3 papers
cs.ET2020
A Device Non-Ideality Resilient Approach for Mapping Neural Networks to Crossbar Arrays
Arman Kazemi, Cristobal Alessandri, Alan C. Seabaugh +3
We propose a technology-independent method, referred to as adjacent connection matrix (ACM), to efficiently map signed weight matrices to non-negative crossbar arrays. When compare…
cs.ET2020
A Hybrid FeMFET-CMOS Analog Synapse Circuit for Neural Network Training and Inference
Arman Kazemi, Ramin Rajaei, Kai Ni +3
An analog synapse circuit based on ferroelectric-metal field-effect transistors is proposed, that offers 6-bit weight precision. The circuit is comprised of volatile least signific…
cs.LG2020
Performance Analysis of Semi-supervised Learning in the Small-data Regime using VAEs
Varun Mannam, Arman Kazemi
Extracting large amounts of data from biological samples is not feasible due to radiation issues, and image processing in the small-data regime is one of the critical challenges wh…