All Outputs (7)

Evaluating Gaussian Grasp Maps for Generative Grasping Models (2022)
Presentation / Conference Contribution
Prew, W., Breckon, T., Bordewich, M., & Beierholm, U. (2022, July). Evaluating Gaussian Grasp Maps for Generative Grasping Models. Presented at Proc. Int. Joint Conf. Neural Networks, Padova, Italy

Generalising robotic grasping to previously unseen objects is a key task in general robotic manipulation. The current method for training many antipodal generative grasping models rely on a binary ground truth grasp map generated from the centre thir... Read More about Evaluating Gaussian Grasp Maps for Generative Grasping Models.

Autoencoders Without Reconstruction for Textural Anomaly Detection (2021)
Presentation / Conference Contribution
Adey, P., Akcay, S., Bordewich, M., & Breckon, T. (2021, July). Autoencoders Without Reconstruction for Textural Anomaly Detection. Presented at 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China

Automatic anomaly detection in natural textures is a key component within quality control for a range of high-speed, high-yield manufacturing industries that rely on camera-based visual inspection techniques. Targeting anomaly detection through the u... Read More about Autoencoders Without Reconstruction for Textural Anomaly Detection.

Improving Robotic Grasping on Monocular Images Via Multi-Task Learning and Positional Loss (2021)
Presentation / Conference Contribution
Prew, W., Breckon, T., Bordewich, M., & Beierholm, U. (2021, January). Improving Robotic Grasping on Monocular Images Via Multi-Task Learning and Positional Loss. Presented at 25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy

In this paper we introduce two methods of improving real-time object grasping performance from monocular colour images in an end-to-end CNN architecture. The first is the addition of an auxiliary task during model training (multi-task learning). Our... Read More about Improving Robotic Grasping on Monocular Images Via Multi-Task Learning and Positional Loss.

On the approximation complexity hierarchy. (2011)
Presentation / Conference Contribution
Bordewich, M. (2010, September). On the approximation complexity hierarchy. Presented at 8th International Workshop on International Workshop on Approximation and Online Algorithms, WAOA 2010, Liverpool

This paper presents an extension of Ladner’s Theorem to the approximation complexity hierarchy. In 1975 Ladner proved that if P≠NP, then there exists an incomplete problem A which is neither in P nor NP-complete. Here we show that if RP≠NP, then ther... Read More about On the approximation complexity hierarchy..

Accuracy Guarantees for Phylogeny Reconstruction Algorithms Based on Balanced Minimum Evolution. (2010)
Presentation / Conference Contribution
Bordewich, M., & Mihaescu, R. (2010, September). Accuracy Guarantees for Phylogeny Reconstruction Algorithms Based on Balanced Minimum Evolution. Presented at 10th Workshop on Algorithms in Bioinformatics (WABI 2010), Liverpool

Distance based phylogenetic methods attempt to reconstruct an accurate phylogenetic tree relating a given set of taxa from an estimated matrix of pair-wise distances between taxa. This paper examines two distance based algorithms (GreedyBME and FastM... Read More about Accuracy Guarantees for Phylogeny Reconstruction Algorithms Based on Balanced Minimum Evolution..

Stopping times, metrics and approximate counting (2006)
Presentation / Conference Contribution
Bordewich, M., Dyer, M., & Karpinski, M. (2006, July). Stopping times, metrics and approximate counting. Presented at 33rd International Colloquium of Automata, Languages and Programming (ICALP 2006)., Venice, Italy

In this paper we examine the importance of the choice of metric in path coupling, and its relationship to stopping time analysis. We give strong evidence that stopping time analysis is no more powerful than standard path coupling. In particular, we p... Read More about Stopping times, metrics and approximate counting.

Path coupling using stopping times (2005)
Presentation / Conference Contribution
Bordewich, M., Dyer, M., & Karpinski, M. (2005, August). Path coupling using stopping times. Presented at 15th International Symposium Fundamentals of Computation Theory : FCT 2005., Lubeck, Germany

We analyse the mixing time of Markov chains using path coupling with stopping times. We apply this approach to two hypergraph problems. We show that the Glauber dynamics for independent sets in a hypergraph mixes rapidly as long as the maximum degree... Read More about Path coupling using stopping times.