Sadegh-Zadeh Seyed-Ali, Bahrami Mahboobe, Soleimani Ommolbanin, Ahmadi Sahar
Department of Computing, School of Digital, Technologies and Arts, Staffordshire University Stoke-on-Trent ST4 2DE, UK.
Behavioral Sciences Research Centre, School of Medicine, Isfahan University of Medical Sciences Isfahan, Iran.
Am J Neurodegener Dis. 2024 Dec 25;13(5):34-48. doi: 10.62347/NHKD7661. eCollection 2024.
This study explores the concept of neural reshaping and the mechanisms through which both human and artificial intelligence adapt and learn.
To investigate the parallels and distinctions between human brain plasticity and artificial neural network plasticity, with a focus on their learning processes.
A comparative analysis was conducted using literature reviews and machine learning experiments, specifically employing a multi-layer perceptron neural network to examine regression and classification problems.
Experimental findings demonstrate that machine learning models, similar to human neuroplasticity, enhance performance through iterative learning and optimization, drawing parallels in strengthening and adjusting connections.
Understanding the shared principles and limitations of neural and artificial plasticity can drive advancements in AI design and cognitive neuroscience, paving the way for future interdisciplinary innovations.
本研究探讨神经重塑的概念以及人类和人工智能适应与学习的机制。
研究人类大脑可塑性与人工神经网络可塑性之间的异同，重点关注它们的学习过程。
通过文献综述和机器学习实验进行比较分析，具体使用多层感知器神经网络来研究回归和分类问题。
实验结果表明，机器学习模型与人类神经可塑性相似，通过迭代学习和优化来提高性能，在加强和调整连接方面存在相似之处。
理解神经可塑性和人工可塑性的共同原理及局限性，可推动人工智能设计和认知神经科学的发展，为未来的跨学科创新铺平道路。
