Results 1 to 10 of about 2,749 (228)

ESRU: Extremely Low-Bit and Hardware-Efficient Stochastic Rounding Unit Design for Low-Bit DNN Training

2023
exaly  

Dynamic point stochastic rounding algorithm for limited precision arithmetic in Deep Belief Network training

2017
Tong Boon Tang, Eric Tatt Wei Ho
exaly  

Optimising Resource Use Through Low‐Precision Feature Selection: A Performance Analysis of Logarithmic Division and Stochastic Rounding

Expert Systems
Laura Moran-Fernandez, Veronica Bolón-Canedo, Samuel Suárez-Marcote   +2 more
exaly  

LowGradQ: Adaptive Gradient Quantization for Low-Bit CNN Training via Kernel Density Estimation-Guided Thresholding and Hardware-Efficient Stochastic Rounding Unit

Hyun Kim
exaly  

Stochastic Model Correction for the Adaptive Vibration Isolation Round-Robin Challenge

Rileigh Bandy, Teresa Portone, Rebecca Morrison   +2 more
openaire   +1 more source

Stochastic rounding: implementation, error analysis and applications [PDF]

Royal Society Open Science, 2022
Stochastic rounding (SR) randomly maps a real number x to one of the two nearest values in a finite precision number system. The probability of choosing either of these two numbers is 1 minus their relative distance to x.
Matteo Croci, Massimiliano Fasi, Nicholas J. Higham, Theo Mary, Mantas Mikaitis   +4 more
doaj   +9 more sources

Stochastic Rounding and Its Probabilistic Backward Error Analysis [PDF]

SIAM Journal of Scientific Computing, 2021
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Nicholas Higham, Theo Mary
exaly   +4 more sources

Stochastic Rounding: Algorithms and Hardware Accelerator [PDF]

2021 International Joint Conference on Neural Networks (IJCNN), 2021
Algorithms and a hardware accelerator for performing stochastic rounding (SR) are presented. The main goal is to augment the ARM M4F based multi-core processor SpiNNaker2 with a more flexible rounding functionality than is available in the ARM processor itself.
Mantas Mikaitis
exaly   +4 more sources

Stochastic Rounding Variance and Probabilistic Bounds: A New Approach

SIAM Journal of Scientific Computing, 2023
Stochastic rounding (SR) offers an alternative to the deterministic IEEE-754 floating-point rounding modes. In some applications such as PDEs, ODEs and neural networks, SR empirically improves the numerical behavior and convergence to accurate solutions while no sound theoretical background has been provided.
El-Mehdi El Arar, Eric Petit
exaly   +5 more sources

Implementation of a Low-Cost Navigation System Using Data Fusion of a Micro-Electro-Mechanical System Inertial Sensor and an Ultra Short Baseline on a Microcontroller [PDF]

Sensors
In this work, a low-cost low-power navigation solution for autonomous underwater vehicles is introduced utilizing a Micro-Electro-Mechanical System (MEMS) inertial sensor and an ultra short baseline (USBL) system.
Julian Winkler, Sabah Badri-Hoeher
doaj   +2 more sources