no code implementations • 6 Jan 2024 • Xuran Hu, Mingzhe Zhu, Yuanjing Liu, Zhenpeng Feng, Ljubisa Stankovic
Explainable artificial intelligence (XAI) holds immense significance in enhancing the deep neural network's transparency and credibility, particularly in some risky and high-cost scenarios, like synthetic aperture radar (SAR).
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 6 Jan 2024 • Xuran Hu, Ziqiang Xu, Zhihan Chen, Zhengpeng Feng, Mingzhe Zhu, Ljubisa Stankovic
Speckle noise poses a significant challenge in maintaining the quality of synthetic aperture radar (SAR) images, so SAR despeckling techniques have drawn increasing attention.
no code implementations • 16 Feb 2023 • Ali Bagheri Bardi, Milos Dakovic, Taher Yazdanpanah, Ljubisa Stankovic
New explicit analytic expressions for the eigenvalues, together with their multiplicities, for the cases of three DTT (DCT$_{(1)}$, DCT$_{(5)}$, and DST$_{(8)}$), are the main contribution of this paper.
no code implementations • 3 Feb 2023 • Zhenpeng Feng, Hongbing Ji, Milos Dakovic, Xiyang Cui, Mingzhe Zhu, Ljubisa Stankovic
Furthermore, we propose an artful strategy to forge a cognition-base map and cognition-scissors from clustered feature maps.
no code implementations • 12 Jan 2023 • Alexander Jenkins, Imad Jaimoukha, Ljubisa Stankovic, Danilo Mandic
Forming the right combination of students in a group promises to enable a powerful and effective environment for learning and collaboration.
no code implementations • 16 Oct 2022 • Shengxi Li, Xinyi Zhao, Ljubisa Stankovic, Danilo Mandic
The success of convolution neural networks (CNN) has been revolutionising the way we approach and use intelligent machines in the Big Data era.
no code implementations • 15 Sep 2022 • Zhenpeng Feng, Xiyang Cui, Hongbing Ji, Mingzhe Zhu, Ljubisa Stankovic
For standard convolutional neural networks (CNNs), class activation mapping (CAM) methods are commonly used to visualize the connection between CNN's decision and image region by generating a heatmap.
no code implementations • 26 May 2022 • Zhenpeng Feng, Milos Dakovic, Hongbing Ji, Mingzhe Zhu, Ljubisa Stankovic
In this paper, we show that latent codes are disentangled to affect the properties of SAR images in a non-linear manner.
no code implementations • 26 Aug 2021 • Ljubisa Stankovic, Danilo Mandic
To help demystify CNNs, we revisit their operation from first principles and a matched filtering perspective.
no code implementations • 23 Aug 2021 • Ljubisa Stankovic, Danilo Mandic
Graph Convolutional Neural Networks (GCNN) are becoming a preferred model for data processing on irregular domains, yet their analysis and principles of operation are rarely examined due to the black box nature of NNs.
no code implementations • 7 Jun 2021 • Alvaro Arroyo, Bruno Scalzo, Ljubisa Stankovic, Danilo P. Mandic
Stock market returns are typically analyzed using standard regression, yet they reside on irregular domains which is a natural scenario for graph signal processing.
no code implementations • 11 Mar 2021 • Ljubisa Stankovic, Milos Brajovic, Danilo Mandic, Isidora Stankovic, Milos Dakovic
Within the Compressive Sensing (CS) paradigm, sparse signals can be reconstructed based on a reduced set of measurements.
no code implementations • 31 Jan 2021 • Bruno Scalzo, Alvaro Arroyo, Ljubisa Stankovic, Danilo P. Mandic
Classical portfolio optimization methods typically determine an optimal capital allocation through the implicit, yet critical, assumption of statistical time-invariance.
no code implementations • 27 Jul 2020 • Bruno Scalzo, Ljubisa Stankovic, Danilo P. Mandic
A class of multivariate spectral representations for real-valued nonstationary random variables is introduced, which is characterised by a general complex Gaussian distribution.
no code implementations • 2 Jan 2020 • Ljubisa Stankovic, Danilo Mandic, Milos Dakovic, Milos Brajovic, Bruno Scalzo, Shengxi Li, Anthony G. Constantinides
Many modern data analytics applications on graphs operate on domains where graph topology is not known a priori, and hence its determination becomes part of the problem definition, rather than serving as prior knowledge which aids the problem solution.
no code implementations • 12 Oct 2019 • Bruno Scalzo Dees, Ljubisa Stankovic, Anthony G. Constantinides, Danilo P. Mandic
Investment returns naturally reside on irregular domains, however, standard multivariate portfolio optimization methods are agnostic to data structure.