Recent advances in deep learning: An overview

MR Minar, J Naher - arXiv preprint arXiv:1807.08169, 2018 - arxiv.org
Deep Learning is one of the newest trends in Machine Learning and Artificial Intelligence
research. It is also one of the most popular scientific research trends now-a-days. Deep …

Deep multi-view multiclass twin support vector machines

X Xie, Y Li, S Sun - Information Fusion, 2023 - Elsevier
Multi-view learning (MVL) is a rapidly evolving direction in the field of machine learning.
Despite the positive results, most algorithms that combine multi-view learning with twin …

A Review of Deep Learning Applications in Tunneling and Underground Engineering in China

C Su, Q Hu, Z Yang, R Huo - Applied Sciences, 2024 - mdpi.com
With the advent of the era of big data and information technology, deep learning (DL) has
become a hot trend in the research field of artificial intelligence (AI). The use of deep …

Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor …

H Jang, SM Plis, VD Calhoun, JH Lee - NeuroImage, 2017 - Elsevier
Feedforward deep neural networks (DNNs), artificial neural networks with multiple hidden
layers, have recently demonstrated a record-breaking performance in multiple areas of …

Incorporating noise robustness in speech command recognition by noise augmentation of training data

A Pervaiz, F Hussain, H Israr, MA Tahir, FR Raja… - Sensors, 2020 - mdpi.com
The advent of new devices, technology, machine learning techniques, and the availability of
free large speech corpora results in rapid and accurate speech recognition. In the last two …

Learning graph convolutional networks based on quantum vertex information propagation

L Bai, Y Jiao, L Cui, L Rossi, Y Wang… - … on Knowledge and …, 2021 - ieeexplore.ieee.org
This paper proposes a new Quantum Spatial Graph Convolutional Neural Network
(QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes …

Learning backtrackless aligned-spatial graph convolutional networks for graph classification

L Bai, L Cui, Y Jiao, L Rossi… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
In this paper, we develop a novel backtrackless aligned-spatial graph convolutional network
(BASGCN) model to learn effective features for graph classification. Our idea is to transform …

A method of speech coding for speech recognition using a convolutional neural network

M Kubanek, J Bobulski, J Kulawik - Symmetry, 2019 - mdpi.com
This work presents a new approach to speech recognition, based on the specific coding of
time and frequency characteristics of speech. The research proposed the use of …

Thermal augmented expression recognition

S Wang, B Pan, H Chen, Q Ji - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Visible facial images provide geometric and appearance patterns of facial expressions and
are sensitive to illumination changes. Thermal facial images record facial temperature …

Learning aligned vertex convolutional networks for graph classification

L Cui, L Bai, X Bai, Y Wang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Graph convolutional networks (GCNs) are powerful tools for graph structure data analysis.
One main drawback arising in most existing GCN models is that of the oversmoothing …