News Archive
The group is renamed into Hardware and Artificial Intelligence (HAWAII) Lab! This reflects in a much more appropriate way our research focus, which is on the intersections of various methods from artificial intelligence, machine learning, and hardware architectures. Stay tuned for current and upcoming work on making AI and ML faster, greener, and more robust, based on various hardware architectures, ranging from conventional but beautiful GPUs to emerging hardware concepts based on physical quantities such as photons, electrons and resistance!
Very happy to report that our joint work with Pernice Lab on “Probabilistic Photonic Computing with Chaotic Light” has been accepted for publication at Nature Communications! Find preprint here
Workshop on Embedded ML (WEML) will take place on Nov 29, 2024 at Heidelberg University and is open for registration! Read more
The Computing Systems Group is going to be renamed soon. Stay tuned for updates!
Check out our new blog posts on Walking Noise and LLM Brain Damage!
Invited talk on our work with LLMs at the special session on “Making LLM Faster, Stronger, and more Efficient” at IEEE SOCC 2024 in Dresden, Germany!
ZITI is very happy to welcome Prof. Dr. Grace Li Zhang from TU Darmstadt for a public talk on “Efficient Hardware for Neural Networks”. The talk will take place July 29, 16:00 in the ZITI lecture room (INF350, room U014).
Also seeing the well-known Nebulae supercomputer, previously ranked number 2 in the TOP500 list and apparently still (with some upgrades) in operation!
Conference article on “Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics” accepted for publication at European Conference on Machine Learning in Vilnius! Preprint: link
Conference article on “DeepHYDRA: A Hybrid Deep Learning and DBSCAN-Based Approach to Time-Series Anomaly Detection in Dynamically-Configured Systems” accepted for publication at International Supercomputing Conference in Kyoto! Read more: link
Congrats to Jonas for a post-PhD-defense publication on “GraphScale: Scalable Processing on FPGAs for HBM and Large Graphs”, an extension of his FPL2023 paper! Read more here: link
Kudos to the colleagues from the Khunjerab project on a published article on “Random telegraph noise caracteristic of nonvolatile resistive random access memories based on optical interference principle”! Read more here: link
The 5th Workshop on IoT, Edge, and Mobile for Embedded Machine Learning (ITEM) has accepted to take place in conjunction with ECML-PKDD2024! CfP: www.item-workshop.org
ZITI is very happy to welcome Dr. Georg Hager for a visit on February 5 2024. Dr. Hager will give a public talk on “Performance Engineering with Resource-Based Metrics” at 4 pm in the ZITI lecture room (INF 350, room U014). Read more
Happy to announce that Daniel got his first paper accepted! - “Compressing the Backward Pass of Large-Scale Neural Architectures by Structured Activation Pruning”, at the AccML workshop, collocated with HiPEAC2024 conference. Read the preprint here: link
Two papers to be presented at ITEM workshop (collocated with ECML 2023), and one paper at PMBS workshop (collocated with SC 2023)!
The HiPEAC Info Magazine covers a couple of our PhD students, some in flight and some who already graduated!
New course on “Embedded Machine Learning” for this summer term.
The fourth ITEM workshop is accepted as a full-day workshop at ECML 2023 in Turin, Italy!
Guest lecture at Xi’an University of Technology on “HW and SW support for Embedded Machine Learning”.
The Workshop on Embedded Machine Learning (WEML2023) took place in Heidelberg, after a long COVID break!
Congrats to Torben and Bernhard for an accepted paper on Towards Hardware-Specific Automatic Compression of Neural Networks at the Practical-DL workshop at the AAAI conference! Find the code here: https://github.com/UniHD-CEG/galen
- Additional kudos for bringing a best paper award back home!
Congrats to Hendrik and Bernhard for an accepted paper on “Walking Noise: Understanding Implications of Noisy Computations on Classification Tasks” at the AccML workshop at the HiPEAC conference!
We are co-organizing the Workshop on “Future of FPGAs in HPC and Datacenter”
The next Workshop on Embedded Machine Learning (WEML2023) will take place March 2nd, 2023! Read more: https://www.deepchip.org/weml2023