3 papers
cs.LG2024
Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision
Dinithi Jayasuriya, Nastaran Darabi, Maeesha Binte Hashem +1
We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weight…
cs.AR2024
TimeFloats: Train-in-Memory with Time-Domain Floating-Point Scalar Products
Maeesha Binte Hashem, Benjamin Parpillon, Divake Kumar +2
In this work, we propose "TimeFloats," an efficient train-in-memory architecture that performs 8-bit floating-point scalar product operations in the time domain. While building on…
cs.AR2023
ADC/DAC-Free Analog Acceleration of Deep Neural Networks with Frequency Transformation
Nastaran Darabi, Maeesha Binte Hashem, Hongyi Pan +3
The edge processing of deep neural networks (DNNs) is becoming increasingly important due to its ability to extract valuable information directly at the data source to minimize lat…