在深度NMF网络中引入局部特征交互，提升视觉模型性能。
Including local feature interactions in deep non-negative matrix factorization networks improves performance
- 在NMF模块后加入正向活动混合模块，模拟皮层柱处理机制。
- 在基准数据集上超越同规模传统CNN的性能表现。
- 为生物可解释性深度网络设计提供新思路，适合神经形态计算研究者。
大脑利用正信号进行信息传递，早期视觉皮层中的前向交互也是正向的，由兴奋性突触实现。而局部交互则包含抑制机制。非负矩阵分解（NMF）能够捕捉正向长程交互的生物学约束，并可用随机脉冲实现。尽管NMF可作为视觉系统早期神经处理的抽象形式化，但含NMF模块的深度卷积网络性能仍不及同规模的CNN。然而，当每个局部NMF模块后接一个混合其正向激活的模块时，模型在基准数据集上的表现超过了同规模的原始深度卷积网络。该设置可视为对皮层（超）柱处理过程更符合生物学的模拟，具有提升深度网络性能的潜力。
原文摘要 · Abstract (English)
The brain uses positive signals as a means of signaling. Forward interactions in the early visual cortex are also positive, realized by excitatory synapses. Only local interactions also include inhibition. Non-negative matrix factorization (NMF) captures the biological constraint of positive long-range interactions and can be implemented with stochastic spikes. While NMF can serve as an abstract formalization of early neural processing in the visual system, the performance of deep convolutional networks with NMF modules does not match that of CNNs of similar size. However, when the local NMF modules are each followed by a module that mixes the NMF's positive activities, the performances on the benchmark data exceed that of vanilla deep convolutional networks of similar size. This setting can be considered a biologically more plausible emulation of the processing in cortical (hyper-)columns with the potential to improve the performance of deep networks.
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。