Heuristic optimisation

We propose rigorously optimised supervised feature extraction methods for multilinear data based on Multilinear Discriminant Analysis (MDA) and demonstrate their usage on Electroencephalography (EEG) and simulated data. While existing MDA methods use heuristic optimisation procedures based on an ambiguous Tucker structure, we propose a rigorous approach via optimisation on the cross-product of Stiefel manifolds.

15p viconnecticut2711 28-10-2020 14 1   Download

The study of complex manufacturing flow-shops has seen a number of approaches and frameworks proposed to tackle various production-associated problems.

32p meriday 20-04-2019 7 2   Download

Large-scale discriminative machine translation promises to further the state-of-the-art, but has failed to deliver convincing gains over current heuristic frequency count systems. We argue that a principle reason for this failure is not dealing with multiple, equivalent translations. We present a translation model which models derivations as a latent variable, in both training and decoding, and is fully discriminative and globally optimised. Results show that accounting for multiple derivations does indeed improve performance.

9p hongphan_1 15-04-2013 53 3   Download