发表机构
African Institute for Mathematical Sciences (AIMS); Rochester Institute of Technology (RIT)（非洲数学科学研究所; 罗切斯特理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对神经网络压缩和可解释性挑战，提出神经原子流行度（NAP）框架，通过四阶段管道运行，经多实验验证，该框架能实现结构稀疏性，概率校准良好，是追求贝叶斯神经网络多方面特性的可靠解决方案。
AI 中文摘要
神经网络压缩和可解释性仍是现代深度学习中的开放挑战，数十亿参数架构以透明度、计算效率和可靠的不确定性量化为代价实现了令人印象深刻的准确性。本文介绍了神经原子流行度（NAP），这是一种用于前馈神经网络中结构化节点级模型选择的有原则的贝叶斯框架。NAP引入神经原子（激活单元），通过四阶段管道运行：通过迭代幅度剪枝（IMP）进行贝叶斯彩票票（BLT）识别、尖峰和平板独立高斯（SS-IG）模型的软变分训练、泊松二项式（PB）最优层大小选择以及贝叶斯微调，以产生稀疏、稳定、可解释且准确的模型。在模拟非线性回归、两个UCI基准数据集（混凝土、年度预测MSD）和MNIST图像分类任务上的广泛实证验证表明，NAP实现了当前最优的结构稀疏性，在MNIST上可将活跃节点减少至原始密集架构的8%，同时概率校准良好：偶然-认知不确定性分解表明，在所有实验中模型无知仅占总预测方差的3%至4%，回归可靠性图证实预测区间覆盖率接近名义值（观察到93.4%，目标为95%）。这些结果确立了NAP作为在贝叶斯神经网络中同时追求稀疏性、准确性、可解释性和不确定性量化的可靠、理论基础扎实且计算上易于处理的解决方案。
英文摘要
Neural network compression and interpretability remain open challenges in modern deep learn- ing, where billion-parameter architectures deliver impressive accuracy at the cost of trans- parency, computational efficiency, and reliable uncertainty quantification. This paper introduces Neural Atom Prevalence (NAP), a principled Bayesian framework for structured node-level model selection in feedforward neural networks. NAP introduces the neural atom (activation unit) and functions as a hybrid method operating through a four-phase pipeline: Bayesian Lottery Ticket (BLT) identification via Iterative Magnitude Pruning (IMP), soft variational training of the Spike and Slab Independent Gaussian (SS-IG) model, Poisson-Binomial (PB) optimal layer-size selection, and Bayesian fine-tuning to produce a sparse, stable, interpretable, and accurate model. Extensive empirical validation across simulated nonlinear regression, two UCI benchmark datasets (Concrete, YearPredictionMSD), and the MNIST image classification task demonstrates that NAP achieves state-of-the-art structural sparsity, reducing active nodes to as few as 8% of the original dense architecture on MNIST, while well-calibrated probabilisti- cally: the aleatoric-epistemic uncertainty decomposition reveals that model ignorance accounts for only 3 to 4% of total predictive variance across all experiments, and regression reliability diagrams confirm a near-nominal predictive interval coverage (93.4% observed against a 95% target). These results establish NAP as a reliable, theoretically grounded, and computation- ally tractable solution to the simultaneous pursuit of sparsity, accuracy, interpretability, and uncertainty quantification in Bayesian neural networks.
Comments32 pages, 4 figures
