Lightning Talk: Bridging Neuro-Dynamics and Cognition

Brain-inspired computing models have shown great potential to outperform today's deep learning solutions in terms of robustness and energy efficiency. Particularly, Spiking Neural Networks (SNNs) and HyperDimensional Computing (HDC) have shown promising results in enabling efficient and robust...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2023 60th ACM/IEEE Design Automation Conference (DAC) s. 1 - 2
Hlavní autor: Imani, Mohsen
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 09.07.2023
Témata:
Brain modeling
Brain-inspired Computing
Computational modeling
Design automation
Hyperdimensional Computing
Lightning
MIMICs
Philosophical considerations
Psychology
Spiking Neural Network
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Brain-inspired computing models have shown great potential to outperform today's deep learning solutions in terms of robustness and energy efficiency. Particularly, Spiking Neural Networks (SNNs) and HyperDimensional Computing (HDC) have shown promising results in enabling efficient and robust cognitive learning. Despite the success, these two brain-inspired models have different strengths. While SNN mimics the physical properties of the human brain, HDC models the brain on a more abstract and functional level. Their design philosophies demonstrate complementary patterns that motivate their combination. With the help of the classical psychological model of memory, we aim to explore the difference between Spiking neural networks and hyperdimensional computing and how they can combine to develop a more advanced cognitive learning model.
DOI:10.1109/DAC56929.2023.10247931