Using ant biology and natural environments to enhance models of vision and robot navigation

利用蚂蚁生物学和自然环境来增强视觉和机器人导航模型

• 批准号: 2768907
• 金额: --
• 依托单位: University of Sussex
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2022
• 资助国家: 英国
• 起止时间: 2022 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2768907
• 关键词: Using; ant; biology; natural; environments

Over the past decade, Deep neural networks (DNNs) have revolutionised AI, achieving highly impressive perceptual feats especially in the domain of vision. In particular, convolutional neural networks have surpassed humans in their ability to classify naturalistic images. These findings, together with their similarities in architecture and activity patterns, have sparked major renewed interest in DNNs as models of the brain. However, these models diverge from the perceptual abilities of biological vision in important and unexpected ways, e.g., through their weakness to noise, susceptibility to adversarial attacks and inability to recognise stylised representations. This has been shown to be due to their over-reliance on diagnostic but brittle features such as texture [1] or even a single pixel correlated with the image class [2]. In part, these limitations arise from a lack of inductive biases in the models to regularise their learning, coupled with unrealistic training environments. Some of these shortcomings have recently been addressed through incorporating more of the properties of the primate visual system into these models [3] or by using more extensive and naturalistic training regimes [4]. The aim of this project is to leverage our knowledge of the brain and foraging behaviour of ants to see if both incorporating biological constraints and naturalistic training data can generate DNN's whose perceptual abilities have the robustness and generalisability of biological vision.

在过去的十年中，深度神经网络（DNN）彻底改变了人工智能，实现了令人印象深刻的感知能力，特别是在视觉领域。特别是，卷积神经网络在对自然图像进行分类的能力上已经超过了人类。这些发现，以及它们在结构和活动模式上的相似性，引发了人们对DNN作为大脑模型的兴趣。然而，这些模型以重要和意想不到的方式偏离了生物视觉的感知能力，例如，通过他们对噪音的弱点，对敌对攻击的敏感性和无法识别风格化的表示。这已被证明是由于它们过度依赖于诊断但脆弱的特征，例如纹理[1]或甚至与图像类相关的单个像素[2]。在某种程度上，这些限制是由于模型中缺乏归纳偏差来规范它们的学习，再加上不切实际的训练环境。其中一些缺点最近已经通过将灵长类动物视觉系统的更多特性纳入这些模型[3]或通过使用更广泛和自然的训练制度[4]得到解决。这个项目的目的是利用我们对蚂蚁大脑和觅食行为的了解，看看结合生物约束和自然主义训练数据是否可以生成DNN，其感知能力具有生物视觉的鲁棒性和普遍性。