Data augmentation, the artificial creation of training data for machine learning by
transformations, is a widely studied research field across machine learning disciplines …

Learning is using past experiences to inform new behaviors and actions. Because all
experiences are unique, learning always requires some generalization. An effective way of …

We present EDA: easy data augmentation techniques for boosting performance on text
classification tasks. EDA consists of four simple but powerful operations: synonym …

Since the proposal of a fast learning algorithm for deep belief networks in 2006, the deep
learning techniques have drawn ever-increasing research interests because of their …

In recent times, deep artificial neural networks have achieved many successes in pattern
recognition. Part of this success can be attributed to the reliance on big data to increase …

Abstract 3D shape is a crucial but heavily underutilized cue in today's computer vision
systems, mostly due to the lack of a good generic shape representation. With the recent …

Membership inference is one of the simplest privacy threats faced by machine learning
models that are trained on private sensitive data. In this attack, an adversary infers whether a …

Deep learning performs remarkably well on many time series analysis tasks recently. The
superior performance of deep neural networks relies heavily on a large number of training …

Data augmentation is a common strategy adopted to increase the quantity of training data,
avoid overfitting and improve robustness of the models. In this paper, we investigate audio …

Abstract State-of-charge (SOC) estimation of lithium-ion battery is one of the core functions
of battery management system. In order to improve the estimation accuracy of SOC, this …