Predictive-Coding Neural Networks: How They Learn and Behave

预测编码神经网络：它们如何学习和行为

• 批准号: RGPIN-2020-04271
• 负责人: Orchard, Jeff
• 金额: $ 2.11万
• 依托单位: University of Waterloo
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=715365
• 关键词: Predictive; Coding; Neural; Networks; How

The brain is a bewilderingly complex organ, but progress is being made to unlock its secrets. The theory of Predictive Coding (PC) states that the brain is a hierarchy of layers in which each layer communicates only with the layer below and the layer above. This architecture mimics the reciprocal connectivity found between brain regions in the mammalian cortex. Information in PC networks flows both up and down the network simultaneously. Our brains do the same, suggesting that perception is an active, two-way inference process. We hypothesize that this two-way process makes perception more robust. A number of challenges remain for PC networks. Firstly, some of the beneficial properties of PC classification networks are thought to stem from them being generative. Instead of feeding an image of a “2” into the bottom of the network and having the network classify it as a two, one can also feed in the class vector for “two” at the top of the network and have the network generate an image of a two. Unfortunately, those images typically do not resemble the training data, but appear random. We will investigate a variety of techniques to encourage PC networks to generate recognizable inputs. Generative PC networks might be more robust at perception than artificial neural networks (ANNs). Current ANNs are easy to fool by adding slight adjustments to the input. Yet, these adversarial inputs do not fool humans. We will test our generative PC networks against adversarial inputs to see if they fall victim to the same attacks, or if they are closer to human perception. It was recently revealed that PC networks approximate the backpropagation learning algorithm; as they run, they learn autonomously, unlike ANNs that require an external governing process to manage the learning. This suggests that something akin to backprop could be going on in the brain. However, the link to backprop was proven only for a restricted, layered architecture. We will extend the theory to derive biologically plausible learning algorithms for other common network topologies, such as layers with recurrent connections. Such a layer could model an attractor network and implement the dynamic process of perception, including the SoftMax-like bistable process of looking at an optical illusion. The learning algorithms developed in this research program will revolutionize AI and inform cognitive neuroscience. These robust neural networks will make mission-critical applications (like vision systems for driverless cars) more reliable. Moreover, these learning methods are autonomous, so PC networks can learn without a supervising program and, as a result, would be easier to deploy in specialized hardware, like those being developed in the emerging industry of neuromorphic chips. The students involved in this research will have a strategic advantage in the fields of AI and neuroscience, and will be leaders in the industrial revolution and expand the theory and practice in academic research.

大脑是一个令人困惑的复杂器官，但正在取得进展，以解开它的秘密。预测编码（PC）理论认为，大脑是一个层次结构，其中每一层只与下层和上层进行通信。这种结构模仿了哺乳动物大脑皮层中大脑区域之间的相互连接。PC网络中的信息同时在网络中向上和向下流动。我们的大脑也会做同样的事情，这表明感知是一个活跃的双向推理过程。我们假设这种双向过程使感知更加强大。 PC网络仍然面临许多挑战。首先，PC分类网络的一些有益特性被认为源于它们的生成性。与其将“2”的图像输入到网络的底部并让网络将其分类为2，还可以在网络的顶部输入“2”的类向量，并让网络生成2的图像。不幸的是，这些图像通常不像训练数据，而是随机出现。我们将研究各种技术，以鼓励PC网络产生可识别的输入。 生成PC网络在感知方面可能比人工神经网络（ANN）更强大。目前的人工神经网络很容易通过对输入进行轻微调整来欺骗。然而，这些对抗性的输入并不能愚弄人类。我们将测试我们的生成PC网络对抗性输入，看看它们是否会成为相同攻击的受害者，或者它们是否更接近人类的感知。 最近发现，PC网络近似于反向传播学习算法;当它们运行时，它们自主学习，不像ANN需要外部控制过程来管理学习。这表明大脑中可能存在类似于反向传播的东西。然而，到反向传播的链接仅在受限的分层架构中得到证明。我们将扩展该理论，为其他常见的网络拓扑结构（例如具有循环连接的层）推导出生物学上合理的学习算法。这样的一个层可以模拟吸引子网络，并实现感知的动态过程，包括类似SoftMax的观看视错觉的过程。 在这项研究计划中开发的学习算法将彻底改变人工智能，并为认知神经科学提供信息。这些强大的神经网络将使关键任务应用（如无人驾驶汽车的视觉系统）更加可靠。此外，这些学习方法是自主的，因此PC网络可以在没有监督程序的情况下学习，因此更容易部署在专用硬件中，就像新兴的神经形态芯片行业中开发的那些硬件一样。 参与这项研究的学生将在人工智能和神经科学领域具有战略优势，并将成为工业革命的领导者，扩大学术研究的理论和实践。