从机器学习的角度实现痕迹：匹配预测
Implementing engrams from a machine learning perspective: matching for prediction
摘要：
尽管有证据表明，记忆印迹作为我们大脑中的记忆支持结构存在，但在神经科学中，关于它们的物理实现可能是什么，还没有达成共识的框架。在这里，我们提出了如何设计一个计算机系统来实现使用神经网络的痕迹，主要目的是探索新的想法，使用机器学习技术，在神经科学的挑战指导下。基于自动编码器，我们提出了潜在的神经空间作为索引，用于以压缩格式存储和检索信息。我们认为这种技术是预测学习的第一步：自动编码器被设计为将重建的信息与接收到的原始信息进行比较，提供一种预测能力，这是一个有吸引力的进化论点。然后，我们考虑如何在潜在的神经空间中对应于不同类型的感觉输入的不同状态可以通过同步激活链接，提供了一个稀疏的实施使用概念神经元的记忆的基础。最后，我们列出了一些将神经科学和数据科学联系起来的挑战和问题，这些挑战和问题可能对这两个领域产生影响，并得出结论，正如许多科学家已经建议的那样，需要一种更加跨学科的方法。
英文摘要：
Despite evidence for the existence of engrams as memory support structures in our brains, there is no consensus framework in neuroscience as to what their physical implementation might be. Here we propose how we might design a computer system to implement engrams using neural networks, with the main aim of exploring new ideas using machine learning techniques, guided by challenges in neuroscience. Building on autoencoders, we propose latent neural spaces as indexes for storing and retrieving information in a compressed format. We consider this technique as a first step towards predictive learning: autoencoders are designed to compare reconstructed information with the original information received, providing a kind of predictive ability, which is an attractive evolutionary argument. We then consider how different states in latent neural spaces corresponding to different types of sensory input could be linked by synchronous activation, providing the basis for a sparse implementation of memory using concept neurons. Finally, we list some of the challenges and questions that link neuroscience and data science and that could have implications for both fields, and conclude that a more interdisciplinary approach is needed, as many scientists have already suggested.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
