A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.





Development of a Parallel Robot Manipulator

Published in Capstone projects - Asian Institute of Technology, Thailand, 2015

Parallel manipulation can offer a number of advantages over conventional serial manipula- tion with respect to optimising operational speed while retaining high accuracy in position- ing. In this study a parallel robot manipulator was developed to achieve precise end effector positioning in a three-dimensional workspace. The mechanical assembly, the kinematics analysis and the control programme were built and composed from scratch and several ap- plications were executed in the end to test the operational capabilities of the robot.

Enhancing Generalisation of First-Order Meta-Learning

Published in The 2nd Learning from Limited Labeled Data (LLD) Workshop at The International Conference on Learning Representations (ICLR) 2019, 2019

In this study we focus on first-order meta-learning algorithms that aim to learn a parameter initialization of a network which can quickly adapt to new concepts, given a few examples. We investigate two approaches to enhance generalization and speed of learning of such algorithms, particularly expanding on the Reptile (Nichol et al., 2018) algorithm. We introduce a novel regularization technique called meta-step gradient pruning and also investigate the effects of increasing the depth of network architectures in first-order meta-learning. We present an empirical evaluation of both approaches, where we match benchmark few-shot image classification results with 10 times fewer iterations using Mini-ImageNet dataset and with the use of deeper networks, we attain accuracies that surpass the current benchmarks of few-shot image classification using Omniglot dataset.

Visual-Semantic Embedding Model Informed by Structured Knowledge

Published in The 9th European Starting AI Researchers’ Symposium (STAIRS@ECAI2020), 2020

This study proposes a novel approach to improve a visual-semantic embedding model by incorporating concept representations captured from an external structured knowledge base. We investigate its performance on image classification under both standard and zero-shot settings. We propose two novel evaluation frameworks to analyse classification errors with respect to the class hierarchy indicated by the knowledge base. The approach is tested using the ILSVRC 2012 image dataset and a WordNet knowledge base. With respect to both standard and zero-shot image classification, our approach shows superior performance compared with the original approach, which uses word embeddings. We discuss reasons for this improvement and future work.



Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.