Informational Neurobayesian Approach to Neural Networks Training. Opportunities and Prospects
This addresses the high data and computational demands in neural network training, potentially benefiting resource-constrained applications, though it appears incremental as an enhancement to existing Bayesian methods.
The authors tackled the classification problem by proposing the Informational Neurobayesian Approach (INA), which reduces the need for large training data and computational power compared to traditional methods, with experiments showing promising results.
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.