People

Matthijs Van keirsbilck

Matthijs is a Research Scientist at NVIDIA, working on foundations of neural networks and machine learning.

He has a broad field of interest, and is currently working on efficient neural network architecture design, leveraging structural sparsity and quantization.

He has a background in Electrical Engineering, studying at KU Leuven (Belgium) and TU Munich (Germany).

Research Area(s)
Algorithms and Numerical Methods
Circuits and VLSI Design
Computer Architecture
Main Field of Interest
Artificial Intelligence and Machine Learning
Google Scholar
https://scholar.google.com/citations?user=qphCQwQAAAAJ&h=

Publications

2022

Deep Learning-Based Synchronization for Uplink NB-IoT
Fayçal Aït Aoudia , Jakob Hoydis, Sebastian Cammerer, Matthijs Van keirsbilck, Alex Keller
IEEE Global Communications Conference 2022
Artificial Neural Networks generated by Low Discrepancy Sequences
Matthijs Van keirsbilck, Alex Keller
arxiv link

2021

Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices
Goncalo Mordido, Matthijs Van keirsbilck, Alex Keller
Interspeech 2021

2020

Monte Carlo Gradient Quantization
Goncalo Mordido, Matthijs Van keirsbilck, Alex Keller
CVPR2020 Workshop

2019

Instant Quantization of neural networks using Monte Carlo Methods
Gonçalo Mordido, Matthijs Van keirsbilck, Alex Keller
NeurIPS 2019 EMC2 workshop (IEEExplore)
Rethinking full connectivity in recurrent neural networks
Matthijs Van keirsbilck, Alex Keller, Xiaodong Yang
arxiv paper