A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence
[article]
2022
arXiv
pre-print
Preserved Fulltext
Other Versions
Using joint optimization of both directions, the proposed model is able to learn upscaling and downscaling simultaneously and achieve bidirectional arbitrary image rescaling. ...
This robustness is beneficial for image rescaling in the wild when this cycle could be applied to one image for multiple times. ...
in arbitrary image rescaling via joint optimization. • A proxy objective that optimize both reconstruction accuracy and idempotence is investigated, and a newly proposed cycle idempotence test is conducted ...
arXiv:2203.00911v2
fatcat:taln5p5jqfbgfklrijlek5huhq
Statistical Methods and Models for Video-Based Tracking, Modeling, and Recognition
2009
Foundations and Trends® in Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2012; you can also visit the original URL.
The file type is application/pdf.
His books explore the use of group theoretical methods [106] and statistical optimization [107] in image understanding and computer vision. ...
Kanatani pioneered statistical optimization under the constraints unique to vision problems. ...
The third author wishes to thank the members of the imaging group at MERL for their support. ...
doi:10.1561/2000000007
fatcat:o5hmdnzbqvbdzjdu72jkojl5ya
25th Annual Computational Neuroscience Meeting: CNS-2016
2016
BMC Neuroscience
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Such classification scheme could augment classification schemes based on molecular, anatomical, and electrophysiological properties. ...
I will discuss theoretical results that point to functional advantages of splitting neural populations into subtypes, both in feedforward and recurrent networks. ...
Allen and Jody Allen, for their vision, encouragement and support. ...
doi:10.1186/s12868-016-0283-6
pmid:27534393
pmcid:PMC5001212
fatcat:bt45etzj2bbolfcxlxo7hlv6ju
Machine learning with neural networks
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Lecture notes for my course on machine learning with neural networks that I have given at Gothenburg University and Chalmers Technical University in Gothenburg, Sweden. ...
Using experience in this way allows the algorithm to simultaneously improve its policy and the Q -values towards optimality. ...
The norm of the weight vector, in particular, is arbitrary. ...
arXiv:1901.05639v3
fatcat:pyyiywuoxzds5kyc6ohqtqtd3e
Diversity-Promoting and Large-Scale Machine Learning for Healthcare
2019
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In the former, we develop diversity-promoting regularizers that are empirically effective, theoretically analyzable, and computationally efficient, and proposea rich set of optimization algorithms to solve ...
In healthcare, a tsunami of medical data has emerged, including electronic healthrecords, images, literature, etc. ...
Teng and Zhang [330] extended the unidirectional tree LSTM to a bidirectional one. Xie and Xing [368] proposed a sequence-of-trees LSTM network to model a passage. ...
doi:10.1184/r1/7553468
fatcat:ac5ifp2lnzbk3hcupr2rszxj2m