Výsledky vyhledávání

Report

Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency

Autor: Gopal, Bhavna, Yang, Huanrui, Zhang, Jingyang, Horton, Mark, Chen, Yiran

Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an innovative approach that mitigates adversarial overfitting by introducing

Externí odkaz: http://arxiv.org/abs/2408.10204

Zobrazit plný text záznamu

Akademický článek

Viscosity Measurements on Colloidal Dispersions (Nanofluids) for Heat Transfer Applications

Publikováno v: Applied Rheology, Vol 20, Iss 4 (2010)

This article reports viscosity data on a series of colloidal dispersions collected as part of the International Nanofluid Property Benchmark Exercise (INPBE). Data are reported for seven different fluids that include dispersions of metal-oxide nanopa

Externí odkaz: https://doaj.org/article/3e13e60c01d240a99a400a8b3dcc7e49

Zobrazit plný text záznamu

Report

On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning

Autor: Prakash, Bharat, Horton, Mark, Waytowich, Nicholas R., Hairston, William David, Oates, Tim, Mohsenin, Tinoosh

In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning agents from high dimensional image representations can be very expensive

Externí odkaz: http://arxiv.org/abs/1903.10404

Zobrazit plný text záznamu