Probing the limits of fake-quantised neural networks

Introduction

Abstract of the project

Competences

Required:

• Numerical representation formats (integer, floating-point)
• Numerical analysis
• Python programming
• C/C++ programming

Optional:

• Knowledge of the PyTorch deep learning framework
• Knowledge of digital arithmetic (e.g., two's complement, overflow, wraparound)

Character

20% Theory

40% C/C++ and Python coding

40% Deep learning

Professor

Luca Benini

Status: Available

We are looking for 1 Master student. It is possible to complete the project either as a Semester Project or a Master Thesis.

Supervisors: Matteo Spallanzanispmatteo@iis.ee.ethz.ch, Renzo Andri (Huawei RC Zurich)