Title :
Architecting for Causal Intelligence at Nanoscale
Author :
Khasanvis, Santosh ; Mingyu Li ; Rahman, Mostafizur ; Biswas, Ayan K. ; Salehi-Fashami, Mohammad ; Atulasimha, Jayasimha ; Bandyopadhyay, Supriyo ; Moritz, Csaba Andras
Abstract :
Conventional Von Neumann microprocessors are inefficient for supporting machine intelligence due to layers of abstraction, limiting the feasibility of machine-learning frameworks in critical applications. A new approach for architecting intelligent systems, using physical equivalence and leveraging emerging nanotechnology, can pave the way to machine intelligence everywhere.
Keywords :
learning (artificial intelligence); microcomputers; nanotechnology; intelligent system; machine intelligence; machine-learning framework; nanotechnology; von Neumann microprocessor; Bayes methods; Cognition; Computer architecture; Machine intelligence; Nanoscale devices; Probabilistic logic; advanced technologies; emerging technologies; machine learning; magneto-electric circuits; mixed-signal computation; non-Von Neumann architectures; probabilistic inference; rebooting computing;
DOI :
10.1109/MC.2015.367
