Non-parametric deep learning with applications in active learning
<p>We challenge a common assumption underlying most supervised <i>deep learning</i>: that a model makes a prediction depending only on its parameters and the features of a <i>single input</i>. To this end, we introduce a general-purpose deep learning architecture---<...
Главный автор: | Band, N |
---|---|
Другие авторы: | Kalaitzis, A |
Формат: | Диссертация |
Язык: | English |
Опубликовано: |
2022
|
Предметы: |
Схожие документы
-
A Comprehensive Review on Fake News Detection With Deep Learning
по: M. F. Mridha, и др.
Опубликовано: (2021-01-01) -
Deep Learning Approach for Predicting Psychodiagnosis
по: Zouaoui Samia, и др.
Опубликовано: (2024-08-01) -
Deep Learning Applications /
по: Mazzeo, Pier Luigi, editor, и др.
Опубликовано: (2021) -
Learning Non-Parametric Surrogate Losses With Correlated Gradients
по: Seungdong Yoa, и др.
Опубликовано: (2021-01-01) -
Urdu Sentiment Analysis With Deep Learning Methods
по: Lal Khan, и др.
Опубликовано: (2021-01-01)