/Student project: Bio-inspired efficient high-resolution visual processing for edge AI

Student project: Bio-inspired efficient high-resolution visual processing for edge AI

Research & development - Eindhoven | More than two weeks ago

Student project: Bio-inspired efficient high-resolution visual processing for edge AI

This project aims to develop a human perception-inspired solution towards processing high-resolution vision sensors on a resource constraint EdgeAI processor.

What you will do

High-resolution vision is crucial for accurate object recognition and detection in real-world applications like autonomous driving, remote sensing and medical imaging. However, the high-resolution input limits the use of existing neural network architectures on EdgeAI processors due to memory constraints. Interestingly, humans efficiently process high-resolution inputs by focusing only on selective parts of the input space. Therefore, we seek to develop an algorithm inspired by human perception for efficient high-resolution visual processing that meets the hardware-related requirements of SENECA [1], imec's low-power neuromorphic processor.

Tasks:

  1. Understand the target application and bio-inspired algorithms for high-resolution visual processing [2, 3] through literature reviews.
  2. Design and implement the bio-inspired neural network algorithm for the selected application and the provided EdgeAI processor.
  3. Perform benchmarking on the performance of the algorithm.

The project can be divided into three phases: 1) single object recognition and classification, 2) multi-object detection, and 3) algorithm optimization for event-based processing. The student is expected at least to demonstrate the results for phase one of the project.

[1] Yousefzadeh, et al., "SENeCA: Scalable Energy-efficient Neuromorphic Computer Architecture", AICAS 2022.
[2] Mnih, et al., "Recurrent models of visual attention", NeurIPS 2014.
[3] Elsayed, et al., "Saccader: Improving accuracy of hard attention models for vision", NeurIPS 2019.

What we do for you

Imec is one of the world's leading research institutes in micro and nano-electronics. The imec-NL lab at Holst Centre is a center of excellence in designing nano-electronics solutions for the Internet of Things and healthcare applications. In this internship project, you will be working on a cutting-edge research project under the supervision of expert researchers from diverse backgrounds. The outputs from the project may be published in high-impact journals/conferences (subject to the quality of the work). Imec-NL provides the required equipment, access to lab facilities, a workplace in the Holst Centre at High Tech Campus, and a monthly allowance for running/living expenses during the internship.

Who you are

  • M.Sc./Ph.D. students with a relevant background (non-European students are only eligible if they study in the Netherlands).
  • Available for 9 months, preferably 12 months.
  • Have excellent programming skills in Python.
  • Have previous experiences  on the deployment of neural networks for image recognition and detection.
  • Knowledge of programming in deep learning frameworks (e.g., TensorFlow, PyTorch).
  • Are in good command of spoken and written English.
  • Motivated student, good communicator, easy collaborator, and eager to work independently and expand knowledge in the field.
Who we are

Accepteer marketing-cookies om deze content weer te geven.

Cookie-instellingen
imec inside out

Accepteer marketing-cookies om deze content weer te geven.

Cookie-instellingen
Vacatures

Verzend deze job naar jouw e-mailadres