Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey
Recently emerged technologies based on Deep Learning (DL) achieved outstanding results
on a variety of tasks in the field of Artificial Intelligence (AI). However, these encounter …
on a variety of tasks in the field of Artificial Intelligence (AI). However, these encounter …
Domain Adaptation Using Class-Balanced Self-Paced Learning for Soil Classification With LIBS
Laser-induced breakdown spectroscopy (LIBS) is a promising technology for soil analysis
due to its simple setup, cost-effectiveness, and rapid (few seconds) analysis time per …
due to its simple setup, cost-effectiveness, and rapid (few seconds) analysis time per …
Class-oriented and label embedding analysis dictionary learning for pattern classification
K Jiang, C Zhao, L Zhu, Q Sun - Multimedia Tools and Applications, 2023 - Springer
Abstract Analysis dictionary learning (ADL) has obtained lots of research interest in sparse
representation-based classification recent years, due to its flexibility and low complexity for …
representation-based classification recent years, due to its flexibility and low complexity for …
A discriminative approach to unsupervised domain adaptation in coarse-to-fine classifiers
IR Alkhouri, AS Awad, C Hatfield… - 2023 IEEE 33rd …, 2023 - ieeexplore.ieee.org
Conventional machine learning models often exhibit poor performance when tested on data
that comes from a different probability distribution than that of the training data. This …
that comes from a different probability distribution than that of the training data. This …
Explainable multimodal deep dictionary learning to capture developmental differences from three fMRI paradigms
L Yang, C Qiao, H Zhou, VD Calhoun… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Objective: Multimodal-based methods show great potential for neuroscience studies by
integrating complementary information. There has been less multimodal work focussed on …
integrating complementary information. There has been less multimodal work focussed on …
Data representation learning via dictionary learning and self-representation
Dictionary learning is an effective feature learning method, leading to many remarkable
results in data representation and classification tasks. However, dictionary learning is …
results in data representation and classification tasks. However, dictionary learning is …
Occlusion recovery face recognition based on information reconstruction
H He, J Liang, Z Hou, H Liu, X Zhou - Machine Vision and Applications, 2023 - Springer
The face data in the wild have a face occlusion, complex background, and inestimable
posture, leading to more sample classification errors. To alleviate the problem of face …
posture, leading to more sample classification errors. To alleviate the problem of face …
Salient double reconstruction-based discriminative projective dictionary pair learning for crowd counting
T Wang, H Luo, K Zhang, H Wang, M Li, J Lu - Applied Intelligence, 2023 - Springer
Crowd counting is one of the most fundamental tasks in the field of computer vision and
dictionary learning has been successfully applied to the task. However, many traditional …
dictionary learning has been successfully applied to the task. However, many traditional …
[HTML][HTML] Learning biologically-interpretable latent representations for gene expression data: Pathway Activity Score Learning Algorithm
I Karagiannaki, K Gourlia, V Lagani, Y Pantazis… - Machine Learning, 2023 - Springer
Molecular gene-expression datasets consist of samples with tens of thousands of measured
quantities (ie, high dimensional data). However, lower-dimensional representations that …
quantities (ie, high dimensional data). However, lower-dimensional representations that …