Author:
Li Da,Li Molan,Huang Zhili
Abstract
Some neural models achieve outstanding results in image recognition, semantic segmentation and natural language processing. However, their classification performance on structured and small-scale datasets that do not involve feature extraction is worse than that of traditional algorithms, although they require more time to train. In this paper, we propose a brain-like neural model with interactive stimulation (NMIS) that focuses on data classification. It consists of a primary neural field and a senior neural field that play different cognitive roles. The former is used to correspond to real instances in the feature space, and the latter stores the category pattern. Neurons in the primary field exchange information through interactive stimulation and their activation is transmitted to the senior field via inter-field interaction, simulating the mechanisms of neuronal interaction and synaptic plasticity, respectively. The proposed NMIS is biologically plausible and does not involve complex optimization processes. Therefore, it exhibits better learning ability on small-scale and structured datasets than traditional BP neural networks. For large-scale data classification, a nearest neighbor NMIS (NN_NMIS), an optimized version of NMIS, is proposed to improve computational efficiency. Numerical experiments performed on some UCI datasets show that the proposed NMIS and NN_NMIS are significantly superior to some classification algorithms that are widely used in machine learning.
Reference55 articles.
1. Cognitive Psychology: A Student’Handbook;Eysenck,2015
2. Supervised machine learning: A review of classification techniques;Kotsiantis;Emerg. Artif. Intell. Appl. Comput. Eng.,2007
3. Machine learning: a review of classification and combining techniques
4. Multiple instance classification: Review, taxonomy and comparative study
5. Era of deep neural networks: A review;Sharma;Proceedings of the 2017 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT),2017
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献