examples. However, typical self-supervised objectives may result in network representations that are overly invariant to changes in the input. Here, we show that a representation with structured variability to input transformations is better aligned with known features of visual perception and neural computation. We introduce a novel framework for converting standard invariant SSL losses into \"contrastive-equivariant\" versions that encourage preservation of input transformations without supervised access to the transformation parameters. We demonstrate that our proposed method systematically increases the ability of models to predict responses in macaque inferior temporal cortex. Our results demonstrate the promise of incorporating known features of neural computation into task-optimization for building better models of visual cortex.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"96045-96070"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12058038/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065347","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

Generalizing CNNs to Graphs with Learnable Neighborhood Quantization. 将cnn推广到具有可学习邻域量化的图。

Advances in neural information processing systems Pub Date : 2024-01-01

Isaac Osafo Nkansah, Neil Gallagher, Ruchi Sandilya, Conor Liston, Logan Grosenick

{"title":"Generalizing CNNs to Graphs with Learnable Neighborhood Quantization.","authors":"Isaac Osafo Nkansah, Neil Gallagher, Ruchi Sandilya, Conor Liston, Logan Grosenick","doi":"","DOIUrl":"","url":null,"abstract":"Convolutional neural networks (CNNs) have led to a revolution in analyzing array data. However, many important sources of data, such as biological and social networks, are naturally structured as graphs rather than arrays, making the design of graph neural network (GNN) architectures that retain the strengths of CNNs an active and exciting area of research. Here, we introduce Quantized Graph Convolution Networks (QGCNs), the first framework for GNNs that formally and directly extends CNNs to graphs. QGCNs do this by decomposing the convolution operation into non-overlapping sub-kernels, allowing them to fit graph data while reducing to a 2D CNN layer on array data. We generalize this approach to graphs of arbitrary size and dimension by approaching sub-kernel assignment as a learnable multinomial assignment problem. Integrating this approach into a residual network architecture, we demonstrate performance that matches or exceeds other state-of-the-art GNNs on benchmark graph datasets and for predicting properties of nonlinear dynamics on a new finite element graph dataset. In summary, QGCNs are a novel GNN framework that generalizes CNNs and their strengths to graph data, allowing for more accurate and expressive models.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"82318-82349"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12124760/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144200955","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

A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis. 教科书补救领域转移：医学图像分析的知识先验。

Advances in neural information processing systems Pub Date : 2024-01-01

Yue Yang, Mona Gandhi, Yufei Wang, Yifan Wu, Michael S Yao, Chris Callison-Burch, James C Gee, Mark Yatskar

{"title":"A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis.","authors":"Yue Yang, Mona Gandhi, Yufei Wang, Yifan Wu, Michael S Yao, Chris Callison-Burch, James C Gee, Mark Yatskar","doi":"","DOIUrl":"","url":null,"abstract":"While deep networks have achieved broad success in analyzing natural images, when applied to medical scans, they often fail in unexpected situations. We investigate this challenge and focus on model sensitivity to domain shifts, such as data sampled from different hospitals or data confounded by demographic variables such as sex, race, etc, in the context of chest X-rays and skin lesion images. A key finding we show empirically is that existing visual backbones lack an appropriate prior from the architecture for reliable generalization in these settings. Taking inspiration from medical training, we propose giving deep networks a prior grounded in explicit medical knowledge communicated in natural language. To this end, we introduce Knowledge-enhanced Bottlenecks (KnoBo), a class of concept bottleneck models that incorporates knowledge priors that constrain it to reason with clinically relevant factors found in medical textbooks or PubMed. KnoBo uses retrieval-augmented language models to design an appropriate concept space and an automatic training procedure for recognizing the concept. We evaluate different resources of knowledge and recognition architectures on a broad range of domain shifts across 20 datasets. In our comprehensive evaluation with two imaging modalities, KnoBo outperforms fine-tuned models on confounded datasets by 32.4% on average. Finally, evaluations reveal that PubMed is a promising resource for making medical models less sensitive to domain shift, outperforming other resources on both diversity of information and final prediction performance.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"37 ","pages":"90683-90713"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12064272/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144060948","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

pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization. 通过主成分正则化改进后验抽样cgan。

Advances in neural information processing systems Pub Date : 2024-01-01

Matthew C Bendel, Rizwan Ahmad, Philip Schniter

引用次数: 0