3 papers
cs.ET2026
XBTorch: A Unified Framework for Modeling and Co-Design of Crossbar-Based Deep Learning Accelerators
Osama Yousuf, Andreu L. Glasmann, Martin Lueker-Boden +2
Emerging memory technologies have gained significant attention as a promising pathway to overcome the limitations of conventional computing architectures in deep learning applicati…
cs.ET2024
Measurement-driven neural-network training for integrated magnetic tunnel junction arrays
William A. Borders, Advait Madhavan, Matthew W. Daniels +7
The increasing scale of neural networks needed to support more complex applications has led to an increasing requirement for area- and energy-efficient hardware. One route to meeti…
cs.ET2024
Layer Ensemble Averaging for Improving Memristor-Based Artificial Neural Network Performance
Osama Yousuf, Brian Hoskins, Karthick Ramu +8
Artificial neural networks have advanced due to scaling dimensions, but conventional computing faces inefficiency due to the von Neumann bottleneck. In-memory computation architect…