20 citations · 36 across the 18 of their papers we have counts for
20 papers
Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference
Niklas Summ, Xiao Wang, Hendrik Borras +2
The energy efficiency of analog computing makes it one of the most promising candidates for deploying resource-intensive machine learning workloads on constrained platforms such as…
Constrained Co-Design for Photonic Bayesian Neural Networks
Hendrik Borras, Xiao Wang, Bernhard Klein +4
Classical neural networks frequently produce overconfident predictions on ambiguous or out-of-distribution (OOD) data, a liability that grows with each AI system deployed in safety…
A Tabular Schedule Abstraction for Communication-Aware Evaluation of Pipeline-Parallel LLM Training
Daniel Barley, Jonathan Leis, Benjamin Klenk +1
Pipeline parallelism is a key technique for distributed training of large language models because it reduces per-device parameter and activation memory. However, comparing pipeline…
Probabilistic Photonic Computing
Frank Brückerhoff-Plückelmann, Anna P. Ovvyan, Akhil Varri +8
Probabilistic computing excels in approximating combinatorial problems and modelling uncertainty. However, using conventional deterministic hardware for probabilistic models is cha…
Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification
Hendrik Borras, Yong Wu, Bernhard Klein +1
Bayesian Neural Networks (BNNs) provide principled uncertainty quantification but suffer from substantial computational and memory overhead compared to deterministic networks. Whil…
Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles
Sophie Steger, Christian Knoll, Bernhard Klein +2
Bayesian inference in function space has gained attention due to its robustness against overparameterization in neural networks. However, approximating the infinite-dimensional fun…
Less Memory Means smaller GPUs: Backpropagation with Compressed Activations
Daniel Barley, Holger Fröning
The ever-growing scale of deep neural networks (DNNs) has lead to an equally rapid growth in computational resource requirements. Many recent architectures, most prominently Large…
DeepHYDRA: Resource-Efficient Time-Series Anomaly Detection in Dynamically-Configured Systems
Franz Kevin Stehle, Wainer Vandelli, Giuseppe Avolio +2
Anomaly detection in distributed systems such as High-Performance Computing (HPC) clusters is vital for early fault detection, performance optimisation, security monitoring, reliab…
GraphMatch: Subgraph Query Processing on FPGAs
Jonas Dann, Tobias Götz, Daniel Ritter +2
Efficiently finding subgraph embeddings in large graphs is crucial for many application areas like biology and social network analysis. Set intersections are the predominant and mo…
Probabilistic Photonic Computing with Chaotic Light
Frank Brückerhoff-Plückelmann, Hendrik Borras, Bernhard Klein +10
Biological neural networks effortlessly tackle complex computational problems and excel at predicting outcomes from noisy, incomplete data, a task that poses significant challenges…
Implications of Noise in Resistive Memory on Deep Neural Networks for Image Classification
Yannick Emonds, Kai Xi, Holger Fröning
Resistive memory is a promising alternative to SRAM, but is also an inherently unstable device that requires substantial effort to ensure correct read and write operations. To avoi…
Compressing the Backward Pass of Large-Scale Neural Architectures by Structured Activation Pruning
Daniel Barley, Holger Fröning
The rise of Deep Neural Networks (DNNs) has led to an increase in model size and complexity, straining the memory capacity of GPUs. Sparsity in DNNs, characterized as structural or…
On Performance Analysis of Graphcore IPUs: Analyzing Squared and Skewed Matrix Multiplication
S. -Kazem Shekofteh, Christian Alles, Nils Kochendörfer +1
In recent decades, High Performance Computing (HPC) has undergone significant enhancements, particularly in the realm of hardware platforms, aimed at delivering increased processin…
On the Non-Associativity of Analog Computations
Lisa Kuhn, Bernhard Klein, Holger Fröning
The energy efficiency of analog forms of computing makes it one of the most promising candidates to deploy resource-hungry machine learning tasks on resource-constrained system suc…
Reducing Memory Requirements for the IPU using Butterfly Factorizations
S. -Kazem Shekofteh, Christian Alles, Holger Fröning
High Performance Computing (HPC) benefits from different improvements during last decades, specially in terms of hardware platforms to provide more processing power while maintaini…
Towards Hardware-Specific Automatic Compression of Neural Networks
Torben Krieger, Bernhard Klein, Holger Fröning
Compressing neural network architectures is important to allow the deployment of models to embedded or mobile devices, and pruning and quantization are the major approaches to comp…
Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics
Hendrik Borras, Bernhard Klein, Holger Fröning
Deep neural networks are extremely successful in various applications, however they exhibit high computational demands and energy consumption. This is exacerbated by stuttering tec…
GraphScale: Scalable Bandwidth-Efficient Graph Processing on FPGAs
Jonas Dann, Daniel Ritter, Holger Fröning
Recent advances in graph processing on FPGAs promise to alleviate performance bottlenecks with irregular memory access patterns. Such bottlenecks challenge performance for a growin…
Understanding Cache Boundness of ML Operators on ARM Processors
Bernhard Klein, Christoph Gratl, Manfred Mücke +1
Machine Learning compilers like TVM allow a fast and flexible deployment on embedded CPUs. This enables the use of non-standard operators, which are common in ML compression techni…
Resource-Efficient Neural Networks for Embedded Systems
Wolfgang Roth, Günther Schindler, Bernhard Klein +5
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-e…