scispace - formally typeset
S

Svetha Venkatesh

Researcher at Deakin University

Publications -  864
Citations -  20118

Svetha Venkatesh is an academic researcher from Deakin University. The author has contributed to research in topics: Bayesian optimization & Computer science. The author has an hindex of 60, co-authored 828 publications receiving 16441 citations. Previous affiliations of Svetha Venkatesh include Australian National University & National University of Singapore.

Papers
More filters
Proceedings ArticleDOI

Ridge Regression for Two Dimensional Locality Preserving Projection

TL;DR: A novel algorithm called Ridge Regression for Two Dimensional Locality Preserving Projection (RR-2DLPP) is proposed, which is an extension of 2D-LPP with the use of ridge regression, comparable to 2D -LPP in performance whilst having a lower computational cost.
Journal ArticleDOI

An Investigation into the Use of Physical Modeling for the Prediction of Various Feature Types Visible from Different Viewpoints

TL;DR: This paper provides a flexible, automated, and general purpose technique for generating the view information for each viewpoint and shows how occluding and nonoccluding edge-based features can be extracted using image processing techniques and then parametrized and also how regions of specularity can be predicted and described.

Representations and Processes in Decision Modelling

TL;DR: A survey by Curtin University on decision modelling is presented in this article, which covers the current understanding of how we make decisions, and points out our qualities, our weaknesses and the types of aids that could help us.
Proceedings ArticleDOI

The adaptable buffer algorithm for high quantile estimation in non-stationary data streams

TL;DR: In this paper, the problem of estimating the running quantile of a data stream with non-stationary stochasticity when the memory for storing observations is limited is addressed.
Posted ContentDOI

Cancer as a tissue anomaly: classifying tumor transcriptomes based only on healthy data

TL;DR: This report argues that discriminatory methods are fundamentally ill-suited for the classification of cancer and proposes an established surveillance method that detects anomalous samples based on their deviation from a learned normal steady-state structure, which can create an anomaly detector for tissue transcriptomes, a “tissue detector” that is capable of identifying cancer without ever seeing a single cancer example.