ActiveAI - active learning and selective attention for robust, transparent and efficient AI

ActiveAI - 主动学习和选择性关注，实现稳健、透明和高效的人工智能

• 批准号: EP/S030964/1
• 负责人: Andrew Philippides
• 金额: $ 121.51万
• 依托单位: University of Sussex
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2019
• 资助国家: 英国
• 起止时间: 2019 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FS030964%2F1
• 关键词: ActiveAI; active; learning; selective; attention

We will bring together world leaders in insect biology and neuroscience with world leaders in biorobotic modelling and computational neuroscience to create a partnership that will be transformative in understanding active learning and selective attention in insects, robots and autonomous systems in artificial intelligence (AI). By considering how brains, behaviours and the environment interact during natural animal behaviour, we will develop new algorithms and methods for rapid, robust and efficient learning for autonomous robotics and AI for dynamic real world applications.Recent advances in AI and notably in deep learning, have proven incredibly successful in creating solutions to specific complex problems (e.g. beating the best human players at Go, and driving cars through cities). But as we learn more about these approaches, their limitations are becoming more apparent. For instance, deep learning solutions typically need a great deal of computing power, extremely long training times and very large amounts of labeled training data which are simply not available for many tasks. While they are very good at solving specific tasks, they can be quite poor (and unpredictably so) at transferring this knowledge to other, closely related tasks. Finally, scientists and engineers are struggling to understand what their deep learning systems have learned and how well they have learned it. These limitations are particularly apparent when contrasted to the naturally evolved intelligence of insects. Insects certainly cannot play Go or drive cars, but they are incredibly good at doing what they have evolved to do. For instance, unlike any current AI system, ants learn how to forage effectively with limited computing power provided by their tiny brains and minimal exploration of their world. We argue this difference comes about because natural intelligence is a property of closed loop brain-body-environment interactions. Evolved innate behaviours in concert with specialised sensors and neural circuits extract and encode task-relevant information with maximal efficiency, aided by mechanisms of selective attention that focus learning on task-relevant features. This focus on behaving embodied agents is under-represented in present AI technology but offers solutions to the issues raised above, which can be realised by pursuing research in AI in its original definition: a description and emulation of biological learning and intelligence that both replicates animals' capabilities and sheds light on the biological basis of intelligence.This endeavour entails studying the workings of the brain in behaving animals as it is crucial to know how neural activity interacts with, and is shaped by, environment, body and behaviour and the interplay with selective attention. These experiments are now possible by combining recent advances in neural recordings of flies and hoverflies which can identify neural markers of selective attention, in combination with virtual reality experiments for ants; techniques pioneered by the Australian team. In combination with verification of emerging hypotheses on large-scale neural models on-board robotic platforms in the real world, an approach pioneered by the UK team, this project represents a unique and timely opportunity to transform our understanding of learning in animals and through this, learning in robots and AI systems. We will create an interdisciplinary collaborative research environment with a "virtuous cycle" of experiments, analysis and computational and robotic modelling. New findings feed forward and back around this virtuous cycle, each discipline informing the others to yield a functional understanding of how active learning and selective attention enable small-brained insects to learn a complex world. Through this understanding, we will develop ActiveAI algorithms which are efficient in learning and final network configuration, robust to real-world conditions and learn rapidly.

我们将把昆虫生物学和神经科学的世界领先者与生物机器人建模和计算神经科学的世界领先者聚集在一起，建立一种伙伴关系，这将在理解人工智能(AI)中的昆虫、机器人和自主系统的主动学习和选择性注意方面产生革命性的影响。通过考虑大脑、行为和环境在自然动物行为中如何相互作用，我们将为自主机器人和动态现实世界应用的人工智能开发快速、稳健和高效的学习新算法和方法。人工智能特别是深度学习方面的最新进展，已被证明在为特定复杂问题创造解决方案方面取得了令人难以置信的成功(例如，击败最好的人类棋手，在城市中驾驶汽车)。但随着我们对这些方法的了解越来越多，它们的局限性也变得越来越明显。例如，深度学习解决方案通常需要大量的计算能力、极长的训练时间和非常大量的标记训练数据，这些数据对于许多任务来说是根本不可用的。虽然他们非常擅长解决特定的任务，但他们在将这些知识转移到其他密切相关的任务上可能相当糟糕(而且出人意料地如此)。最后，科学家和工程师正在努力理解他们的深度学习系统学到了什么，以及他们学得有多好。与昆虫自然进化的智力相比，这些局限性尤其明显。昆虫当然不会下围棋，也不会开车，但它们非常擅长做它们进化出来的事情。例如，与目前的任何人工智能系统不同，蚂蚁学习如何利用它们微小的大脑提供的有限计算能力和对它们世界的最小探索来有效地觅食。我们认为，这种差异是因为自然智力是大脑-身体-环境闭合循环相互作用的一种属性。进化的先天行为与专门的传感器和神经回路一起以最高的效率提取和编码与任务相关的信息，这得益于将学习集中在与任务相关的特征上的选择性注意机制。这种对行为具体化主体的关注在目前的人工智能技术中没有得到充分的体现，但它提供了对上述问题的解决方案，这可以通过研究人工智能的原始定义来实现：对生物学习和智力的描述和仿真，既复制了动物的能力，又揭示了智能的生物学基础。这项努力需要研究表现动物的大脑的工作原理，因为它对于了解神经活动如何与环境、身体和行为相互作用并由环境、身体和行为以及与选择性注意的相互作用至关重要。这些实验现在是可能的，因为结合了苍蝇和飞蝇神经记录的最新进展，这些神经记录可以识别选择性注意的神经标记，并结合了蚂蚁的虚拟现实实验；这项技术由澳大利亚团队开创。结合英国团队首创的在真实世界的机载机器人平台上对大规模神经模型的新兴假设进行验证，该项目代表着一个独特而及时的机会，可以改变我们对动物学习的理解，并通过此改变我们对机器人和人工智能系统的学习的理解。我们将创造一个跨学科的协作研究环境，实现实验、分析、计算和机器人建模的“良性循环”。新的发现围绕这一良性循环进行反馈，每一门学科都向其他学科提供信息，以产生一种功能性理解，即主动学习和选择性注意如何使小脑昆虫能够学习复杂的世界。通过这一理解，我们将开发出在学习和最终网络配置方面高效、对真实世界条件稳健且学习速度快的ActiveAI算法。

项目成果

A robust geometric method of singularity avoidance for kinematically redundant planar parallel robot manipulators

运动冗余平面并联机器人机械臂奇点避免的鲁棒几何方法

• DOI: 10.1016/j.mechmachtheory.2020.103863
• 发表时间: 2020
• 期刊: Mechanism and Machine Theory
• 影响因子: 5.2
• 作者: Baron N

Multimodal interactions in insect navigation.

• DOI: 10.1007/s10071-020-01383-2
• 发表时间: 2020-11
• 期刊: Animal cognition
• 影响因子: 2.7
• 作者: Buehlmann C;Mangan M;Graham P
• 通讯作者: Graham P

DoPI: The Database of Pollinator Interactions.

• DOI: 10.1002/ecy.3801
• 发表时间: 2022-11
• 期刊: Ecology
• 影响因子: 4.8

Robustness of the Infomax Network for View Based Navigation of Long Routes

用于基于视图的长路线导航的 Infomax 网络的鲁棒性

• DOI: 10.1162/isal_a_00645
• 发表时间: 2023
• 作者: Amin A

Trail using ants follow idiosyncratic routes in complex landscapes

• DOI: 10.3758/s13420-023-00615-y
• 发表时间: 2023-11-22
• 期刊: LEARNING & BEHAVIOR
• 影响因子: 1.8
• 作者: Barrie，Robert;Haalck，Lars;Buehlmann，Cornelia
• 通讯作者: Buehlmann，Cornelia