Koen Goetschalckx
机构: System architect, Axelera AI
每年引用次数
引用次数
引用: 349
H-指数: 7
I10-指数 : 6
出版物: 9
Minimum Energy Quantized Neural Networks
Marian Verhelst , Bert Moons , Nick Van Berckelaer , Koen Goetschalckx
arXiv: Neural and Evolutionary Computing
126
2017
Optimized Hierarchical Cascaded Processing
Koen Goetschalckx , Bert Moons , Steven Lauwereins , Martin Andraud
IEEE Journal on Emerging and Selected Topics in Circuits and Systems 8 ( 4) 884 -894
10
2018
Breaking High-Resolution CNN Bandwidth Barriers With Enhanced Depth-First Execution
Koen Goetschalckx , Marian Verhelst
IEEE Journal on Emerging and Selected Topics in Circuits and Systems 9 ( 2) 323 -331
8
2019
Efficiently Combining SVD, Pruning, Clustering and Retraining for Enhanced Neural Network Compression
Koen Goetschalckx , Bert Moons , Patrick Wambacq , Marian Verhelst
Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning 1 -6
8
2018
11.3 Metis AIPU: A 12nm 15TOPS/W 209.6 TOPS SoC for Cost-and Energy-Efficient Inference at the Edge
Pascal Alexander Hager , Bert Moons , Stefan Cosemans , Ioannis A Papistas
2024 IEEE International Solid-State Circuits Conference (ISSCC) 67 212 -214
2024
DepFiN: A 12nm, 3.8 TOPs depth-first CNN processor for high res. image processing
Koen Goetschalckx , Marian Verhelst
2021 Symposium on VLSI Circuits 1 -2
36
2021
Depfin: a 12-nm depth-first, high-resolution CNN processor for IO-efficient inference
Koen Goetschalckx , Fengfeng Wu , Marian Verhelst
IEEE Journal of Solid-State Circuits 58 ( 5) 1425 -1435
5
2022
Optimizing Embedded Vision Efficiency across the Hardware-dataflow-algorithm Stack
Koen Goetschalckx ,
2023