Results 11 to 20 of about 7,775,419 (309)

Conformer: Convolution-augmented Transformer for Speech Recognition [PDF]

Interspeech, 2020
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).
Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, Ruoming Pang   +10 more
semanticscholar   +1 more source

An fMRI Dataset for Concept Representation with Semantic Feature Annotations

Scientific Data, 2022
The neural representation of concepts is a focus of many cognitive neuroscience studies. Prior works studying concept representation with neural imaging data have been largely limited to concrete concepts. The use of relatively small and constrained sets
Shaonan Wang, Yunhao Zhang, Xiaohan Zhang, Jingyuan Sun, Nan Lin, Jiajun Zhang, Chengqing Zong   +6 more
doaj   +1 more source

Neural Architectures for Named Entity Recognition [PDF]

North American Chapter of the Association for Computational Linguistics, 2016
Comunicacio presentada a la 2016 Conference of the North American Chapter of the Association for Computational Linguistics, celebrada a San Diego (CA, EUA) els dies 12 a 17 de juny 2016.
Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer   +4 more
semanticscholar   +1 more source

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition [PDF]

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224$\times$ 224) input image. This requirement is “artificial” and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale.
Kaiming He, X. Zhang, Shaoqing Ren, Jian Sun   +3 more
semanticscholar   +1 more source

A synchronized multimodal neuroimaging dataset for studying brain language processing

Scientific Data, 2022
Measurement(s) functional brain measurement • Magnetoencephalography Technology Type(s) Functional Magnetic Resonance Imaging • Magnetoencephalography Factor Type(s) naturalistic stimuli listening Sample Characteristic - Organism ...
Shaonan Wang, Xiaohan Zhang, Jiajun Zhang, Chengqing Zong   +3 more
doaj   +1 more source

DeepTRIAGE: interpretable and individualised biomarker scores using attention mechanism for the classification of breast cancer sub-types

BMC Medical Genomics, 2020
Background Breast cancer is a collection of multiple tissue pathologies, each with a distinct molecular signature that correlates with patient prognosis and response to therapy.
Adham Beykikhoshk, Thomas P. Quinn, Samuel C. Lee, Truyen Tran, Svetha Venkatesh   +4 more
doaj   +1 more source

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition [PDF]

Interspeech, 2019
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients).
Daniel S. Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, E. D. Cubuk, Quoc V. Le   +6 more
semanticscholar   +1 more source

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

Sensors, 2021
Motor imagery (MI) promotes motor learning and encourages brain–computer interface systems that entail electroencephalogram (EEG) decoding. However, a long period of training is required to master brain rhythms’ self-regulation, resulting in users with ...
Diego Fabian Collazos-Huertas, Luisa Fernanda Velasquez-Martinez, Hernan Dario Perez-Nastar, Andres Marino Alvarez-Meza, German Castellanos-Dominguez   +4 more
doaj   +1 more source

Long-term recurrent convolutional networks for visual recognition and description [PDF]

Computer Vision and Pattern Recognition, 2014
Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or “temporally deep”, are effective for tasks involving sequences, visual and otherwise.
Jeff Donahue, Lisa Anne Hendricks, Marcus Rohrbach, Subhashini Venugopalan, S. Guadarrama, Kate Saenko, Trevor Darrell   +6 more
semanticscholar   +1 more source

Deep learning-based patient re-identification is able to exploit the biometric nature of medical chest X-ray data

Scientific Reports, 2022
With the rise and ever-increasing potential of deep learning techniques in recent years, publicly available medical datasets became a key factor to enable reproducible development of diagnostic algorithms in the medical domain.
Kai Packhäuser, Sebastian Gündel, Nicolas Münster, Christopher Syben, Vincent Christlein, Andreas Maier   +5 more
doaj   +1 more source