This work presents a novel algorithm for transforming a neural network i...
A typical machine learning (ML) development cycle for edge computing is ...
We present a theory of ensemble diversity, explaining the nature and eff...
There is growing interest in continuous wearable vital sign sensors for
...
We give lower bounds on the amount of memory required by one-pass stream...
We introduce a novel bias-variance decomposition for a range of strictly...
We present two sample-efficient differentially private mean estimators f...
Modern machine learning models are complex and frequently encode surpris...
Deployed supervised machine learning models make predictions that intera...
This paper demonstrates that ensembles of spiking neural networks can be...
The ultimate goal of a supervised learning algorithm is to produce model...
Probability estimates generated by boosting ensembles are poorly calibra...
We examine the practice of joint training for neural network ensembles, ...
Learning in adversarial settings is becoming an important task for
appli...
In this paper we propose and explore the k-Nearest Neighbour UCB algorit...
Ensemble methods are a cornerstone of modern machine learning. The
perfo...
We study the approximate nearest neighbour method for cost-sensitive
cla...
Deep neural networks have been widely adopted in recent years, exhibitin...