Thesis opportunity- Efficient Pruning of Backbone Networks

Training neural networks from scratch requires large amounts of data and computation. It is therefore common to start with a network pre-trained on a large problem and adapt it to a more specific task using a smaller set of training data. This can be done by fine-tuning the pre-trained network or by using it as a feature extractor backbone for a task-specific algorithm. In many cases, the pre-trained network is much larger than needed to solve only the specific task.

Pruning and distillation are types of methods that aim to reduce the size of a network, while keeping the parts that are useful for a specific task. There are many such methods, but they can be complex and costly to run.

We would like your help to investigate pruning methods fast enough to run on embedded devices, and what types of backbone networks are suitable for them. This will require surveying literature, trying out open-source tools and likely implementing some variants yourself.

There are several possible directions for this project, and during the interview we will discuss details see what best aligns with your interests.

Prerequisites

You should have some experience of machine learning or mathematical optimization, and related programming. Familiarity with neural networks and related software frameworks is helpful, as is an interest in reading machine learning papers.

Contact
For more information about the position, contact:

Erik Hedberg, Algorithm Developer, erik.hedberg@sick.se

or

Sarah Lantz, HR Business Partner, +46 739 10 99 37.

We warmly welcome your application — please submit it no later than October 26th.

SICK is a world-leading supplier of sensors and sensor solutions for industrial applications. We’re part of SICK AG — a global leader in sensor technology with 10,000 employees across 50 countries and headquarters in Freiburg, Germany. Together, we build technology that makes industries more efficient, intelligent, and safe.

 As a Machine Vision Innovation Center, SICK Linköping develops high-performance cameras and advanced AI-powered software that drives the future of both manufacturing and logistics automation. Whether it’s helping robots pick the right item or enabling high-precision quality control with 2D and 3D vision, our solutions bring clarity, speed, and smart decision-making to complex industrial environments — all driven by a dedicated team of 100 colleagues.

We are very proud of being a healthy and attractive workplace. We have consistently been recognized as one of the best workplaces in Sweden according to the Great Place to Work survey. We actively work to reduce our climate footprint and engage in various initiatives to contribute to society and enhance diversity at our workplace.