Correo Electrónico
DNINFOA - SIA
Bibliotecas
Convocatorias
Identidad U.N.
Publicado
Los hilos del aprendizaje: tejiendo conexiones entre máquinas y mentes humanas
The threads of learning: weaving connections between machines and human minds
DOI:
https://doi.org/10.15446/dyna.v92n237.118489Palabras clave:
aprendizaje mecánico, aprendizaje profundo, comportamiento humano, inteligencia artificial (es)Machine learnig, deep learning, human behavior, artificial intelligence (en)
Descargas
Desde 2018, OpenAI ha liderado el desarrollo de inteligencia artificial tras la popularización de su herramienta ChatGPT, promoviendo la investigación de la comunicación humano-máquina que sigue teniendo problemas para representar la personalidad de una persona. Por ello, el objetivo del presente estudio es identificar métodos de Deep Learning que puedan recrear genuinamente la personalidad humana. Esta investigación utilizó la pregunta PICO, la metodología PRISMA y la búsqueda en la base de datos SCOPUS para identificar artículos vinculados a diferentes enfoques de aprendizaje profundo para mejorar la comunicación Humano-Máquina. Se identificaron como modelos más destacados de Deep Learning el modelo mixto que integra LSTM con RNN y FNN, el algoritmo Multi-Distribution Noise y el Latent Semantic Indexing. Se concluye que el Deep Learning ofrece herramientas poderosas para la comunicación Humano-Máquina, pero requiere investigaciones continuas para optimizar y automatizar su aplicación práctica.
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.
Referencias
[1] Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I., Improving language understanding by generative pre-training. amazon web services, [online]. 2018. Disponible en: https://s3-us-west-2.amazonaws.com/openai-assets/research-covers/language-unsupervised/
[2] Manakitsa, N., Maraslidis, G.S., Moysis, L., and Fragulis, G.F., A review of machine learning and deep learning for object detection, semantic segmentation, and human action recognition in machine and robotic vision. Technologies, 12(2), art. 20015, 2024. DOI: https://doi.org/10.3390/technologies12020015
[3] Negro, P., and Pons, C., Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: a systematic review of the literature. Inteligencia Artificial, 25(69), pp. 13-41, 2022. DOI: https://doi.org/10.4114/intartif.vol25iss69pp13-41
[4] Maroto-Gómez, M., Castro-González, Á., Castillo, J.C., Malfaz, M., and Salichs, M.A., An adaptive decision-making system supported on user preference predictions for human–robot interactive communication. User Modeling and User-Adapted Interaction, 33(2), pp. 359–403, 2023. DOI: https://doi.org/10.1007/s11257-022-09321-2
[5] Hooshyar, D., Azevedo, R., and Yang, Y., Augmenting deep Neural Networks with symbolic educational knowledge: towards trustworthy and interpretable AI for education. Machine Learning and Knowledge Extraction, 6(1), pp. 593-618, 2024. DOI: https://doi.org/10.3390/make6010028
[6] Wang, P., Fan, E., and Wang, P., Comparative analysis of image classification algorithms based on traditional machine learning and deep learning. Pattern Recognition Letters, 141, pp. 61–67, 2021. DOI: https://doi.org/10.1016/j.patrec.2020.07.042
[7] Yilmaz, A.A., Guzel, M.S., Bostanci, E., and Askerzade, I., A novel action recognition framework based on deep-learning and genetic algorithms. IEEE Access, 8, pp. 100631–100644, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.2997962
[8] Page, M.J., McKenzie, J.E., Bossuyt, P.M., et al. Declaración PRISMA 2020: una guía actualizada para la publicación de revisiones sistemáticas. Revista panamericana de salud pública, 46, art. 112, 2020. DOI: https://doi.org/10.26633/RPSP.2022.112
[9] Ger, Y., Nachmani, E., Wolf, L. and Shahar, N., Harnessing the flexibility of neural networks to predict dynamic theoretical parameters underlying human choice behavior. PLOS Computational Biology, 20(1), art. 1011678, 2024. DOI: https://doi.org/10.1371/journal.pcbi.1011678
[10] Kuroki-Júnior, G.H., and Gottschalg-Duque, C., Information architecture applied on natural language processing: a proposal. Information Science contributions on data pre-processing for training and learning of artificial neural networks. Revista Digital de Biblioteconomia e Ciência da Informação, 21, art. 023002, 2023. DOI: https://doi.org/10.20396/rdbci.v21i00.8671396/30919
[11] Remaida, A., Abdellaoui, B., Lafraxo, M.A., Sabri, Z., Nouib, H., El Idrissi, Y.E.B., and Moumen, A., Application of artificial neural networks for personality traits prediction based on handwriting. Indonesian Journal of Electrical Engineering and Computer Science, 31(3), pp. 1534-1544, 2023. DOI: http://doi.org/10.11591/ijeecs.v31.i3.pp1534-1544
[12] Yu, Z., Li, S., Sun, L., Liu, L. and Haining, W., Multi-distribution noise quantisation: an extreme compression scheme for transformer according to parameter distribution. Connection Science, 34(1), pp. 990–1004, 2022. DOI: https://doi.org/10.1080/09540091.2021.2024510
[13] YiTao, Z., Natural language processing with improved deep learning neural networks. Scientific Programming, 2022, pp. 1-8, DOI: https://doi.org/10.1155/2022/6028693
[14] Jäger, G., and Reisinger, D., Can we replicate real human behaviour using artificial neural networks?. Mathematical and Computer Modelling of Dynamical Systems, 28(1), pp. 95-109, 2022. DOI: https://doi.org/10.1080/13873954.2022.2039717
[15] Guest, O., and Martin, A.E., On logical inference over brains, behaviour, and artificial neural networks. Computational Brain & Behavior, 6, pp. 213-227, 2023. DOI: https://doi.org/10.1007/s42113-022-00166-x
[16] Alamia, A., Gauducheau, V., Paisios, D., and VanRullen, R., Comparing feedforward and recurrent neural network architectures with human behavior in artificial grammar learning. Scientific Reports, 10(1), pp. 22172, 2020. DOI: https://doi.org/10.1038/s41598-020-79127-y
[17] Hasibuan, M.S., Nugroho, L.E. and Santosa, P.I., Model detecting learning styles with artificial Neural Network. Journal of Technology and Science Education, 9(1), pp. 85-95, 2019. DOI: https://doi.org/10.3926/jotse.540
[18] Costa-Jussà, M.R., Nuez, Á., and Segura, C., Experimental research on encoder-decoder architectures with attention for chatbots. Computación y Sistemas, 22(4), pp. 1233-1239, 2018. DOI: https://doi.org/10.13053/cys-22-4-3060
[19] Cleeremans, A., Servan-Schreiber, D., and McClelland, J.L., Finite state automata and simple recurrent networks. Neural Computation, 1, pp. 372-381, 1989. DOI: https://doi.org/10.1162/neco.1989.1.3.372
[20] Servan-Schreiber, D., Cleeremans, A., and McClelland, J.L., Graded state machines: the representation of temporal contingencies in simple recurrent networks. Machine Learning, [online]. 7, pp. 161-193, 1991. Available at: https://link.springer.com/article/10.1007/BF00114843
[21] Cleeremans, A., and McClelland, J.L., Learning the structure of event sequences. Journal of Experimental Psychology: General, 120(3), pp. 235-253, 1991. DOI: https://doi.org/10.1037/0096-3445.120.3.235
[22] Giles, C.L., Miller; C.B., Chen, D., Chen, H.H., Sun, G.Z. and Lee, Y.C., Learning and extracting finite state automata with second-order recurrent neural networks. Neural Computation, 4, pp. 393-405, 1992. DOI: https://doi.org/10.10.1162/neco.1992.4.3.393
[23] Dienes, Z., Connectionist and memory-array models of artificial grammar learning. Cognitive Science, 16, pp. 41–79, 1992. DOI: https://doi.org/10.1207/s15516709cog1601_2
[24] Bodén, M., and Wiles, J., Context-free and context-sensitive dynamics in recurrent neural networks. Connection Science. 12(3/4), pp. 197-210, 2000. DOI: https://doi.org/10.1080/095400900750060122
[25] Kinder, A., and Shanks, D.R., Amnesia and the declarative/nondeclarative distinction: a recurrent network model of classification, recognition, and repetition priming. Journal of Cognitive Neuroscience, 13(5), pp. 648–669, 2001. DOI: https://doi.org/10.1162/089892901750363217
[26] Tunney, R.J., and Shanks, D.R., Subjective measures of awareness and implicit cognition. Memory & Cognition, 31, pp. 1060–1071, 2023. DOI: https://doi.org/10.3758/BF03196127
[27] Petersson, K.M., Grenholm, P. and Forkstam, C., Artificial grammar learning and neural networks. Proceedings of the 27th Annual Conference of the Cognitive Science Society, [online]. 2005, pp. 1726–1731. Available at: https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=1bef0e63cefc9eefce22c32ae676350b714f6aca
[28] Wierzchon, M., and Barbasz, J.A., Wierzchoń, M., and Barbasz, J., A connectionist model of artificial grammar learning: simulations based on Higham (1997) Indexes of Knowledge Representation. 29th Annual Conference of the Cognitive Science Society, 2008.
[29] Cohen, M., Caciularu, A., Rejwan, I., and Berant, J., Inducing regular grammars using recurrent Neural Networks. Computation and Language, pp. 1-5, 2018. DOI: https://doi.org/10.48550/arXiv.1710.10453
[30] Alamia, A., Gauducheau, V., Paisios, D., and VanRullen, R., Which Neural Network Architecture matches Human Behavior in Artificial Grammar” Learning? Neurons and Cognition, 2019. DOI: https://doi.org/10.48550/arXiv.1902.04861
Cómo citar
IEEE
ACM
ACS
APA
ABNT
Chicago
Harvard
MLA
Turabian
Vancouver
Descargar cita
Licencia
Derechos de autor 2025 DYNA
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
El autor o autores de un artículo aceptado para publicación en cualquiera de las revistas editadas por la facultad de Minas cederán la totalidad de los derechos patrimoniales a la Universidad Nacional de Colombia de manera gratuita, dentro de los cuáles se incluyen: el derecho a editar, publicar, reproducir y distribuir tanto en medios impresos como digitales, además de incluir en artículo en índices internacionales y/o bases de datos, de igual manera, se faculta a la editorial para utilizar las imágenes, tablas y/o cualquier material gráfico presentado en el artículo para el diseño de carátulas o posters de la misma revista.
