References on Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices

In a groundbreaking study published in Advanced Materials in 2019, Tang, J. et al. explored the intersection of biological and artificial neural networks using emerging neuromorphic devices. The research delves into the fundamentals, progress, and challenges of bridging these two domains, shedding light on the potential for revolutionary advancements in the field of neural network technology.

The study builds on previous work by Sejnowski, T. J. & Rosenberg, C. R. in 1987, which focused on parallel networks that learn to pronounce English text. It also draws from the comprehensive book by Samarasinghe, S. on Neural Networks for Applied Sciences and Engineering, providing a solid foundation for the exploration of neuromorphic devices.

One of the key findings highlighted in the study is the acceleration of deep neural network training using resistive cross-point devices, as demonstrated by Gokmen, T. & Vlasov, Y. in 2016. This breakthrough has significant implications for the future of neural network technology and artificial intelligence.

The research also touches on brain-inspired computing, with Mehonic, A. & Kenyon, A. J. emphasizing the need for a master plan in this rapidly evolving field. The use of memristive crossbar arrays for brain-inspired computing, as discussed by Xia, Q. & Yang, J. J., represents a promising avenue for future research and development.

Overall, the study by Tang, J. et al. serves as a comprehensive overview of the current state of neural network technology, highlighting the progress made, the challenges faced, and the exciting possibilities that lie ahead in the realm of bridging biological and artificial neural networks.