Results 61 to 70 of about 3,274,646 (190)

An unsupervised dual-network connectionist model of rule emergence in category learning [PDF]

, 2007
We develop an unsupervised dual-network connectionist model of category learning in which rules gradually emerge from a standard Kohonen network. The architecture is based on the interaction of a statistical-learning (Kohonen) network and a competitive ...
Cowell, Rosemary A., French, Robert M.
core  

Variational Connectionist Temporal Classification for Order-Preserving Sequence Modeling [PDF]

, 2023
Connectionist temporal classification (CTC) is commonly adopted for sequence modeling tasks like speech recognition, where it is necessary to preserve order between the input and target sequences.
Ahmed, Beena, Nan, Zheng, Dang, Ting, Sethu, Vidhyasaharan   +3 more
core   +1 more source

Soft Active Electromyography Interface for Machine Learning‐Enabled Silent Speech Recognition

Advanced Intelligent Systems, Volume 8, Issue 9, September 2026.
A soft, hand‐worn electromyography interface enables intent‐driven silent speech recognition without continuous facial attachment. The device integrates liquid‐metal interconnects, a transparent flexible circuit, and elastomer encapsulation with a fingertip electrode that contacts perioral muscles only on demand.
Yuta Kurotaki, Shusuke Yamakoshi, Reitaro Yoshida, Yutaka Isoda, Tamami Takano, Yuji Isano, Yusuke Miyake, Kentaro Kuribayashi, Hiroki Ota   +8 more
wiley   +1 more source

Graph Connectionist Temporal Classification for Phoneme Recognition

2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
Accepted to the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2025)
Grafé, Henry, Van hamme, hugo
openaire   +5 more sources

Arabic Handwriting Recognition Using Deep Learning: A Comprehensive Review

Iraqi Journal for Computers and Informatics
Arabic handwriting recognition (AHR) remains challenging due to the context-dependent, cursive script that’s affected by diacritic marks, overlapping strokes, and high writer variability.
Enas Munther Altai, Ali Mohammed Sahan
doaj   +1 more source

Bidirectional Representations for Low-Resource Spoken Language Understanding

Applied Sciences, 2023
Speech representation models lack the ability to efficiently store semantic information and require fine tuning to deliver decent performance. In this research, we introduce a transformer encoder–decoder framework with a multiobjective training strategy,
Quentin Meeus, Marie-Francine Moens, Hugo Van hamme   +2 more
doaj   +1 more source

Unveiling Functional Architecture of Human Thalamus: AStereoelectroencephalography Study

MedComm, Volume 7, Issue 9, September 2026.
The human thalamo‐cortical loop underpins complex behavior and is implicated in a wide range of neurological and psychiatric disorders, yet its functional organization remains incompletely understood. Using direct electrical stimulation combined with the human functional connectome, we mapped the functional architecture of the human thalamus and ...
Liankun Ren, Di Wu, Cuiping Xu, Lei Qi, Guangyuan Jin, Xueyuan Wang, Yueyang Cheng, Jialin Du, Siyi Wang, Dongmei Hu, Junliang Ge, Yixi Zheng, Yihe Wang, Huaqiang Zhang, Yang Dai, Hao Yan, Runshi Gao, Ying Gao, Zeyu Zhang, Penghu Wei, Yuping Wang, Philippe Kahane, Fabrice Bartolomei, Tao Yu, Guoguang Zhao   +24 more
wiley   +1 more source

A deep neural network-based automatic mispronunciation detection in Bengali accented English speech

Discover Computing
Learning a second language, especially English, became necessary as globalisation started. One crucial component of language learning resources is computer-assisted pronunciation training, or CAPT.
Puja Bharati, Sabyasachi Chandra, Aniket Aitawade, Debolina Pramanik, Satya Prasad Gaddamedi, Shyamal Kumar Das Mandal   +5 more
doaj   +1 more source

Design of recognition algorithm for multiclass digital display instrument based on convolution neural network

Biomimetic Intelligence and Robotics, 2023
Digital display instrument identification is a crucial approach for automating the collection of digital display data. In this study, we propose a digital display area detection CTPNpro algorithm to address the problem of recognizing multiclass digital ...
Xuanzhang Wen, Yuxia Wang, Qiuguo Zhu, Jun Wu, Rong Xiong, Anhuan Xie   +5 more
doaj   +1 more source

Information Dynamics and Learning in Complex Adaptive Systems: Toward a Transdisciplinary Framework

Systems Research and Behavioral Science, Volume 43, Issue 4, Page 1344-1363, July/August 2026.
ABSTRACT This article develops a framework for understanding learning and adaptation in complex adaptive systems. Drawing from neuroscience, systems theory, information theory and quantum field theory, it examines how information processing, plasticity and systemic coherence emerge from distributed, nonlinear and feedback‐driven interactions. It argues
Anderson de Souza Sant'Anna
wiley   +1 more source