Unifying models of information processing across machine learning, artificial intelligence and neuroscience

统一机器学习、人工智能和神经科学的信息处理模型

• 批准号: EP/X011151/1
• 负责人: Padraig Gleeson
• 金额: $ 161.6万
• 依托单位: University College London
• 依托单位国家: 英国
• 项目类别: Fellowship
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FX011151%2F1
• 关键词: Unifying; models; information; processing; across

The structure and function of circuits in the brain have inspired many innovations in artificial intelligence (AI) and robotics. New mechanisms for how information is processed in the brain are constantly being discovered, both at the cellular level (how individual neurons, synapses and circuits process input signals received from our senses), and at the cognitive level (how decisions are made and actions planned). A better understanding of these processes, honed over millions of years of evolution, can help us make AI systems more robust and efficient. On the other hand, advances in AI provide neuroscientists with important clues on how the brain may process information and provide powerful new computational tools to add to their arsenal of research techniques. However, because researchers and software developers in these fields often have different objectives and use different terminology, workflows and approaches, there is still a big disconnect between these areas. This makes it extremely difficult for researchers to share and exchange their ideas, their latest findings, and their tools (such as models and software) with each other.An example is the variety of approaches being taken to studying and building computer models of vision. Huge progress has been made in Machine Learning (ML) for image recognition and classification using deep convolutional neural networks. Many computational neuroscientists on the other hand investigate vision using spiking neuronal elements arranged in populations inspired by the visual processing pathway of the brain. Cognitive scientists try to understand object recognition and subsequent decision making from a more abstract, higher level. While all of these perspectives are important, they use very different software frameworks and terminology for building models and disseminating their work, limiting how progress in one domain can be readily interpreted and reused in another.I aim to address this unnecessary disconnection between disciplines in this fellowship. I have extensive experience in computational neuroscience and the development of standards, tools, and infrastructure that enable building, sharing, and reuse of complex, biologically realistic models. I am the main developer of the well established NeuroML exchange format and associated software tools that are used widely by researchers and large scale brain initiatives around the world. To expand the scope of this into related domains, I recently initiated a new international collaboration to develop MDF (Model Description Format). MDF is designed to be a more general format for models across both AI and neuroscience - from complex deep learning models and artificial neural networks, all the way to biologically detailed neuronal models and models of cognition. I will build on my preliminary work in this area to expand the scope of MDF and create associated analysis methods to provide a powerful suite of tools for a wide range of researchers and application developers working with brain-inspired network models. This work will be guided by specific scientific use cases based on my previous research (cortical computation, in-silico emulation of worm behaviour), where widely varying approaches are used by different researchers to examine these complex systems.An EPSRC Open Fellowship will provide the resources necessary to develop and expand these technologies while acquiring new scientific and professional skills necessary to lead in this area. The Plus Component is an absolutely crucial part of this, supporting me to actively engage with, and disseminate these approaches to researchers from a wide range of fields, as well as build a diverse community of users and developers around the technologies. Many of the barriers to communicating ideas across AI/ML/neuroscience are related to lack of the underlying software/modelling support, and the work proposed in this fellowship will make significant progress in this area.

大脑中电路的结构和功能激发了人工智能（AI）和机器人技术的许多创新。关于大脑如何处理信息的新机制不断被发现，无论是在细胞水平（单个神经元，突触和电路如何处理从我们的感官接收的输入信号）还是在认知水平（如何做出决定和计划行动）。更好地理解这些经过数百万年进化磨练的过程，可以帮助我们使人工智能系统更加强大和高效。另一方面，人工智能的进步为神经科学家提供了关于大脑如何处理信息的重要线索，并提供了强大的新计算工具来增加他们的研究技术。然而，由于这些领域的研究人员和软件开发人员通常有不同的目标，使用不同的术语，工作流程和方法，这些领域之间仍然存在很大的脱节。这使得研究人员很难相互分享和交流他们的想法、最新发现和工具（如模型和软件），例如，研究和构建视觉计算机模型的方法多种多样。机器学习（ML）在使用深度卷积神经网络进行图像识别和分类方面取得了巨大进展。另一方面，许多计算神经科学家研究视觉使用尖峰神经元元素，这些神经元元素排列在受大脑视觉处理途径启发的群体中。认知科学家试图从更抽象、更高的层次来理解物体识别和随后的决策。虽然所有这些观点都很重要，但它们使用非常不同的软件框架和术语来构建模型和传播他们的工作，限制了一个领域的进展如何容易地在另一个领域中解释和重用。我在计算神经科学以及标准，工具和基础设施的开发方面拥有丰富的经验，这些标准，工具和基础设施可以构建，共享和重用复杂的生物现实模型。我是NeuroML交换格式和相关软件工具的主要开发人员，这些软件工具被世界各地的研究人员和大规模的大脑计划广泛使用。为了将其范围扩展到相关领域，我最近发起了一项新的国际合作来开发MDF（模型描述格式）。它被设计成一种更通用的格式，用于人工智能和神经科学的模型-从复杂的深度学习模型和人工神经网络，一直到生物详细的神经元模型和认知模型。我将在这一领域的初步工作的基础上，扩大神经网络的范围，并创建相关的分析方法，为使用脑启发网络模型的广泛研究人员和应用程序开发人员提供一套强大的工具。这项工作将由基于我以前的研究（皮层计算，蠕虫行为的计算机模拟）的特定科学用例指导，其中不同的研究人员使用各种各样的方法来研究这些复杂的系统。EPSRC开放奖学金将提供开发和扩展这些技术所需的资源，同时获得在该领域领先所需的新科学和专业技能。Plus组件是其中至关重要的一部分，支持我积极参与并向来自各个领域的研究人员传播这些方法，并围绕这些技术建立一个多元化的用户和开发人员社区。在人工智能/机器学习/神经科学中交流思想的许多障碍都与缺乏底层软件/建模支持有关，这项研究中提出的工作将在这一领域取得重大进展。

项目成果

The NeuroML ecosystem for standardized multi-scale modeling in neuroscience

用于神经科学标准化多尺度建模的 NeuroML 生态系统

• DOI: 10.1101/2023.12.07.570537
• 发表时间: 2023
• 作者: Sinha A