Master Thesis: Optimization of Machine Learning Models

Job Description

Date: Oct 10, 2019

Background

Mobile networks are used all over the world and are the corner stone for the networked society, where everything shall be connected. To support the vast amount and diversity of data expected in future networks, Ericsson are developing products to drive and support the networked society. The subjects for Master Thesis are defined to investigate and develop algorithms, architecture, tools etc. to support huge increase of speech, data and massive IoT for Radio Access Networks.
 

Thesis Description

When using machine learning in resource constrained embedded systems a need arises to optimize the machine learning models, e.g. with respect to the memory used by the models, the CPU usage when training and predicting.

 

The thesis work is proposed to cover:

 

  • Explore methods to optimize machine learning models, considering that the optimization step also will be performed in the embedded system itself and thus needs to be optimized and will be resource constrained.
  • Investigate how these optimization methods can be implemented and deployed in a resource constrained embedded system, e.g. considering implementation language and dependencies to possible third-party components, e.g. existing open source libraries.

 

The thesis will be concluded with a result presentation for the Ericsson team.

 

Qualifications

This project aims at students in electrical engineering, computer science, computer engineering or similar.

Extent

1-2 students, 30hp each

Location

Ericsson AB Mjärdevi, Linköping

Preferred Starting Date

Spring 2020

 

For any questions or enquiries, please contact recruiter Sarah Lashari, sarah.lashari@ericsson.com 

Last day of application is 10th of November 2019

 

 

Ericsson provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetics.

Ericsson complies with applicable country, state and all local laws governing nondiscrimination in employment in every location across the world in which the company has facilities. In addition, Ericsson supports the UN Guiding Principles for Business and Human Rights and the United Nations Global Compact.

This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, training and development.

Ericsson expressly prohibits any form of workplace harassment based on race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetic information.

 

Primary country and city: Sweden (SE) || || Linköping || R&D

Req ID: 302941