Basic Unit: As a Common Module of Neural Networks


  • Seisuke Yanagawa OptID, Machida, Tokyo, Japan



In this paper, the logic is developed assuming that all parts of the brain are composed of a combination of modules that basically have the same structure. The feeding behavior of searching for food while avoiding the dangers of animals in the early stages of evolution is regarded as the basis of time series data processing. The module that performs the processing is presented by a neural network equipped with a learning function based on Hebb's rule, and is called a basic unit. The basic units are arranged in layers, and the information between the layers is bidirectional. This new neural network is an extension of the traditional neural network that has evolved from pattern recognition. The biggest feature is that in the processing of time series data, the activated part changes according to the context structure inherent in the data, and can be mathematically expressed the method of predicting events from the context of learned behavior and utilizing it in best action.


Acceptance and generation of time-series data, Context learning, Prediction using context, Extended DNN, Two-way communication between layers


[1] G.Buzsaki “Rhythms of the Brain”, Oxford university press, 2006, p.43.

[2] S.Yanagawa “Each Role of Short-Term and LongTerm Memory in Neural Networks American Journal of Neural Networks and Applications (AJNNA).(ISSN Print: 2469-7400; ISSN Online:2469-7419).

[3] S.Yanagawa “From Bacteria, a Consideration of the Evolution of Neural Network” Journal of Mechanics Engineering and Automation 1 (2019) p.17-23.

[4] S.Yanagawa, “Neural Network That Learns Sequential Processing and Predicts by the Context.” In The 28th Annual Conference of the Japanese Neural Network Society (JNNS2018).

[5] D. C. Dennet, “From Bacteria to Bach and Back: The Evolution of Minds.” In Penguin.

[6] T M.Iacoboni, “Mirroring People.” Picador 33. 2008.


How to Cite

Yanagawa, S. (2021). Basic Unit: As a Common Module of Neural Networks. Electrical Science & Engineering, 3(1), 1–3.


Article Type