对比七种海布学习规则，发现贝叶斯海布在记忆存储和原型提取上表现最佳。
Benchmarking local Hebbian learning rules for memory storage and prototype extraction
- 采用非模块化与模块化递归网络，测试七种海布学习规则的性能。
- 贝叶斯海布规则在多种条件下均实现最高存储容量和原型提取准确率。
- 适用于研究脑启发式记忆系统或神经网络原型学习任务的研究者。
关联记忆或内容寻址记忆是计算机科学与信息处理中的关键功能，也是认知与计算脑科学的核心概念。尽管已有多种神经网络架构和学习规则被用于建模大脑的关联记忆，以研究图底分割、感知重构和竞争等核心功能，但一个较少被研究却同样重要的能力——原型提取——仍待深入。该任务中，训练集包含失真原型实例，目标是在给定新失真实例时恢复出正确的生成原型。本文对七种不同的海布学习规则在非模块化与模块化递归网络中的关联记忆性能进行基准测试，这些网络采用获胜者通吃动态机制，在中等稀疏二值模式上运行。我们评估了模式存储能力、权重信息容量、原型提取效果以及对数据相关性的敏感度。结果表明，原始加性海布规则容量最差；协方差学习规则虽稳健但容量中等；而贝叶斯海布学习规则在几乎所有测试条件下均表现出最高容量。
原文摘要 · Abstract (English)
Associative memory or content-addressable memory is an important component function in computer science and information processing, and at the same time a key concept in cognitive and computational brain science. Many different neural network architectures and learning rules have been proposed to model the brain's associative memory while investigating key component functions like figure-ground segmentation, perceptual reconstruction and rivalry. A less investigated but equally important capability of associative memory is prototype extraction where the training set comprises distorted prototype instances and the task is to recall the correct generating prototype given a new distorted instance. In this paper we benchmark associative memory function of seven different Hebbian learning rules employed in non-modular and modular recurrent networks with winner-take-all dynamics operating on moderately sparse binary patterns. We measure pattern storage and weight information capacity, prototype extraction capabilities, and sensitivity to correlations in data. The original additive Hebb rule comes out with worst capacity, covariance learning proves to be robust but with moderate capacity, and the Bayesian-Hebbian learning rules show highest capacity in almost all different conditions tested.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。