基于局部神经信号的非对称学习规则实现创造性生成与图像修复
Neural Langevin Machine: a local asymmetric learning rule can be creative
- 用局部神经信号设计非对称学习规则，模拟生物预测学习机制
- 在训练数据增加时，模型从记忆转向泛化，展现相变特征
- 可连续探索生成空间，支持图像去噪和多样化生成
循环神经网络的固定点可用于存储和生成信息。这些固定点可通过玻尔兹曼-吉布斯分布捕捉，从而引出神经朗之万动力学，用于发现真实数据集的生成模式。我们称此类生成模型为神经朗之万机，其基于仅依赖局部神经信号的非对称、发放率-速度调整的学习规则，具备生物学合理性。生成过程揭示了一个非平衡态行为，随着训练数据量增大，出现从记忆到泛化的相变。该神经启发模型还能对相空间进行连续探索，生成多种图像，并实现对受损图像的去噪。
原文摘要 · Abstract (English)
Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points can be captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that can be used to find them for generative learning of a real dataset. We call this type of generative model a neural Langevin machine, which derives an asymmetric and firing-rate-speed adjusted learning rule requiring only local neural signals, thereby bearing biological relevance in terms of local predictive learning. An interesting out-of-equilibrium regime of the generative process is revealed, together with a memorization-to-generalization transition with increasing training data size. The neuro-inspired machine can also realize a continuous exploration of the phase space for different kinds of generative images and can denoise a corrupted image as well.
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。