The threads of learning: weaving connections between machines and human minds

Rochambrun-Flores J.; Rivas-Alvarez A.; Neyra-Rivera C. · DYNA (Colombia) (2025) · DOI: 10.15446/dyna.v92n237.118489

Resumen

Since 2018, OpenAI has led the development of artificial intelligence following the popularization of its ChatGPT tool, promoting research into human-machine communication, which still struggles to represent a person's personality. Therefore, the objective of this study is to identify deep learning methods that can truly recreate human personality. This research used the PICO query, the PRISMA methodology, and a search of the SCOPUS database to identify articles linked to different deep learning approaches to improve human-machine communication. The most notable deep learning models were the mixed model that integrates LSTM with RNN and FNN, the Multi-Distribution Noise algorithm, and Latent Semantic Indexing. It is concluded that deep learning offers powerful tools for human-machine communication but requires continued research to optimize and automate its practical application.

Instituciones: Universidad Tecnológica del Perú