About
11
Publications
741
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
60
Citations
Introduction
Daren Ler currently lectures at the National University of Singapore, School of Computing. His research focus is on machine learning, and in particular, on automated machine learning, or AutoML. More specifically, his research has focused primarily on the algorithm selection problem, which is part of the larger domain of meta-learning
Current institution
Publications
Publications (11)
In this paper, we introduce a new form of meta-feature that is based on a distance-weighted class-homogeneous neighbourhood ratio to facilitate algorithm selection. We show that these new meta-features, while exhibiting a cost advantage, achieve a comparable, and in some cases, higher performance than conventional meta-features. These results were...
Recently, we proposed a new meta-learning approach based on landmarking. This approach, which utilises a new set of criteria for selecting landmarkers, generates a set of landmarkers that are each functions over the performance over subsets of the candidate algorithms being landmarked. In this paper, we experiment with three heuristics based on cor...
For a given classification task, there are typically several learning algorithms available. The question then arises: which is the most appropriate algorithm to apply. Recently, we proposed a new algorithm for making such a selection based on landmarking - a meta-learning strategy that utilises meta-features that are measurements based on efficient...
We believe that a user should be able to scrutinise the be-liefs a system has about him/her, namely the user model, as well as be able to update that model. A MyMuseum proto-type of a scrutable and personalised museum guide has been built to explore ways to visualise how the system adapts to the user and the reasons for the adaptation. As a result...
In this paper, we present a method for efficient se- lection of heterogeneous majority voting ensem- bles. Given a set A of algorithms, the set of possi- ble voters V over A is exponential in the size of A. Thus, it is not computationally feasible to select the best ensemble by evaluating each possibility. In- stead, we compute the classification a...
Landmarking is a recent and promising meta-learning strategy, which defines meta-features that are themselves efficient learning algorithms. However, the choice of landmarkers is often made in an ad hoc manner. In this paper, we propose a new perspective and set of criteria for landmarkers. Based on the new criteria, we propose a landmarker generat...
This paper presents a named entity classifica-tion system that utilises both orthographic and contextual information. The random subspace method was employed to generate and refine at-tribute models. Supervised and unsupervised learning techniques used in the recombination of models to produce the final results.
Landmarking is a recent and promising meta- learning strategy, which defines meta-features that are themselves efficient learning algorithms. However, the choice of landmarkers is made in an ad hoc manner. In this paper, we propose a new perspective and set of criteria for landmarkers. With these, we introduce a landmarker generation algorithm, whi...
To create efficiencies in the production process of revisable multi-media systems it is necessary to define processes for the control of content revision and regeneration with a workflow control of these processes. A model for manag-ing Multimedia Run-time Systems (MRS) is presented as consisting of a revision control strategy for managing primary...
