Negar Heidari


Negar Heidari


Negar Heidari received her BSc. in Information Technology and her MSc. in Artificial Intelligence from Department of Electrical and Computer Engineering, Isfahan University of Technology in 2014 and 2017, respectively. Her MSc. research has targeted the integration of Fuzzy Clustering and Unsupervised Distance Metric Learning in a probabilistic manner.

She is currently a PhD fellow at the Computer Vision Lab, Department of Engineering, Electrical and Computer Engineering, Aarhus University.

Her current research interests include Machine Learning, Pattern Recognition and Deep Learning. In particular, employing machine learning approaches towards autonomy in industry.


Project title: Efficient Deep Learning approaches for Unmanned Aerial Vehicles


Main supervisor: Associate Prof. Alexandros Iosifidis

Co-supervisor: Prof. Peter Gorm Larsen       

Project period: 3 years                     


Project description:


Recent advances in Machine Learning have enabled us to target and successfully solve many challenging problems, most notably problems related to Computer Vision applications including image/scene recognition, object detection and recognition and human action localization and recognition. However, the current state of the art solutions, based on deep neural networks require heavy computations, high memory footprint and long training processes. These requirements are restrictive in many real-life application scenarios like when they are applied in Unmanned Aerial Vehicles – UAVs (e.g. drones).

This PhD project will research new techniques and methodologies for reducing the computational cost of deep neural network architectures (Convolutional Neural Networks and Recurrent Neural Networks). We will focus on the proposal of novel techniques for creating compact network topologies that can achieve the same (or better) performance with the state-of- the-art. Development of the proposed approaches in UAVs and testing in real application scenarios will also lead to exciting research directions for improving existing technology.

Vis alle (1) »

ID: 134648138