Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.
2021Pruning by explaining: A novel criterion for deep neural network pruning
Yeom, S.-K.; Seegerer, P.; Lapuschkin, S.; Binder, A.; Wiedemann, S.; Müller, K.-R.; Samek, W.
Zeitschriftenaufsatz
2020Compact and Computationally Efficient Representation of Deep Neural Networks
Wiedemann, S.; Müller, K.-R.; Samek, W.
Zeitschriftenaufsatz
2020Deepcabac: Plug & Play Compression of Neural Network Weights and Weight Updates
Neumann, D.; Sattler, F.; Kirchhoffer, H.; Wiedemann, S.; Müller, K.; Schwarz, H.; Wiegand, T.; Marpe, D.; Samek, W.
Konferenzbeitrag
2020DeepCABAC: A universal compression algorithm for deep neural networks
Wiedemann, S.; Kirchhoffer, H.; Wiegand, T.; Marpe, D.; Samek, W.; Matlage, S.; Haase, P.; Marban, A.; Marinc, T.; Neumann, D.; Nguyen, T.; Schwarz, H.
Zeitschriftenaufsatz
2020Dependent Scalar Quantization for Neural Network Compression
Haase, P.; Schwarz, H.; Kirchhoffer, H.; Wiedemann, S.; Marinc, T.; Marban, A.; Müller, K.; Samek, W.; Marpe, D.; Wiegand, T.
Konferenzbeitrag
2020Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training
Wiedemann, S.; Mehari, T.; Kepp, K.; Samek, W.
Konferenzbeitrag
2020Learning sparse ternary neural networks with Entropy-Constrained Trained Ternarization (EC2T)
Marban, A.; Becking, D.; Wiedemann, S.; Samek, W.
Konferenzbeitrag
2020Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data
Sattler, F.; Wiedemann, S.; Müller, K.-R.; Samek, W.
Zeitschriftenaufsatz
2019Neural network representation
Müller, Klaus-Robert; Samek, Wojciech; Wiedemann, Simon; Wiegand, Thomas
Patent