no code implementations • 2 Jul 2023 • Mingxue Xu, Yao Lei Xu, Danilo P. Mandic
High-dimensional token embeddings underpin Large Language Models (LLMs), as they can capture subtle semantic information and significantly enhance the modelling of complex language patterns.
no code implementations • 23 Mar 2023 • 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-explored within the deep learning community.
no code implementations • 5 Dec 2022 • Hongjian Xiao, Yao Lei Xu, Danilo P. Mandic
Financial markets typically exhibit dynamically complex properties as they undergo continuous interactions with economic and environmental factors.
no code implementations • 26 Oct 2022 • Yao Lei Xu, Kriton Konstantinidis, Danilo P. Mandic
This represents a challenge for modern machine learning models, as the number of model parameters needed to process such data grows exponentially with the data dimensions; an effect known as the Curse-of-Dimensionality.
no code implementations • 11 May 2021 • Bruno Scalzo Dees, Yao Lei Xu, Anthony G. Constantinides, Danilo P. Mandic
Finally, we also explore the application of modern deep learning models, such as graph neural networks and hyper-graph neural networks, as general purpose models for the modelling and forecasting of underground data, especially in the context of the morning and evening rush hours.
no code implementations • 11 May 2021 • 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.
no code implementations • 27 Mar 2021 • 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.
1 code implementation • 25 Oct 2020 • 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.
no code implementations • 18 Sep 2020 • 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 parameters when dealing with large multidimensional data.