Project Overview

Project Code: CIT 03

Project name:

Brain-inspired Computing for Edge AI

TUM Department:

CIT - Electrical and Computer Engineering

TUM Chair / Institute:

Professorship for AI Processor Design

Research area:

Computer Engineering, Circuits, AI, Deep learning

Student background:

Computer EngineeringComputer Science/ InformaticsPhysics

Further disciplines:

Planned project location: 

Munich (Garching Campus)
Munich Institute of Robotics and Machine Intelligence (MIRMI) near Olympiapark München

Project Supervisor - Contact Details


Title:

Prof. Dr.-Ing.

Given name:

Hussam

Family name:

Amrouch

E-mail:

amrouch@tum.de

Phone:

0000

Additional Project Supervisor - Contact Details


Title:

Given name:

Family name:

E-mail:

Phone:

Additional Project Supervisor - Contact Details


Title:

Given name:

Family name:

E-mail:

Phone:

Project Description


Project description:

Edge AI is propelling a wide array of applications, from autonomous vehicles to personalized healthcare. In this project, students will learn the latest advancements in edge AI. The project comes with highly interdisciplinary research that spans from technology to architecture, culminating in innovative AI algorithms and student can select the key research area that he/she want to dive in. student will explore novel architectures that transcend the von Neumann computing paradigm, in conjunction with brain-inspired algorithms. Further, the project will delve into the use of cutting-edge emerging beyond-CMOS technology in 3D integration for ultra-dense brain-inspired computing. The vital role of technology/algorithm co-optimization in enhancing reliability will be covered in detail.

Students will do one or multiple of the following tasks:

- implement and simulate circuits in SPICE that are inspired
- implement and simulate hardware design for AI and deep learning acceleration in RTL
- implement and simulate hardware accelerators in FPGA
- implement and simulate processor (RISC-V) after extending it with special instructions to accelerate AI workloads.

Working hours per week planned:

Mon-Fri, ca. 40 hrs./week

Prerequisites


Required study level minimum (at time of TUM PREP project start):

3 years of bachelor studies completed

Subject related:

Other:

  • Keine Stichwörter