Zobrazeno 1 - 10
of 268
pro vyhledávání: '"SRIHARI, SARGUR N."'
EEG decoding systems based on deep neural networks have been widely used in decision making of brain computer interfaces (BCI). Their predictions, however, can be unreliable given the significant variance and noise in EEG signals. Previous works on E
Externí odkaz:
http://arxiv.org/abs/2201.00627
In clinical applications, neural networks must focus on and highlight the most important parts of an input image. Soft-Attention mechanism enables a neural network toachieve this goal. This paper investigates the effectiveness of Soft-Attention in de
Externí odkaz:
http://arxiv.org/abs/2105.03358
Deep learning system have drawback that their output is not accompanied with ex-planation. In a domain such as forensic handwriting verification it is essential to provideexplanation to jurors. The goal of handwriting verification is to find a measur
Externí odkaz:
http://arxiv.org/abs/1909.02548
Publikováno v:
In Neurocomputing 14 June 2023 538
Current state-of-the-art nonparametric Bayesian text clustering methods model documents through multinomial distribution on bags of words. Although these methods can effectively utilize the word burstiness representation of documents and achieve dece
Externí odkaz:
http://arxiv.org/abs/1811.12500
Autor:
Srihari, Sargur N.
Publikováno v:
Journal of the Washington Academy of Sciences, 2020 Dec 01. 106(4), 9-38.
Externí odkaz:
https://www.jstor.org/stable/27130153
Recognition of handwritten words continues to be an important problem in document analysis and recognition. Existing approaches extract hand-engineered features from word images--which can perform poorly with new data sets. Recently, deep learning ha
Externí odkaz:
http://arxiv.org/abs/1612.01072
Visual restoration and recognition are traditionally addressed in pipeline fashion, i.e. denoising followed by classification. Instead, observing correlations between the two tasks, for example clearer image will lead to better categorization and vic
Externí odkaz:
http://arxiv.org/abs/1612.01075
Autor:
Chen, Gang, Srihari, Sargur N.
Multimodal learning with deep Boltzmann machines (DBMs) is an generative approach to fuse multimodal inputs, and can learn the shared representation via Contrastive Divergence (CD) for classification and information retrieval tasks. However, it is a
Externí odkaz:
http://arxiv.org/abs/1503.07906