提出新模型让神经网络潜变量更独立可解释。
A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity
- 将潜变量分组并强制组间独立，组内可复杂纠缠
- 在合成数据和真实神经数据上显著提升解耦效果
- 适合研究神经活动的独立计算模块与连接结构
低秩循环神经网络（lrRNN）能揭示神经群体活动的低维潜动态。然而其功能连接虽为低秩，却缺乏独立性解释，难以给各潜变量分配明确计算角色。为此，我们提出因子化循环神经网络（FacRNN），一种生成式lrRNN框架，假设潜动态在组内独立，同时允许组内灵活纠缠。该设计使潜动态可独立演化，又具备内部复杂计算能力。我们在变分自编码器（VAE）框架下重构lrRNN，引入部分相关性惩罚项以促进潜变量组间的独立性。在合成数据、猴子运动皮层M1及小鼠电压成像数据上的实验表明，相比不鼓励组间独立性的基线lrRNN，FacRNN在低维空间中的潜轨迹解耦性和可解释性，以及低秩连接结构方面均有持续改进。
原文摘要 · Abstract (English)
Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks independence interpretations, making it difficult to assign distinct computational roles to different latent dimensions. To address this, we propose the Factored Recurrent Neural Network (FacRNN), a generative lrRNN framework that assumes group-wise independence among latent dynamics while allowing flexible within-group entanglement. These independent latent groups allow latent dynamics to evolve separately, but are internally rich for complex computation. We reformulate the lrRNN under a variational autoencoder (VAE) framework, enabling us to introduce a partial correlation penalty that encourages independence between groups of latent dimensions. Experiments on synthetic, monkey M1, and mouse voltage imaging data show that FacRNN consistently improves the disentanglement and interpretability of learned neural latent trajectories in low-dimensional space and low-rank connectivity over baseline lrRNNs that do not encourage group-wise independence.
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。