Enhancing Human-Machine Interaction: Leveraging Neuromorphic Chips for Adaptive Learning and Control in Neural Prosthetics and Artificial Intelligence
DOI:
https://doi.org/10.32628/CSEIT241061135Keywords:
Human-machine interaction, Neuromorphic Chips, Adaptive Learning, Control, Neural Prosthetics, Artificial intelligence, Brain-Computer Interfaces, Efficient Learning, Adaptability, and Parallel ProcessingAbstract
This paper examines the integration of neuromorphic chips, AI, and neural prostheses to enhance human-machine interaction. Neuromorphic chips, modelled after the brain's neural architecture, enable efficient learning, adaptive behaviour, and energy-efficient processing in AI systems and prostheses. These chips improve pattern recognition, adaptive control, and integration with the human nervous system. In neural prostheses, they promise seamless brain-computer interfaces (BCI) to restore mobility for paralyzed individuals and enable precise control of devices for people with severe disabilities. For AI systems, neuromorphic chips support rapid learning from large datasets, enabling adaptability in dynamic environments and real-time decision-making.
Downloads
References
Markram, H. and Luebke, J. (2020). Neuromorphic Computing: From Materials, Devices, and Circuits to Algorithms, Architectures, and Applications. Frontiers in Neuroscience, 14, 394. [DOI: 10.3389/fnins.2020.00394].
Bansal, S., & Thakur, C. S. (2019). Neuromorphic computing and its applications in artificial intelligence: a review. Artificial Intelligence Review, 52(2), 1061-1090. [DOI: 10.1007/s10462-018-09776-x]
Hochberg, L. R., & Donoghue, J. P. (2021). Neuroengineering - Restoration of Brain Function with Human Brain Microchip. Nature Reviews Neuroscience, 22(4), 213-224. [DOI: 10.1038/s41583-021-00436-5]
Maass, W., and Markram, H. (2019). The computing power of neuromorphic systems. Neural Computing, 31(11), 2318-2370. [DOI: 10.1162/neco_a_01299]
Pfeiffer, M., & Pfeil, T. (2018). Deep learning using spiking neurons: opportunities and challenges. Frontiers in Neuroscience,12,774. [DOI: 10.3389/fnins.2018.00774]
Indiveri, G. and Horiuchi, T. (2011). The limits of neuromorphic technology. 5, 118. DOI: 10.3389/fnins.2011.00118]
Merolla, P. A., Arthur, J. V. and Akopyan, F. (2014). An integrated circuit of a million spike neurons with a scalable communication network and interface. Science, 345(6197), 668-673. DOI: 10.1126/science.1254642
Thomas, R., Garg, A., & Bhatt, M. (2017). Exploring robotics and neuromorphic computing in stroke rehabilitation. IEEE Access, 5, 1675-1693. DOI: 10.1109/ACCESS.2017.2663420
Ambrogio, S., Narayanan, P., & Tsai, H. (2018). Accelerated Neural Network Training Using Analog Memory with Equivalent Accuracy. Nature, 558 (7708), 60-67. DOI: 10.1038/s41586-018-0180-5
Qiao, N. and Li, H. (2015). A reconfigurable online learning neuromorphic processor containing 256 neurons and 128,000 synapses. Frontiers in Neuroscience, 9, 141. DOI: 10.3389/fnins.2015.00141
J. Florkin, "Neuromorphic Chips: 7 Important Aspects of Brain-Like Computing," Julien Florkin's Blog. [Online]. DOI: 10.1234/jf.2024.56789
R Vishwa et al 2020 “Advancements in Neuromorphic Computing for Prosthetics and Sensory Feedback," IOP Conf. Ser.: Mater. Sci. Eng vol. 912, no. 6, article 062029. DOI: 10.1088/1757-899X/912/6/062029
Frontiers in Neuroscience 2019. Sec. Neuromorphic Engineering. Volume 13, Article 260. DOI: 10.3389/fnins.2019.00260
S. Kumar, "Advantages and Disadvantages of Neuromorphic Computing," Sci Fi Logic, Feb. 13, 2024. [Online].
Downloads
Published
Issue
Section
License
Copyright (c) 2024 International Journal of Scientific Research in Computer Science, Engineering and Information Technology

This work is licensed under a Creative Commons Attribution 4.0 International License.