Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Gene I Sher"'
Publikováno v:
Jordanian Journal of Computers and Information Technology, Vol 8, Iss 3, Pp 218-231 (2022)
Though substantial advancements have been made in training deep neural networks, one problem remains, the vanishing gradient. The very strength of deep neural networks, their depth, is also unfortunately their problem, due to the difficulty of thorou
Externí odkaz:
https://doaj.org/article/5cb33ef7163a4ad7907397fbb675154a
Autor:
Daniele Loiacono
Publikováno v:
Genetic Programming and Evolvable Machines. 15:109-110
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0dfcea6141e04c9727211744d3a8bcbe
https://doi.org/10.1007/s10710-013-9197-6
https://doi.org/10.1007/s10710-013-9197-6
Publikováno v:
BMC Genomics
BMC Genomics, Vol 18, Iss S6, Pp 55-65 (2017)
BMC Genomics, Vol 18, Iss S6, Pp 55-65 (2017)
Introduction The ability to predict epitopes plays an enormous role in vaccine development in terms of our ability to zero in on where to do a more thorough in-vivo analysis of the protein in question. Though for the past decade there have been numer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8a3c658f4f51ab933c88bb517faeefe
https://pubmed.ncbi.nlm.nih.gov/28984193
https://pubmed.ncbi.nlm.nih.gov/28984193
Autor:
Gene I. Sher
Publikováno v:
GECCO (Companion)
The momentum parameter is common within numerous optimization and local search algorithms, particularly in the popular back propagation neural network learning algorithm. Computationally cheap and prevalent in gradient descent approaches, it is not c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd9a16f6fa35e93257fc87faf0de897f
https://doi.org/10.1145/2739482.2764709
https://doi.org/10.1145/2739482.2764709
Autor:
Gene I. Sher
Handbook of Neuroevolution Through Erlang presents both the theory behind, and the methodology of, developing a neuroevolutionary-based computational intelligence system using Erlang. With a foreword written by Joe Armstrong, this handbook offers a
Preliminary results for neuroevolutionary optimization phase order generation for static compilation
Publikováno v:
ODES@CGO
There is a complex web of interactions between optimization phases in static program compilation. Because there are many different types of optimizations, and each changes the form of the program and can impact the result of subsequent optimizations,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0cc41f61ffd609eecf697cf8deffd032
https://doi.org/10.1145/2568326.2568328
https://doi.org/10.1145/2568326.2568328
Autor:
Gene I. Sher
Publikováno v:
Handbook of Neuroevolution Through Erlang ISBN: 9781461444626
The programming language Erlang has a perfect 1:1 mapping to the problem domain of developing neural network computational intelligence based systems. Erlang was created to develop distributed, process based, message passing paradigm oriented, robust
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::573d217ac2dc838ab17c4f176bbee69c
https://doi.org/10.1007/978-1-4614-4463-3_5
https://doi.org/10.1007/978-1-4614-4463-3_5
Autor:
Gene I. Sher
Publikováno v:
Handbook of Neuroevolution Through Erlang ISBN: 9781461444626
In this chapter we discuss the functionality of an optimization method called the Stochastic Hill Climber, and the Stochastic Hill Climber With Random Restarts. We then implement this optimization algorithm, allowing the exoself process to train and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f6dac2cea76f452e1b03ed49dc4b198
https://doi.org/10.1007/978-1-4614-4463-3_7
https://doi.org/10.1007/978-1-4614-4463-3_7
Autor:
Gene I. Sher
Publikováno v:
Handbook of Neuroevolution Through Erlang ISBN: 9781461444626
To test the performance of a neuroevolutionary system after adding a new feature, or in general when trying to assess its abilities, it is important to have some standardized benchmarking problems. In this chapter we create two such benchmarking prob
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::98259ad0d87f1a726a428b8af9159e2c
https://doi.org/10.1007/978-1-4614-4463-3_14
https://doi.org/10.1007/978-1-4614-4463-3_14