Zobrazeno 1 - 10
of 289
pro vyhledávání: '"Cherkassky, Vladimir"'
Autor:
Cherkassky, Vladimir, Lee, Eng Hock
Large Language Models (LLMs) are known for their remarkable ability to generate synthesized 'knowledge', such as text documents, music, images, etc. However, there is a huge gap between LLM's and human capabilities for understanding abstract concepts
Externí odkaz:
http://arxiv.org/abs/2408.06598
Autor:
Lee, Eng Hock, Cherkassky, Vladimir
There has been growing interest in generalization performance of large multilayer neural networks that can be trained to achieve zero training error, while generalizing well on test data. This regime is known as 'second descent' and it appears to con
Externí odkaz:
http://arxiv.org/abs/2205.15549
Autor:
Cherkassky, Vladimir, Lee, Eng Hock
Publikováno v:
In Neural Networks January 2024 169:242-256
Autor:
Dhar, Sauptik, Cherkassky, Vladimir
This paper extends the idea of Universum learning [1, 2] to single-class learning problems. We propose Single Class Universum-SVM setting that incorporates a priori knowledge (in the form of additional data samples) into the single class estimation p
Externí odkaz:
http://arxiv.org/abs/1909.09862
We introduce Universum learning for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We also propose an analytic span bound for model selection with almost 2-4x faster computation times than standard resampli
Externí odkaz:
http://arxiv.org/abs/1808.08111
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We introduce Universum learning for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We also propose a span bound for MU-SVM that can be used for model selection thereby avoiding resampling. Empirical results
Externí odkaz:
http://arxiv.org/abs/1609.09162
Autor:
Dhar, Sauptik, Cherkassky, Vladimir
This paper extends the idea of Universum learning [18, 19] to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowledge in the form of additional data samples. These additional data sam
Externí odkaz:
http://arxiv.org/abs/1605.08497
Autor:
Chen, Hsiang-Han, Cherkassky, Vladimir
Publikováno v:
In Neural Networks August 2020 128:22-32