English
Related papers

Related papers: Machine learning using magnetic stochastic synapse…

200 papers

This paper presents a physics-informed neural network approach for dynamic modeling of saturable synchronous machines, including cases with spatial harmonics. We introduce an architecture that incorporates gradient networks directly into…

Systems and Control · Electrical Eng. & Systems 2026-02-17 Junyi Li , Tim Foissner , Floran Martin , Antti Piippo , Marko Hinkkanen

The use of analog resistance states for storing weights in neuromorphic systems is impeded by fabrication imprecision and device stochasticity that limit the precision of synapse weights. This challenge can be resolved by emulating analog…

Neural and Evolutionary Computing · Computer Science 2021-12-13 Peng Zhou , Julie A. Smith , Laura Deremo , Stephen K. Heinrich-Barna , Joseph S. Friedman

Thermodynamic-driven filament formation in redox-based resistive memory and the impact of thermal fluctuations on switching probability of emerging magnetic switches are probabilistic phenomena in nature, and thus, processes of binary…

Other Condensed Matter · Physics 2013-10-21 Omid Kavehei , Efstratios Skafidas

Binary stochastic neurons (BSNs) are excellent activators for machine learning. An ideal platform for implementing them are low- or zero-energy-barrier nanomagnets (LBMs) possessing in-plane anisotropy (e.g. circular or slightly elliptical…

Mesoscale and Nanoscale Physics · Physics 2023-02-28 Rahnuma Rahman , Supriyo Bandyopadhyay

Stochastic binary hidden units in a multi-layer perceptron (MLP) network give at least three potential benefits when compared to deterministic MLP networks. (1) They allow to learn one-to-many type of mappings. (2) They can be used in…

Machine Learning · Statistics 2015-04-10 Tapani Raiko , Mathias Berglund , Guillaume Alain , Laurent Dinh

An energy-efficient voltage controlled domain wall device for implementing an artificial neuron and synapse is analyzed using micromagnetic modeling in the presence of room temperature thermal noise. By controlling the domain wall motion…

Mesoscale and Nanoscale Physics · Physics 2020-03-31 Md Ali Azam , Dhritiman Bhattacharya , Damien Querlioz , Caroline A. Ross , Jayasimha Atulasimha

The brain modifies its synaptic strengths during learning in order to better adapt to its environment. However, the underlying plasticity rules that govern learning are unknown. Many proposals have been suggested, including Hebbian…

Neurons and Cognition · Quantitative Biology 2020-12-09 Aran Nayebi , Sanjana Srivastava , Surya Ganguli , Daniel L. K. Yamins

Understanding how the brain learns to compute functions reliably, efficiently and robustly with noisy spiking activity is a fundamental challenge in neuroscience. Most sensory and motor tasks can be described as dynamical systems and could…

Neurons and Cognition · Quantitative Biology 2017-05-24 Sophie Denève , Alireza Alemi , Ralph Bourdoukan

In the presence of system-environment coupling, classical complex systems undergo stochastic dynamics, where rich phenomena can emerge at large spatio-temporal scales. To investigate these phenomena, numerical approaches for simulating…

Statistical Mechanics · Physics 2024-03-15 Pei-Fang Wu , Wei-Chen Guo , Liang He

With the rapid development of artificial intelligence in recent years, mankind is facing an unprecedented demand for data processing. Today, almost all data processing is performed using electrons in conventional complementary…

Applied Physics · Physics 2023-11-13 Qi Wang , Gyorgy Csaba , Roman Verba , Andrii V. Chumak , Philipp Pirro

As neural computation is revolutionizing the field of Artificial Intelligence (AI), rethinking the ideal neural hardware is becoming the next frontier. Fast and reliable von Neumann architecture has been the hosting platform for neural…

Neural and Evolutionary Computing · Computer Science 2024-12-31 Yigit Demirag

Spiking neural networks (SNNs) possess energy-efficient potential due to event-based computation. However, supervised training of SNNs remains a challenge as spike activities are non-differentiable. Previous SNNs training methods can be…

Neural and Evolutionary Computing · Computer Science 2019-10-08 Yunzhe Hao , Xuhui Huang , Meng Dong , Bo Xu

Neuromorphic computing, inspired by the brain, promises extreme efficiency for certain classes of learning tasks, such as classification and pattern recognition. The performance and power consumption of neuromorphic computing depends…

Emerging Technologies · Computer Science 2018-06-14 Baibhab Chatterjee , Priyadarshini Panda , Shovan Maity , Ayan Biswas , Kaushik Roy , Shreyas Sen

Stochastic neural networks are a prototypical computational device able to build a probabilistic representation of an ensemble of external stimuli. Building on the relationship between inference and learning, we derive a synaptic plasticity…

Disordered Systems and Neural Networks · Physics 2018-10-23 Luca Saglietti , Federica Gerace , Alessandro Ingrosso , Carlo Baldassi , Riccardo Zecchina

We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of…

Machine Learning · Computer Science 2020-04-02 Sirui Xie , Hehui Zheng , Chunxiao Liu , Liang Lin

We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Tiffany Vlaar , Timothée Pouchon , Amos Storkey

Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be…

Machine Learning · Computer Science 2019-12-24 Sébastien Henwood , François Leduc-Primeau , Yvon Savaria

Physical computing has the potential to enable widespread embodied intelligence by leveraging the intrinsic dynamics of complex systems for efficient sensing, processing, and interaction. While individual devices provide basic data…

Non-Boolean computing based on emerging post-CMOS technologies can potentially pave the way for low-power neural computing platforms. However, existing work on such emerging neuromorphic architectures have either focused on solely mimicking…

Emerging Technologies · Computer Science 2016-11-15 Abhronil Sengupta , Yong Shim , Kaushik Roy

This paper introduces novel alternate training procedures for hard-parameter sharing Multi-Task Neural Networks (MTNNs). Traditional MTNN training faces challenges in managing conflicting loss gradients, often yielding sub-optimal…

Machine Learning · Computer Science 2025-05-20 Stefania Bellavia , Francesco Della Santa , Alessandra Papini