Zobrazeno 1 - 10
of 163
pro vyhledávání: '"Bart Kosko"'
Autor:
Olaoluwa Adigun, Bart Kosko
Publikováno v:
2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db094a31b1e78f849890da3a25eb00a4
https://doi.org/10.1109/icmla55696.2022.00017
https://doi.org/10.1109/icmla55696.2022.00017
Autor:
Akash Kumar Panda, Bart Kosko
Publikováno v:
2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b786aa194641dc9b28585bdf7c21648
https://doi.org/10.1109/icmla55696.2022.00031
https://doi.org/10.1109/icmla55696.2022.00031
Autor:
Bart Kosko
Publikováno v:
2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::974273fd54070974533f909e01351e8e
https://doi.org/10.1109/fuzz-ieee55066.2022.9882762
https://doi.org/10.1109/fuzz-ieee55066.2022.9882762
Autor:
Bart Kosko
Publikováno v:
IEEE Transactions on Systems, Man, and Cybernetics: Systems. 51:103-115
Bidirectional associative memories (BAMs) pass neural signals forward and backward through the same web of synapses. Earlier BAMs had no hidden neurons and did not use supervised learning. They tuned their synaptic weights with unsupervised Hebbian o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a6790b901594ee1c3e064661b85a3f9
https://doi.org/10.1109/tsmc.2020.3043249
https://doi.org/10.1109/tsmc.2020.3043249
Autor:
Olaoluwa Adigun, Bart Kosko
Publikováno v:
IEEE Transactions on Systems, Man, and Cybernetics: Systems. 50:1982-1994
We extend backpropagation (BP) learning from ordinary unidirectional training to bidirectional training of deep multilayer neural networks. This gives a form of backward chaining or inverse inference from an observed network output to a candidate inp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0b45fca55a0bc59088a7b49357307e06
https://doi.org/10.1109/tsmc.2019.2916096
https://doi.org/10.1109/tsmc.2019.2916096
Autor:
Akash Kumar Panda, Bart Kosko
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783030815608
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b4ed6cd2d6c6d403641e6ecd3212d5b4
https://doi.org/10.1007/978-3-030-81561-5_21
https://doi.org/10.1007/978-3-030-81561-5_21
Autor:
Olaoluwa Adigun, Bart Kosko
Publikováno v:
2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5cd94d2d8475c7d34b44932a2cf9cc1c
https://doi.org/10.1109/icmla52953.2021.00118
https://doi.org/10.1109/icmla52953.2021.00118
Autor:
Olaoluwa Adigun, Bart Kosko
Publikováno v:
2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80625ce9149526f8f231d23ab4060eb8
https://doi.org/10.1109/icmla52953.2021.00227
https://doi.org/10.1109/icmla52953.2021.00227
Autor:
Olaoluwa Adigun, Bart Kosko
Publikováno v:
IJCNN
We show that training neural classifiers with Bayesian bidirectional backpropagation improves the performance of the network. Bidirectional backpropagation trains a deep network for both forward and backward recall through the same layers of neurons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3de1f412a72ff29905a09834697995e
https://doi.org/10.1109/ijcnn52387.2021.9533873
https://doi.org/10.1109/ijcnn52387.2021.9533873
Autor:
Akash Kumar Panda, Bart Kosko
Publikováno v:
FUZZ-IEEE
A random rule foam grows and combines several independent fuzzy rule-based systems by randomly sampling input-output data from a trained deep neural classifier. The random rule foam defines an interpretable proxy system for the sampled black-box clas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e513b8be08e41981ee46374ba4d6944d
https://doi.org/10.1109/fuzz45933.2021.9494525
https://doi.org/10.1109/fuzz45933.2021.9494525