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

iMEC
December 02, 2022
Contact:N/A
Offerd Salary:Negotiation
Location:N/A
Working address:N/A
Contract Type:Other
Working Time:Negotigation
Working type:N/A
Job Ref.:N/A
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:

  • Understand the target application and bio-inspired algorithms for high-resolution visual processing 2, 3 through literature reviews.
  • Design and implement the bio-inspired neural network algorithm for the selected application and the provided EdgeAI processor.
  • 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.
  • From this employer

    Recent blogs

    Recent news