Data Augmentation News Today

Los Angeles CA (SPX) May 03, 2024 - A study conducted by researchers from Northwestern University has revealed a discrepancy in seismic hazard maps, which are instrumental in guiding the construction of earthquake-resistant structures

New York, March 27, 2024 – ACM, the Association for Computing Machinery, and IMS, the Institute of Mathematical Statistics, have announced the publication [...]

In the light of new regulations how do we verify and validate AI in safety critical systems. By Lucas Garcia.

Ever-increasing efforts in state of charge (SOC) of lithium-ion battery estimation techniques have been centered on machine learning-based methods, and a prerequisite guaranteeing the effectiveness of these methods demands an abundance of high-quality datasets. However, performing battery-related experiments is time-consuming and expensive, and manufacturers are reluctant to release their datasets due to confidentiality constraints. This limited data availability has hindered further research in...

/PRNewswire/ -- AONDevices, a leader in super low-power, high-accuracy edge AI solutions, today announced the launch of AONx360™. This innovative online...

A new technique enables a human to efficiently fine-tune a robot that failed to complete a desired task with very little effort on the part of the human. Their system uses algorithms, counterfactual explanations, and feedback from the user to generate synthetic data it uses to quickly fine-tune the robot.

Training convolutional neural networks (CNN) often require a large amount of data. However, for some biometric data, such as fingerprints and iris, it is often difficult to obtain a large amount of data due to privacy issues. Therefore, training the CNN model often suffers from specific problems, such as overfitting, low accuracy, poor generalization ability, etc. To solve them, we propose a novel image augmentation algorithm for small sample iris image in this article. It is based on a modified...

Graph anomaly detection in this paper aims to distinguish abnormal nodes that behave differently from the benign ones accounting for the majority of graph-structured instances. Receiving increasing attention from both academia and industry, yet existing research on this task still suffers from two critical issues when learning informative anomalous behavior from graph data. For one thing, anomalies are usually hard to capture because of their subtle abnormal behavior and the shortage of backgrou...

The outstanding performance of deep learning has prompted the rise of Machine Learning as a Service (MLaaS), which significantly reduces the difficulty for users to train and deploy models. For privacy and security considerations, most models in the MLaaS scenario only provide users with black-box access. However, previous works have shown that this defense mechanism still faces potential threats, such as model extraction attacks, which aim at stealing the function or parameters of a black-box v...

The goal of contrastive representation learning is to learn such an embedding space in which similar sample pairs stay close to each other while dissimilar ones are far apart. Contrastive learning can be applied to both supervised and unsupervised settings. When working with unsupervised data, contrastive learning is one of the most powerful approaches in self-supervised learning. Contrastive Training Objectives In early versions of loss functions for contrastive learning, only one positive and ...