CAREER: Co-evolution of Machine Intelligence and Continuous Information

职业：机器智能和连续信息的共同进化

• 批准号: 2045804
• 负责人: Rui Li
• 金额: $ 47.06万
• 依托单位: Rochester Institute of Tech
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-06-01 至 2026-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2045804&HistoricalAwards=false
• 关键词: CAREER; Co; evolution; Machine; Intelligence

The real world is complex and constantly changing. Information becomes progressively available over time via continuous stream of noisy data. For example, molecular biology databases are always updated with various new gene-protein relationships (e.g., gene regulations, genetic interactions) validated in wet lab experiments. High-energy experiments in astro-particle physics give rise to large amounts of data in the form of continuous high-volume streams. Interpersonal interaction behaviors (e.g., facial expressions, gestures) contain rhythms that are not only correlated in time but also exhibit phase synchronization in an ongoing flow of mutual influence. In order to fully exploit these non-stationary streams of data online and in real-time, this project aims to build machine intelligence capable of quantifying uncertainty, constantly accommodating new information, and consolidating previously acquired knowledge in the meantime. The project is specifically motivated by applications to computational biology, astro-physics, and human interaction behaviors, and will result in innovative online inference methods that are broadly applicable across data-intensive domains. Furthermore, this research will support the interdisciplinary development of a diverse student body of disability, women, and minorities, and the development of graduate-level machine learning courses. The outreach work will contribute to increasing partnerships between academia and industry, and increasing public scientific literacy.The overarching research objective is to create a unified dynamic statistical inference framework based on Bayesian nonparametrics to jointly update deep neural network parameters, adapt neural architectures, and consolidate acquired knowledge. The investigator highlights three inter-related projects that significantly advance this research agenda: (1) neural parameter online inference: design and develop online inference algorithms to recursively update posterior distributions of neural network parameters with continuous data stream, (2) neural architecture online inference: create modeling and computational methods to enable deep neural architectures to automatically go through a qualitative growth to accommodate progressively available information from new data as they are streaming, and (3) dynamic knowledge distillation: design and develop modeling methods to merge old knowledge with new one while both neural parameters and architectures are evolving to extract statistical structures from heterogeneous data stream. These research aims will be complemented by multidisciplinary collaborations to rigorously validate and generalize the framework. This research will lead to efficient statistical online inference methods for the whole information integration and data science.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

现实世界是复杂的，不断变化。随着时间的流逝，信息通过连续的嘈杂数据逐渐获得。例如，在湿实验室实验中验证的各种新的基因蛋白关系（例如，基因法规，遗传相互作用）始终更新分子生物学数据库。天体粒子物理学的高能量实验以连续的高量流形式产生大量数据。人际交往行为（例如，面部表情，手势）包含的节奏不仅在时间上相关，而且在持续的相互影响的流动中表现出相位同步。为了在线和实时充分利用这些非平稳的数据流，该项目旨在建立能够量化不确定性，不断适应新信息并合并以前获得的知识的机器智能。该项目是由应用于计算生物学，天文学和人类互动行为的应用，并将导致创新的在线推理方法，这些方法广泛适用于数据密集型领域。此外，这项研究将支持一个多元化的残疾，妇女和少数群体的学生跨学科发展，以及研究生级的机器学习课程的发展。宣传工作将有助于增加学术界与行业之间的伙伴关系，并提高公共科学素养。总体研究目标是建立一个基于贝叶斯非参数的统一动态统计推理框架，以共同更新深层神经网络参数，适应神经体系结构，适应神经结构，并合并获得知识。研究者突出了三个相互关联的项目，这些项目显着推进了这项研究议程：（1）神经参数在线推理：设计和开发在线推理算法，以递归更新神经网络参数的后验分布，具有连续数据流的神经网络参数，（2）神经结构推理：在线推理和计算方法，以启用新的模型，以启用新的数据，以使其逐渐逐步促进，从而使新的数据逐渐逐步促进，从而使他们能够通过自动构建术语来实现，从而可以通过自动构建效果，从而使他们能够通过促进性能，从而使他们可以通过促进促进性，从而通过促进自动构建方法，从是流媒体，（3）动态知识蒸馏：设计和开发建模方法与旧知识合并，而神经​​参数和体系结构都在演变为从异质数据流中提取统计结构。这些研究的目标将由多学科的合作进行补充，以严格验证和概括框架。这项研究将为整个信息集成和数据科学提供有效的统计在线推断方法。该奖项反映了NSF的法定使命，并使用基金会的知识分子优点和更广泛的影响审查标准，被认为值得通过评估来提供支持。

项目成果

Joint Inference for Neural Network Depth and Dropout Regularization

• 发表时间: 2021
• 作者: C. KishanK.;Rui Li;MohammadMahdi Gilany

TarGAN: Target-aware generative adversarial networks for multi-modality medical image translation

• DOI: 10.48550/arxiv.2105.08993
• 发表时间: 2021-01-01
• 期刊: arXiv.
• 作者: Chen, J.;Wei, J.;Li, R.
• 通讯作者: Li, R.

Predicting Biological Interactions with Higher-Order Graph Convolutional Networks

用高阶图卷积网络预测生物相互作用

• 发表时间: 2022
• 期刊: IEEEACM transactions on computational biology and bioinformatics
• 作者: KC, Kishan;Li, Rui;Cui, Feng;Haake, Anne R
• 通讯作者: Haake, Anne R

Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation

通过无判别器图像到图像转换的无监督多模态医学图像配准

• 发表时间: 2022
• 期刊: IJCAI
• 作者: Chen, Z-K;Wei, J;Li, R.
• 通讯作者: Li, R.

Slice Imputation: Multiple Intermediate Slices Interpolation for Anisotropic 3D Medical Image Segmentation

切片插补：用于各向异性 3D 医学图像分割的多个中间切片插值

• 发表时间: 2022
• 期刊: Computers in biology and medicine
• 影响因子: 7.7
• 作者: Wu, Z-T;Wei, J;Wang, J-B;Li, R.
• 通讯作者: Li, R.