Results 71 to 80 of about 3,274,646 (190)

Commonsense knowledge representation and reasoning with fuzzy neural networks [PDF]

, 1996
This paper highlights the theory of common-sense knowledge in terms of representation and reasoning. A connectionist model is proposed for common-sense knowledge representation and reasoning.
Kouzani, Abbas, Sammut, Karl, He, Fangpo
core  

On the Proper Treatment of Dynamics in Cognitive Science

Topics in Cognitive Science, Volume 18, Issue 3, July 2026.
Abstract This essay examines the relevance of dynamical ideas for cognitive science. On its own, the mere mathematical idea of a dynamical system is too weak to serve as a scientific theory of anything, and dynamical approaches within cognitive science are too rich and varied to be subsumed under a single “dynamical hypothesis.” Instead, after first ...
Randall D. Beer
wiley   +1 more source

Discriminative Tandem Features for HMM-based EEG Classification [PDF]

, 2013
We investigate the use of discriminative feature extractors in tandem configuration with generative EEG classification system. Existing studies on dynamic EEG classification typically use hidden Markov models (HMMs) which lack discriminative capability ...
Ting, Chee-Ming, Simon King, A. K. Ariff, Salleh, Sh-Hussain, King, Simon, King, Simon; id_orcid, Chee-Ming Ting, Sh-Hussain Salleh, Ariff, A. K.   +8 more
core   +1 more source

Inter‐Model Feature Fusion for Robust Low‐Resource Speech Recognition

Applied AI Letters, Volume 7, Issue 2, June 2026.
Our Self‐Supervised Feature Fusion (SSF‐FT) method enhances low‐resource speech recognition by adaptively combining features from self‐supervised models trained with Contrastive, Predictive, and Reconstruction objectives. This attention‐weighted ensemble delivers robust performance, particularly in acoustically challenging conditions, extending current
Ussen Kimanuka, Ciira wa Maina, Osman Büyük   +2 more
wiley   +1 more source

Attention-based CNN-ConvLSTM for Handwritten Arabic Word Extraction

ELCVIA Electronic Letters on Computer Vision and Image Analysis, 2022
Word extraction is one of the most critical steps in handwritten recognition systems. It is challenging for many reasons, such as the variability of handwritten writing styles, touching and overlapping characters, skewness problems, diacritics ...
takwa Ben Aicha, Afef Kacem Echi
doaj   +1 more source

Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification

CoRR, 2015
Final version: Kyuyeon Hwang and Wonyong Sung, "Sequence to Sequence Training of CTC-RNNs with Partial Windowing," Proceedings of The 33rd International Conference on Machine Learning, pp. 2178-2187, 2016.
Kyuyeon Hwang, Wonyong Sung
openaire   +3 more sources

Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification [PDF]

Interspeech 2017, 2017
Connectionist temporal classification (CTC) is a powerful approach for sequence-to-sequence learning, and has been popularly used in speech recognition. The central ideas of CTC include adding a label "blank" during training. With this mechanism, CTC eliminates the need of segment alignment, and hence has been applied to various sequence-to-sequence ...
Bo-Ru Lu, Frank Shyu, Yun-Nung Chen, Hung-yi Lee, Lin-Shan Lee   +4 more
openaire   +4 more sources

A Survey for Deep Reinforcement Learning Based Network Intrusion Detection

Applied AI Letters, Volume 7, Issue 2, June 2026.
This paper surveys deep reinforcement learning (DRL) for network intrusion detection, evaluating model efficiency, minority attack detection, and dataset imbalance. Findings show DRL achieves state‐of‐the‐art results on public datasets, sometimes surpassing traditional deep learning.
Wanrong Yang, Alberto Acuto, Yihang Zhou, Dominik Wojtczak   +3 more
wiley   +1 more source

BERT-NAR-BERT: A Non-Autoregressive Pre-Trained Sequence-to-Sequence Model Leveraging BERT Checkpoints

IEEE Access
We introduce BERT-NAR-BERT (BnB) – a pre-trained non-autoregressive sequence-to-sequence model, which employs BERT as the backbone for the encoder and decoder for natural language understanding and generation tasks.
Mohammad Golam Sohrab, Masaki Asada, Matiss Rikters, Makoto Miwa   +3 more
doaj   +1 more source

Accented Speech Recognition Based on End-to-End Domain Adversarial Training of Neural Networks

Applied Sciences, 2021
The performance of automatic speech recognition (ASR) may be degraded when accented speech is recognized because the speech has some linguistic differences from standard speech.
Hyeong-Ju Na, Jeong-Sik Park
doaj   +1 more source