I
Iuri Frosio
Researcher at Nvidia
Publications - 89
Citations - 4213
Iuri Frosio is an academic researcher from Nvidia. The author has contributed to research in topics: Image processing & Artificial neural network. The author has an hindex of 23, co-authored 87 publications receiving 2918 citations. Previous affiliations of Iuri Frosio include Instituto Politécnico Nacional & University of Milan.
Papers
More filters
Journal ArticleDOI
Loss Functions for Image Restoration With Neural Networks
TL;DR: It is shown that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged, and a novel, differentiable error function is proposed.
Proceedings ArticleDOI
Importance Estimation for Neural Network Pruning
TL;DR: A novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores and two variations of this method using the first and second-order Taylor expansions to approximate a filter's contribution are described.
Posted Content
Loss Functions for Neural Networks for Image Processing
TL;DR: It is shown that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged, and a novel, differentiable error function is proposed.
Journal ArticleDOI
Autocalibration of MEMS Accelerometers
TL;DR: A novel procedure for the on-the-field autocalibration of triaxial micro accelerometers, which requires neither any equipment nor a controlled environment and allows increasing the accuracy of this kind of microsensor.
Proceedings Article
Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
TL;DR: In this article, a hybrid CPU/GPU version of the Asynchronous Advantage Actor-Critic (A3C) algorithm is introduced, which achieves a significant speed up compared to a CPU implementation.