Daniel Becking

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 11

Top Topics

Embedded Zerotree Wavelet

Quantization Error

Top Venues

IEEE Open J. Circuits Syst.

Publications

Daniel Becking, Karsten Müller, Paul Haase, Heiner Kirchhoffer, Gerhard Tech, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
Neural Network Coding of Difference Updates for Efficient Distributed Learning Communication. IEEE Trans. Multim. 26 (2024)
Daniel Becking, Heiner Kirchhoffer, Gerhard Tech, Paul Haase, Karsten Müller, Heiko Schwarz, Wojciech Samek
Adaptive Differential Filters for Fast and Communication-Efficient Federated Learning. CVPR Workshops (2022)
Daniel Becking, Heiner Kirchhoffer, Gerhard Tech, Paul Haase, Karsten Müller, Heiko Schwarz, Wojciech Samek
Adaptive Differential Filters for Fast and Communication-Efficient Federated Learning. CoRR (2022)
Gerhard Tech, Paul Haase, Daniel Becking, Heiner Kirchhoffer, Karsten Müller, Jonathan Pfaff, Heiko Schwarz, Wojciech Samek, Detlev Marpe, Thomas Wiegand
History Dependent Significance Coding for Incremental Neural Network Compression. ICIP (2022)
Simon Wiedemann, Suhas Shivapakash, Daniel Becking, Pablo Wiedemann, Wojciech Samek, Friedel Gerfers, Thomas Wiegand
FantastIC4: A Hardware-Software Co-Design Approach for Efficiently Running 4Bit-Compact Multilayer Perceptrons. IEEE Open J. Circuits Syst. 2 (2021)
Paul Haase, Daniel Becking, Heiner Kirchhoffer, Karsten Müller, Heiko Schwarz, Wojciech Samek, Detlev Marpe, Thomas Wiegand
Encoder Optimizations For The NNR Standard On Neural Network Compression. ICIP (2021)
Daniel Becking, Maximilian Dreyer, Wojciech Samek, Karsten Müller, Sebastian Lapuschkin
: Explainability-Driven Quantization for Low-Bit and Sparse DNNs. CoRR (2021)
Daniel Becking, Maximilian Dreyer, Wojciech Samek, Karsten Müller, Sebastian Lapuschkin
: Explainability-Driven Quantization for Low-Bit and Sparse DNNs. xxAI@ICML (2020)
Simon Wiedemann, Suhas Shivapakash, Pablo Wiedemann, Daniel Becking, Wojciech Samek, Friedel Gerfers, Thomas Wiegand
FantastIC4: A Hardware-Software Co-Design Approach for Efficiently Running 4bit-Compact Multilayer Perceptrons. CoRR (2020)
Arturo Marbán, Daniel Becking, Simon Wiedemann, Wojciech Samek
Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T). CVPR Workshops (2020)
Arturo Marbán, Daniel Becking, Simon Wiedemann, Wojciech Samek
Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T). CoRR (2020)