Prof. Iman Soltani

We propose a memory-augmented deep learning model for semisupervised anomaly detection (AD). While many traditional AD methods focus on modeling the distribution of normal data, additional constraints in the modeling process are needed to distinguish between normal and abnormal data. The proposed model, named memory augmented generative adversarial networks (MEMGAN), is coupled with external memory units through attentional operations. One property of MEMGAN in the latent space is such that encoded normal data are expected to reside in the convex hull of the memory units, while the abnormal ones are separated outside. This property makes the AD process of MEMGAN more robust and reliable. Experiments on AD datasets adapted from MVTec, MNIST, CIFAR10, and Arrhythmia demonstrate that MEMGAN notably improves over previous AD models. We also find that the decoded memory units in MEMGAN are more diverse and interpretable than those in previous memory-augmented models.

1 June 2010 in Smart Materials and Structures

Journal Article

Teager energy operator for multi-modulation extraction and its application for gearbox fault detection

Iman Soltani

Ming Liang

About Me

Iman Soltani is an assistant professor of Mechanical and Aerospace Engineering and a graduate faculty with the Departments of Computer Science and Electrical and Computer Engineering at UC Davis. His research lies at the interface of artificial intelligence, controls and machine design, focusing on the development of automation tools with applications in materials and medical research, autonomous driving, and manufacturing. Prior to joining UC Davis, he worked at the Ford Greenfield Labs in Palo Alto, CA, where he led the Advanced Automation Laboratory. He received his B.Sc. from Amir-Kabir University of Technology in Iran, his M.Sc. from the University of Ottawa in Canada, and his PhD and Postdoc training at the Massachusetts Institute of Technology (MIT). His research has been featured in the news such as the Boston Globe, Elsevier Materials Today, ScienceDaily, and MIT-News. He is a recipient of multiple awards in academia and industry such as the MIT Carl G. Sontheimer award and the National Instrument’s engineering impact award.

Prof. Iman Soltani

Prof. Iman Soltani

Research Focus & Metrics

Academic Career Length

Publication Type Breakdown

Representative Publications

About Me