可解释的无监督神经网络结构用于通过ONMF的可微分重建和稀疏的自编码器进行数据聚类
1School of Computer and Control Engineering, Yantai University, Yantai, 264005, Shandong, China.
概括
这项研究介绍了OSINN,一种用于可解释集群的新型神经网络. OSINN集成了正交非负矩阵因数分解 (ONMF),以提高无监督学习任务的透明度和性能.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 数据科学数据科学数据科学
背景情况:
- 神经网络在聚类任务中往往缺乏可解释性.
- 传统方法依赖于后期解释或监督学习,限制透明度.
- 现有的深度集群方法在端到端的可训练性和清晰的可解释性方面扎.
研究的目的:
- 开发一种用于可解释集群的新型神经网络模型.
- 通过综合因素化方法提高聚类任务的透明度和性能.
- 为了使神经网络具有嵌入式集群层的端到端训练.
主要方法:
- 在神经网络集群层中整合直角非负矩阵分解 (ONMF).神经网络集群层.
- 使用Sparse自动编码器 (SAE) 进行特征提取的模型增强.
- 为端到端的培训和可解释性开发可差异化的ONMF重建.
主要成果:
- 在基准数据集上,OSINN实现了高集群精度:MNIST (90%),CIFAR-10 (24%),时尚-MNIST (64%) 和CIFAR-100 (44%).
- 该模型在传统集群算法 (+10%) 和深度集群方法 (+1.2%) 上显示出显著的性能改进.
- 在集群性能方面,OSINN超过非负矩阵因子化 (NMF) 和自动编码器 (AE) 变体超过1.5%.
结论:
- OSINN为基于神经网络的集群提供了一种透明和可解释的方法.
- 端到端可训练架构提高了对集群结果的性能和理解.
- 这种方法对大型,未标记的数据集特别有效,推进了无监督学习能力.
更多相关视频
12:27Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
Published on: February 15, 2017
6.9K
08:51Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
Published on: November 1, 2019
5.6K
相关概念视频
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
25
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
25
01:30Classification of Signals
314
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
314