Motivation

Compressed sensing is a technique used in signal processing and data compression. It's particularly useful when dealing with signals or data that can be represented sparsely. It can provide near perfect resonstruction with randomly sampled data.

However, In certain applications, data reconstruction isn't the primary objective. In such instances, compressed learning (CL) is employed, which integrates compressed sensing with machine learning. In contrast to compressed sensing, the goal of CL is inference from the signal rather than signal reconstruction.

Objectives

Implementing a functioning compressed learning framework

Statistical evaluation and comparison of the proposed method with classical CS methods

Requirements

Familiar with artificial neural networks and Python programming language

Interest in image and signal processing

Interest in novel deep learning topics like self-supervised learning, meta-learning, explainable AI, etc.

Literature

[1] A. Adler, M. Elad, and M. Zibulevsky, "Compressed learning: A deep neural network approach," arXiv preprint arXiv:1610.09615, Oct. 2016.