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---<...
Glavni avtor: | Band, N |
---|---|
Drugi avtorji: | Kalaitzis, A |
Format: | Thesis |
Jezik: | English |
Izdano: |
2022
|
Teme: |
Podobne knjige/članki
-
A Comprehensive Review on Fake News Detection With Deep Learning
od: M. F. Mridha, et al.
Izdano: (2021-01-01) -
Deep Learning Approach for Predicting Psychodiagnosis
od: Zouaoui Samia, et al.
Izdano: (2024-08-01) -
Deep Learning Applications /
od: Mazzeo, Pier Luigi, editor, et al.
Izdano: (2021) -
Learning Non-Parametric Surrogate Losses With Correlated Gradients
od: Seungdong Yoa, et al.
Izdano: (2021-01-01) -
Urdu Sentiment Analysis With Deep Learning Methods
od: Lal Khan, et al.
Izdano: (2021-01-01)