1.4k citations · 3.2k across the 73 of their papers we have counts for
16 papers · 1 filter
Pearl: Parallel Evolutionary and Reinforcement Learning Library
Rohan Tangri, Danilo P. Mandic, Anthony G. Constantinides
Reinforcement learning is increasingly finding success across domains where the problem can be represented as a Markov decision process. Evolutionary computation algorithms have al…
Understanding the Basis of Graph Convolutional Neural Networks via an Intuitive Matched Filtering Approach
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 examin…
Graph Theory for Metro Traffic Modelling
Bruno Scalzo Dees, Yao Lei Xu, Anthony G. Constantinides +1
A unifying graph theoretic framework for the modelling of metro transportation networks is proposed. This is achieved by first introducing a basic graph framework for the modelling…
Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting
Yao Lei Xu, Giuseppe G. Calvi, Danilo P. Mandic
Recurrent Neural Networks (RNNs) represent the de facto standard machine learning tool for sequence modelling, owing to their expressive power and memory. However, when dealing wit…
Tensor Networks for Multi-Modal Non-Euclidean Data
Yao Lei Xu, Kriton Konstantinidis, Danilo P. Mandic
Modern data sources are typically of large scale and multi-modal natures, and acquired on irregular domains, which poses serious challenges to traditional deep learning models. The…
A Review of Hidden Markov Models and Recurrent Neural Networks for Event Detection and Localization in Biomedical Signals
Yassin Khalifa, Danilo Mandic, Ervin Sejdić
Biomedical signals carry signature rhythms of complex physiological processes that control our daily bodily activity. The properties of these rhythms indicate the nature of interac…
Multi-Graph Tensor Networks
Yao Lei Xu, Kriton Konstantinidis, Danilo P. Mandic
The irregular and multi-modal nature of numerous modern data sources poses serious challenges for traditional deep learning algorithms. To this end, recent efforts have generalized…
Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequence
Yao Lei Xu, Danilo P. Mandic
Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of para…
Reciprocal Adversarial Learning via Characteristic Functions
Shengxi Li, Zeyang Yu, Min Xiang +1
Generative adversarial nets (GANs) have become a preferred tool for tasks involving complicated distributions. To stabilise the training and reduce the mode collapse of GANs, one o…
Tensor Decompositions in Deep Learning
Davide Bacciu, Danilo P. Mandic
The paper surveys the topic of tensor decompositions in modern machine learning applications. It focuses on three active research topics of significant relevance for the community.…
Supervised Learning for Non-Sequential Data: A Canonical Polyadic Decomposition Approach
Alexandros Haliassos, Kriton Konstantinidis, Danilo P. Mandic
Efficient modelling of feature interactions underpins supervised learning for non-sequential tasks, characterized by a lack of inherent ordering of features (variables). The brute…
Solving general elliptical mixture models through an approximate Wasserstein manifold
Shengxi Li, Zeyang Yu, Min Xiang +1
We address the estimation problem for general finite mixture models, with a particular focus on the elliptical mixture models (EMMs). Compared to the widely adopted Kullback-Leible…
Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation
Giuseppe G. Calvi, Ahmad Moniri, Mahmoud Mahfouz +2
This work aims to help resolve the two main stumbling blocks in the application of Deep Neural Networks (DNNs), that is, the exceedingly large number of trainable parameters and th…
Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion
Longhao Yuan, Chao Li, Danilo Mandic +2
In tensor completion tasks, the traditional low-rank tensor decomposition models suffer from the laborious model selection problem due to their high model sensitivity. In particula…
A universal framework for learning the elliptical mixture model
Shengxi Li, Zeyang Yu, Danilo Mandic
Mixture modelling using elliptical distributions promises enhanced robustness, flexibility and stability over the widely employed Gaussian mixture model (GMM). However, existing st…
Online Multilinear Dictionary Learning
Thiernithi Variddhisai, Danilo Mandic
A method for online tensor dictionary learning is proposed. With the assumption of separable dictionaries, tensor contraction is used to diminish a -way model of $\mathcal{O}\le…