当前位置:
X-MOL 学术
›
arXiv.cs.AI
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Indeterminate Probability Neural Network
arXiv - CS - Artificial Intelligence Pub Date : 2023-03-21 , DOI: arxiv-2303.11536 Tao Yang, Chuang Liu, Xiaofeng Ma, Weijia Lu, Ning Wu, Bingyang Li, Zhifei Yang, Peng Liu, Lin Sun, Xiaodong Zhang, Can Zhang
arXiv - CS - Artificial Intelligence Pub Date : 2023-03-21 , DOI: arxiv-2303.11536 Tao Yang, Chuang Liu, Xiaofeng Ma, Weijia Lu, Ning Wu, Bingyang Li, Zhifei Yang, Peng Liu, Lin Sun, Xiaodong Zhang, Can Zhang
We propose a new general model called IPNN - Indeterminate Probability Neural
Network, which combines neural network and probability theory together. In the
classical probability theory, the calculation of probability is based on the
occurrence of events, which is hardly used in current neural networks. In this
paper, we propose a new general probability theory, which is an extension of
classical probability theory, and makes classical probability theory a special
case to our theory. Besides, for our proposed neural network framework, the
output of neural network is defined as probability events, and based on the
statistical analysis of these events, the inference model for classification
task is deduced. IPNN shows new property: It can perform unsupervised
clustering while doing classification. Besides, IPNN is capable of making very
large classification with very small neural network, e.g. model with 100 output
nodes can classify 10 billion categories. Theoretical advantages are reflected
in experimental results.
中文翻译:
不确定概率神经网络
我们提出了一种新的通用模型,称为 IPNN - 不确定概率神经网络,它将神经网络和概率论结合在一起。在经典概率论中,概率的计算是基于事件的发生,这在当前的神经网络中几乎没有使用。在本文中,我们提出了一种新的一般概率论,它是经典概率论的扩展,并使经典概率论成为我们理论的特例。此外,对于我们提出的神经网络框架,神经网络的输出被定义为概率事件,并基于对这些事件的统计分析,推导出分类任务的推理模型。IPNN 显示出新特性:它可以在进行分类的同时进行无监督聚类。除了,IPNN 能够用非常小的神经网络进行非常大的分类,例如具有 100 个输出节点的模型可以分类 100 亿个类别。理论优势体现在实验结果中。
更新日期:2023-03-22
中文翻译:
不确定概率神经网络
我们提出了一种新的通用模型,称为 IPNN - 不确定概率神经网络,它将神经网络和概率论结合在一起。在经典概率论中,概率的计算是基于事件的发生,这在当前的神经网络中几乎没有使用。在本文中,我们提出了一种新的一般概率论,它是经典概率论的扩展,并使经典概率论成为我们理论的特例。此外,对于我们提出的神经网络框架,神经网络的输出被定义为概率事件,并基于对这些事件的统计分析,推导出分类任务的推理模型。IPNN 显示出新特性:它可以在进行分类的同时进行无监督聚类。除了,IPNN 能够用非常小的神经网络进行非常大的分类,例如具有 100 个输出节点的模型可以分类 100 亿个类别。理论优势体现在实验结果中。