English
Related papers

Related papers: SOT-MRAM-Enabled Probabilistic Binary Neural Netwo…

200 papers

Differentiable logic gate networks (DLGNs) learn compact, interpretable Boolean circuits via gradient-based training, but all existing variants are restricted to the 16 two-input binary gates. Extending DLGNs to Ternary Kleene $K_3$ logic…

Machine Learning · Computer Science 2026-03-03 Sai Sandeep Damera , Ryan Matheu , Aniruddh G. Puranic , John S. Baras

Stochastic neurons are extremely efficient hardware for solving a large class of problems and usually come in two varieties -- "binary" where the neuronal statevaries randomly between two values of -1, +1 and "analog" where the neuronal…

Mesoscale and Nanoscale Physics · Physics 2025-02-03 Rahnuma Rahman , Supriyo Bandyopadhyay

State-of-the-Art (SotA) hardware implementations of Deep Neural Networks (DNNs) incur high latencies and costs. Binary Neural Networks (BNNs) are potential alternative solutions to realize faster implementations without losing accuracy. In…

Hardware Architecture · Computer Science 2024-02-01 Taha Shahroodi , Raphael Cardoso , Stephan Wong , Alberto Bosio , Ian O'Connor , Said Hamdioui

Memristor-based Spiking Neural Networks (SNNs) with temporal spike encoding enable ultra-low-energy computation, making them ideal for battery-powered intelligent devices. This paper presents a circuit-level memristive spiking neural…

Emerging Technologies · Computer Science 2025-07-29 Santlal Prajapati , Susmita Sur-Kolay , Soumyadeep Dutta

We report the possibility of achieving an order of magnitude reduction in the energy dissipation needed to write bits in perpendicular magnetic tunnel junctions (p-MTJs) by simulating the magnetization dynamics under a combination of…

Mesoscale and Nanoscale Physics · Physics 2019-10-02 Austin Roe , Dhritiman Bhattacharya , Jayasimha Atulasimha

A new device structure for spin transfer torque based magnetic random access memory is proposed for on-chip memory applications. Our device structure exploits spin Hall effect to create a differential memory cell that exhibits fast and…

Mesoscale and Nanoscale Physics · Physics 2014-02-12 Yusung Kim , Sri Harsha Choday , Kaushik Roy

Neural networks span a wide range of applications of industrial and commercial significance. Binary neural networks (BNN) are particularly effective in trading accuracy for performance, energy efficiency or hardware/software complexity.…

It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of deep networks. Some works attempted to artificially simulate…

Machine Learning · Computer Science 2022-08-31 Zeke Xie , Li Yuan , Zhanxing Zhu , Masashi Sugiyama

Spin orbit torque (SOT) provides an efficient way of generating spin current that promises to significantly reduce the current required for switching nanomagnets. However, an in-plane current generated SOT cannot deterministically switch a…

Efficient generation of spin-orbit torques (SOTs) is central for the exciting field of spin-orbitronics. Platinum, the archetypal spin Hall material, has the potential to be an outstanding provider for spin-orbit torques due to its giant…

Mesoscale and Nanoscale Physics · Physics 2021-08-17 Lijun Zhu , Daniel C. Ralph , Robert A Buhrman

Magnetization reversal of a perpendicular ferromagnetic free layer by spin-orbit torque (SOT) is an attractive alternative to spin-transfer torque (STT) switching in magnetic random-access memory (MRAM) where the write process involves…

Mesoscale and Nanoscale Physics · Physics 2015-11-19 Yong-Chang Lau , Davide Betto , Karsten Rode , JMD Coey , Plamen Stamenov

Verification of binary neural network (BNN) robustness is NP-hard, as it can be formulated as a combinatorial search for an adversarial perturbation that induces misclassification. Exact verification methods therefore scale poorly with…

Emerging Technologies · Computer Science 2026-03-09 Madhav Vadlamani , Rahul Singh , Yuyao Kong , Zheng Zhang , Shimeng Yu

Efficient inference of Deep Neural Networks (DNNs) on resource-constrained edge devices is essential. Quantization and sparsity are key techniques that translate to repetition and sparsity within tensors at the hardware-software interface.…

Machine Learning · Computer Science 2025-05-07 Sachit Kuhar , Yash Jain , Alexey Tumanov

Current-induced spin-orbit torque (SOT) has emerged as a promising method for achieving energy-efficient magnetization switching in advanced spintronic devices. However, technological advancement has been inadequate because an external…

Mesoscale and Nanoscale Physics · Physics 2025-01-23 Badsha Sekh , Hasibur Rahaman , Ramu Maddu , Pinkesh Kumar Mishra , Tianli Jin , S. N. Piramanayagam

Spiking Neural Networks (SNNs) can do inference with low power consumption due to their spike sparsity. ANN-SNN conversion is an efficient way to achieve deep SNNs by converting well-trained Artificial Neural Networks (ANNs). However, the…

Neural and Evolutionary Computing · Computer Science 2023-03-24 Xiang He , Yang Li , Dongcheng Zhao , Qingqun Kong , Yi Zeng

Neuromorphic computing (NC) architecture has shown its suitability for energy-efficient computation. Amongst several systems, spin-orbit torque (SOT) based domain wall (DW) devices are one of the most energy-efficient contenders for NC. To…

Mesoscale and Nanoscale Physics · Physics 2022-12-16 Durgesh Kumar , Ramu Maddu , Hong Jing Chung , Hasibur Rahaman , Tianli Jin , Sabpreet Bhatti , Sze Ter Lim , Rachid Sbiaa , S. N. Piramanayagam

This paper proposes a new algorithm based on multi-scale stochastic local search with binary representation for training neural networks. In particular, we study the effects of neighborhood evaluation strategies, the effect of the number of…

Neural and Evolutionary Computing · Computer Science 2016-11-17 Mauro Brunato , Roberto Battiti

By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward…

Machine Learning · Computer Science 2023-04-11 Yang Zhao , Hao Zhang , Xiuyuan Hu

The performance and efficiency of running large-scale datasets on traditional computing systems exhibit critical bottlenecks due to the existing "power wall" and "memory wall" problems. To resolve those problems, processing-in-memory (PIM)…

Hardware Architecture · Computer Science 2022-04-22 Yinglin Zhao , Jianlei Yang , Bing Li , Xingzhou Cheng , Xucheng Ye , Xueyan Wang , Xiaotao Jia , Zhaohao Wang , Youguang Zhang , Weisheng Zhao

As artificial intelligence (AI) advances into diverse applications, ensuring reliability of AI models is increasingly critical. Conventional neural networks offer strong predictive capabilities but produce deterministic outputs without…

‹ Prev 1 8 9 10 Next ›