User profiles for Cheng Soon Ong
Cheng Soon OngData61, CSIRO, Canberra Verified email at anu.edu.au Cited by 9698 |
[HTML][HTML] Support vector machines and kernels for computational biology
The increasing wealth of biological data coming from a large variety of platforms and the
continued development of new high-throughput methods for probing biological systems require …
continued development of new high-throughput methods for probing biological systems require …
The balanced accuracy and its posterior distribution
Evaluating the performance of a classification algorithm critically requires a measure of the
degree to which unseen examples have been identified with their correct class labels. In …
degree to which unseen examples have been identified with their correct class labels. In …
[PDF][PDF] Protein function prediction via graph kernels
KM Borgwardt, CS Ong, S Schönauer… - …, 2005 - researchgate.net
Motivation: Computational approaches to protein function prediction infer protein function by
finding proteins with similar sequence, structure, surface clefts, chemical properties, amino …
finding proteins with similar sequence, structure, surface clefts, chemical properties, amino …
[BOOK][B] Mathematics for machine learning
The fundamental mathematical tools needed to understand machine learning include linear
algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability …
algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability …
[PDF][PDF] Learning the kernel with hyperkernels
This paper addresses the problem of choosing a kernel suitable for estimation with a support
vector machine, hence further automating machine learning. This goal is achieved by …
vector machine, hence further automating machine learning. This goal is achieved by …
Multiclass multiple kernel learning
A Zien, CS Ong - Proceedings of the 24th international conference on …, 2007 - dl.acm.org
In many applications it is desirable to learn from several kernels. "Multiple kernel learning" (MKL)
allows the practitioner to optimize over linear combinations of kernels. By enforcing …
allows the practitioner to optimize over linear combinations of kernels. By enforcing …
Learning with non-positive kernels
In this paper we show that many kernel methods can be adapted to deal with indefinite kernels,
that is, kernels which are not positive semidefinite. They do not satisfy Mercer's condition …
that is, kernels which are not positive semidefinite. They do not satisfy Mercer's condition …
[PDF][PDF] The need for open source software in machine learning
Open source tools have recently reached a level of maturity which makes them suitable for
building large-scale real-world systems. At the same time, the field of machine learning has …
building large-scale real-world systems. At the same time, the field of machine learning has …
Learning from corrupted binary labels via class-probability estimation
Many supervised learning problems involve learning from samples whose labels are corrupted
in some way. For example, each sample may have some constant probability of being …
in some way. For example, each sample may have some constant probability of being …
Wheel defect detection with machine learning
G Krummenacher, CS Ong, S Koller… - IEEE Transactions …, 2017 - ieeexplore.ieee.org
Wheel defects on railway wagons have been identified as an important source of damage to
the railway infrastructure and rolling stock. They also cause noise and vibration emissions …
the railway infrastructure and rolling stock. They also cause noise and vibration emissions …