20 citations · 36 across the 18 of their papers we have counts for
10 papers · 1 filter
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…
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…
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…
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…