129 citations · 152 across the 16 of their papers we have counts for
7 papers · 1 filter
Interpretable Pre-Trained Transformers for Heart Time-Series Data
Harry J. Davies, James Monsen, Danilo P. Mandic
Decoder-only transformers are the backbone of the popular generative pre-trained transformer (GPT) series of large language models. In this work, we employ this framework to the an…
Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion
Pauline Bourigault, Dongpo Xu, Danilo P. Mandic
We develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers. This is achieved by combining the real-time recurrent learn…
Widely Linear Matched Filter: A Lynchpin towards the Interpretability of Complex-valued CNNs
Qingchen Wang, Zhe Li, Zdenka Babic +3
A recent study on the interpretability of real-valued convolutional neural networks (CNNs) {Stankovic_Mandic_2023CNN} has revealed a direct and physically meaningful link with the…
Improving Diffusion Models for ECG Imputation with an Augmented Template Prior
Alexander Jenkins, Zehua Chen, Fu Siong Ng +1
Pulsative signals such as the electrocardiogram (ECG) are extensively collected as part of routine clinical care. However, noisy and poor-quality recordings are a major issue for s…
Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains
Yao Lei Xu, Kriton Konstantinidis, Danilo P. Mandic
Despite the omnipresence of tensors and tensor operations in modern deep learning, the use of tensor mathematics to formally design and describe neural networks is still under-expl…
Fair and skill-diverse student group formation via constrained k-way graph partitioning
Alexander Jenkins, Imad Jaimoukha, Ljubisa Stankovic +1
Forming the right combination of students in a group promises to enable a powerful and effective environment for learning and collaboration. However, defining a group of students i…