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

在过去的十年里，深度神经网络（dnn）已经彻底改变了人工智能，特别是在视觉领域取得了令人印象深刻的感知壮举。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越了人类。这些发现，加上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，这些模型在重要和意想不到的方面偏离了生物视觉的感知能力，例如，通过它们对噪声的弱点，对抗性攻击的敏感性以及无法识别程式化表示。这被证明是由于他们过度依赖于诊断性但脆弱的特征，如纹理[1]，甚至是与图像类别[2]相关的单个像素。在某种程度上，这些限制来自于模型中缺乏归纳偏差来规范他们的学习，再加上不切实际的训练环境。最近，通过将灵长类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[3]，解决了其中的一些缺点。该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训练数据是否可以生成感知能力具有生物视觉鲁棒性和通用性的深度神经网络。

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.