Non-Boolean computing with nanomagnets for computer vision applications

Bhanja, Sanjukta; Karunaratne, D. K.; Panchumarthy, Ravi; Rajaram, S.; Sarkar, Sudeep

doi:10.1038/nnano.2015.245

Cited by 57 publications

(39 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following this idea, it has been recently demonstrated experimentally that arrays of coupled nanomagnets can perform pattern recognition in images by minimizing their global energy [134]. The attractors can also be the different synchronized states of networks of coupled oscillators.…”

Section: Implementations Of Bioinspired Hardware Using Spintronicsmentioning

confidence: 99%

Spintronic Nanodevices for Bioinspired Computing

2016

View full text Add to dashboard Cite

Bioinspired hardware holds the promise of low-energy, intelligent, and highly adaptable computing systems. Applications span from automatic classification for big data management, through unmanned vehicle control, to control for biomedical prosthesis. However, one of the major challenges of fabricating bioinspired hardware is building ultra-high-density networks out of complex processing units interlinked by tunable connections. Nanometer-scale devices exploiting spin electronics (or spintronics) can be a key technology in this context. In particular, magnetic tunnel junctions (MTJs) are well suited for this purpose because of their multiple tunable functionalities. One such functionality, non-volatile memory, can provide massive embedded memory in unconventional circuits, thus escaping the von-Neumann bottleneck arising when memory and processors are located separately. Other features of spintronic devices that could be beneficial for bioinspired computing include tunable fast nonlinear dynamics, controlled stochasticity, and the ability of single devices to change functions in different operating conditions. Large networks of interacting spintronic nanodevices can have their interactions tuned to induce complex dynamics such as synchronization, chaos, soliton diffusion, phase transitions, criticality, and convergence to multiple metastable states. A number of groups have recently proposed bioinspired architectures that include one or several types of spintronic nanodevices. In this paper, we show how spintronics can be used for bioinspired computing. We review the different approaches that have been proposed, the recent advances in this direction, and the challenges toward fully integrated spintronics complementary metal–oxide–semiconductor (CMOS) bioinspired hardware.

show abstract

Section: Implementations Of Bioinspired Hardware Using Spintronicsmentioning

confidence: 99%

Spintronic Nanodevices for Bioinspired Computing

2016

View full text Add to dashboard Cite

show abstract

“…Because of this impasse, there has recently been increasing interest in applying magnetic switches for non-Boolean applications such as in Bayesian inference engines [16,17], restricted Boltzmann machines [18], image processing [19,20], computer vision [21], neural networks [22,23], analog-to-digital converters [24], and probabilistic computing [25,26]. These applications can tolerate much larger error probabilities than Boolean logic or memory can.…”

Section: Introductionmentioning

confidence: 99%

Low Energy Barrier Nanomagnet Design for Binary Stochastic Neurons: Design Challenges for Real Nanomagnets With Fabrication Defects

Abeed

Bandyopadhyay

2019

IEEE Magn. Lett.

View full text Add to dashboard Cite

Much attention has been focused on the design of low barrier nanomagnets (LBM), whose magnetizations vary randomly in time owing to thermal noise, for use in binary stochastic neurons (BSN) which are hardware accelerators for machine learning. The performance of BSNs depend on two important parameters: the correlation time c associated with the random magnetization dynamics in a LBM, and the spin-polarized pinning current Ip which stabilizes the magnetization of a LBM in a chosen direction within a chosen time. Here, we show that common fabrication defects in LBMs make these two parameters unpredictable since they are strongly sensitive to the defects. That makes the design of BSNs with real LBMs very challenging. Unless the LBMs are fabricated with extremely tight control, the BSNs which use them could be unreliable or suffer from poor yield.Index Terms-Low barrier magnets, binary stochastic neurons, correlation time, pinning currents, effect of defects.

show abstract

“…We explore three nonBoolean computational framework: (1) Energy minimization based optimizer, which we recently published in Nature Nanotechnology [23], (2) Coupled Oscillatory framework [47] and (3) Neuromorphic learning framework. In Energy minimization framework, we harness the innate physical properties of nanomagnets to directly solve a class of energy minimization problems.…”

Section: Introductionmentioning

confidence: 99%