activity
20202026
most citedTowards Explainable Bit Error Tolerance of Resistive RAM-Based Binarized Neural Networks

3 citations · 8 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Diagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum Description Length

Sebastian Buschjäger, Michael Frichert, Daniel Kuhe +1

Multichannel time-series classification commonly assumes synchronized sensor streams, although latency, clock drift, and preprocessing can introduce relative delays during data col…

cs.LG2023★ 1 cited

Fast Inference of Tree Ensembles on ARM Devices

Simon Koschel, Sebastian Buschjäger, Claudio Lucchese +1

With the ongoing integration of Machine Learning models into everyday life, e.g. in the form of the Internet of Things (IoT), the evaluation of learned models becomes more and more…

cs.LG2021★ 1 cited

There is no Double-Descent in Random Forests

Sebastian Buschjäger, Katharina Morik

Random Forests (RFs) are among the state-of-the-art in machine learning and offer excellent performance with nearly zero parameter tuning. Remarkably, RFs seem to be impervious to…

cs.LG2021★ 1 cited

Bit Error Tolerance Metrics for Binarized Neural Networks

Sebastian Buschjäger, Jian-Jia Chen, Kuan-Hsun Chen +5

To reduce the resource demand of neural network (NN) inference systems, it has been proposed to use approximate memory, in which the supply voltage and the timing parameters are tu…

cs.LG2020

Very Fast Streaming Submodular Function Maximization

Sebastian Buschjäger, Philipp-Jan Honysz, Lukas Pfahler +1

Data summarization has become a valuable tool in understanding even terabytes of data. Due to their compelling theoretical properties, submodular functions have been in the focus o…

cs.LG2020★ 3 cited

Towards Explainable Bit Error Tolerance of Resistive RAM-Based Binarized Neural Networks

Sebastian Buschjäger, Jian-Jia Chen, Kuan-Hsun Chen +6

Non-volatile memory, such as resistive RAM (RRAM), is an emerging energy-efficient storage, especially for low-power machine learning models on the edge. It is reported, however, t…