Bachelor / Master Thesis Assignments

Uploaded March 2024

Computer Architecture Research Student – Edge AI with Event-Based Neural Processing Unit

SNAP is at the forefront of pioneering technology. We want to advance the field of Edge AI through innovative solutions. Our cutting-edge Event-Based Neural Processing Units (NPU) are revolutionizing data processing, providing unprecedented efficiency and speed. Join us to be part of a dynamic team committed to reshaping the future of technology. As a Computer Architecture Research Student, you will work with us in the context of your final graduation project at the university. You will collaborate with Edge AI experts to enhance our event-based NPU capabilities. Your role will involve designing, simulating, benchmarking, and optimizing the processor architecture to ensure maximum efficiency and performance. You will be at the heart of our innovation, contributing to projects that push the boundaries of what is possible in Edge AI.

Key Responsibilities

• Assist in designing and optimizing advanced computer architecture optimizations for our Event-Based NPU.
• Participate in developing and simulating innovative algorithms to improve processing efficiency and speed.
• Evaluate planned innovations on the NPU architecture, suggesting improvements and optimizations.
• (Re)train and/or compile neural Networks for performance on our NPU;
• Engage in performance benchmarking and analysis, documenting and presenting findings to the team
• Stay abreast of the latest trends and advancements in Edge AI and computer architecture.
• Write the thesis for your master course final assignment based on your findings and results

Updated March 2024

The most updated list can be found on the IMEC carrier website. If you are interested in any of those, you can apply directly through the IMEC website or contact me (don’t worry about the duration of the project if it is longer than the time you have).

• Student project: Efficient Audio De-Noising in Neuromorphic Hardware
• Student project: Brain-inspired Learning for Extreme Edge Neuromorphic Computing
• Student project: Sensor fusion on Embedded DNN accelerator
• Student project: Designing Hardware Accelerator for Sparse Transformer Models

Uploaded March 2024

This master thesis project explores the potential of dynamic neural networks (DNNs) in enhancing the performance and efficiency of artificial intelligence (AI) applications within embedded systems. Embedded devices, characterized by their limited computational resources, memory, and energy constraints, necessitate innovative approaches to deploy AI solutions effectively. The project will investigate how DNNs can overcome these limitations with their ability to adapt architecture and computational processes based on input data. By dynamically adjusting their complexity, these networks offer a promising solution to maintaining or enhancing AI application performance under stringent resource constraints. The research will focus on developing methodologies for implementing DNNs in embedded systems, evaluating their performance against traditional static neural networks, and understanding the trade-offs in computational efficiency, energy consumption, and model accuracy.

Required skills

• Python and C programming
• Knowledge about neural networks

Uploaded March 2024

A master thesis project on a RISC-V-based neuromorphic processor aims to explore the design, implementation, and evaluation of a novel computing architecture that merges the efficient, open-source RISC-V instruction set architecture with the principles of neuromorphic computing. This project will focus on leveraging the modularity and extensibility of RISC-V to integrate specialized neuromorphic computing modules, which mimic the neural structures and processing mechanisms of the human brain, to achieve high efficiency and low power consumption in tasks related to artificial intelligence and machine learning. The research will encompass the development of a prototype processor, including the design of custom neuromorphic computing extensions for the RISC-V architecture, the simulation of neural network models on this platform, and a comprehensive analysis of its performance, power efficiency, and potential applications in edge computing and IoT devices. This endeavour will contribute to the advancement of neuromorphic computing technologies and demonstrate the versatility and potential of the RISC-V architecture in addressing the growing demands for energy-efficient AI computation.

Required skills

• Hardware design in FPGA
• Knowledge about neural networks