.png){kind=icon}
返回
Synchronization-Inspired Interpretable Neural Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2023.3297672.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Synchronization is a ubiquitous phenomenon in nature that enables the orderly presentation of information. In the human brain, for instance, functional modules such as the visual, motor, and language cortices form through neuronal synchronization. Inspired by biological brains and previous neuroscience studies, we propose an interpretable neural network incorporating a synchronization mechanism. The basic idea is to constrain each neuron, such as a convolution filter, to capture a single semantic pattern while synchronizing similar neurons to facilitate the formation of interpretable functional modules. Specifically, we regularize the activation map of a neuron to surround its focus position of the activated pattern in a sample. Moreover, neurons locally interact with each other, and similar ones are synchronized together during the training phase adaptively. Such local aggregation preserves the globally distributed representation nature of the neural network model, enabling a reasonably interpretable representation. To analyze the neuron interpretability comprehensively, we introduce a series of novel evaluation metrics from multiple aspects. Qualitative and quantitative experiments demonstrate that the proposed method outperforms many state-of-the-art algorithms in terms of interpretability. The resulting synchronized functional modules show module consistency across data and semantic specificity within modules.
Keyword:
Synchronization
Neurons
Semantics
Neural networks
Measurement
Training
Biological system modeling
Active interpretability
interpretability metrics
interpretable neural networks
synchronization
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
分享收藏Intercellular Adhesion Molecule 1 (ICAM-1) Gene Variant is Associated with Coronary Artery Calcification Independent of Soluble ICAM-1 Levels细胞间粘附分子1 (ICAM-1) 基因变异与冠状动脉钙化相关，与可溶性ICAM-1水平无关
PREAI
分享收藏A Machine Learning Technique to Predict Biaxial Failure Envelope of Unidirectional Composite Lamina
PREAI
分享收藏Prediction of Mechanical Properties of Rubberized Concrete Incorporating Fly Ash and Nano Silica by Artificial Neural Network Technique.png)
Axioms
OAAI
AxiomsIF0
OAAI分享收藏Binding of factor VIIa to tissue factor on human fibroblasts leads to activation of phospholipase C and enhanced PDGF-BB–stimulated chemotaxis因子VIIa与人成纤维细胞上的组织因子的结合导致磷脂酶C的激活和pdgf-bb刺激的趋化性的增强Blood
BloodIF0
PREAI
分享收藏Cell-free Protein Synthesis in an Autoinduction System for NMR Studies of Protein–Protein Interactions用于NMR研究蛋白质-蛋白质相互作用的自动诱导系统中的无细胞蛋白质合成
PREAI
分享收藏
查看更多内容