神经网络训练的信息神经模型方法。机会和前景
Informational Neurobayesian Approach to Neural Networks Training. Opportunities and Prospects
摘要:
本文从信息论的角度对分类问题进行了研究。目前在该领域的研究集中在优化和bapliterature方法。虽然这给出了令人满意的结果,他们需要大量的数据和计算的训练on.Authors提出了一个新的概念,名为信息神经网络方法(INA),它允许解决同样的问题,但需要显着更少的训练数据以及计算能力。实验结果表明,该算法具有较好的性能。
英文摘要:
A study of the classification problem in context of information theory is presented in the paper. Current research in that field is focused on optimisation and bayesian approach. Although that gives satisfying results, they require a vast amount of data and computations to train on. Authors propose a new concept named Informational Neurobayesian Approach (INA), which allows to solve the same problems, but requires significantly less training data as well as computational power. Experiments were conducted to compare its performance with the traditional one and the results showed that capacity of the INA is quite promising.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。