| Robust and communication-efficient federated learning from non-iid data F Sattler, S Wiedemann, KR Müller, W Samek IEEE transactions on neural networks and learning systems 31 (9), 3400-3413, 2019 | 816 | 2019 |
| Sparse binary compression: Towards distributed deep learning with minimal communication F Sattler, S Wiedemann, KR Müller, W Samek 2019 International Joint Conference on Neural Networks (IJCNN), 1-8, 2019 | 146 | 2019 |
| Pruning by explaining: A novel criterion for deep neural network pruning SK Yeom, P Seegerer, S Lapuschkin, A Binder, S Wiedemann, KR Müller, ... Pattern Recognition 115, 107899, 2021 | 104 | 2021 |
| DeepCABAC: A universal compression algorithm for deep neural networks S Wiedemann, H Kirchhoffer, S Matlage, P Haase, A Marban, T Marinč, ... IEEE Journal of Selected Topics in Signal Processing 14 (4), 700-714, 2020 | 64 | 2020 |
| Compact and computationally efficient representation of deep neural networks S Wiedemann, KR Müller, W Samek IEEE transactions on neural networks and learning systems 31 (3), 772-785, 2019 | 57 | 2019 |
| Entropy-constrained training of deep neural networks S Wiedemann, A Marban, KR Müller, W Samek 2019 International Joint Conference on Neural Networks (IJCNN), 1-8, 2019 | 28 | 2019 |
| DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression S Wiedemann, H Kirchhoffer, S Matlage, P Haase, A Marban, T Marinc, ... arXiv preprint arXiv:1905.08318, 2019 | 16 | 2019 |
| Learning sparse & ternary neural networks with entropy-constrained trained ternarization (EC2T) A Marban, D Becking, S Wiedemann, W Samek Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020 | 10 | 2020 |
| Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training S Wiedemann, T Mehari, K Kepp, W Samek Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020 | 9 | 2020 |
| FantastIC4: a hardware-software co-design approach for efficiently running 4bit-compact multilayer perceptrons S Wiedemann, S Shivapakash, D Becking, P Wiedemann, W Samek, ... IEEE Open Journal of Circuits and Systems 2, 407-419, 2021 | 8 | 2021 |
| Deepcabac: Plug & play compression of neural network weights and weight updates D Neumann, F Sattler, H Kirchhoffer, S Wiedemann, K Müller, H Schwarz, ... 2020 IEEE International Conference on Image Processing (ICIP), 21-25, 2020 | 8 | 2020 |
| Dependent scalar quantization for neural network compression P Haase, H Schwarz, H Kirchhoffer, S Wiedemann, T Marinc, A Marban, ... 2020 IEEE International Conference on Image Processing (ICIP), 36-40, 2020 | 8 | 2020 |
| Neural Network Representation Formats S Matlage, P Haase, H Kirchhoffer, K Mueller, W Samek, S Wiedemann, ... US Patent App. 17/711,569, 2022 | 1 | 2022 |
| Pruning and/or quantizing machine learning predictors W Samek, S Lapuschkin, S Wiedemann, P Seegerer, Y Seul-Ki, K Mueller, ... US Patent App. 17/556,657, 2022 | 1 | 2022 |
| Compact and efficient representations of deep neural networks. S Wiedemann Technical University of Berlin, Germany, 2022 | | 2022 |
| Methods and apparatuses for compressing parameters of neural networks P Haase, AM GONZALEZ, H Kirchhoffer, T Marinc, D Marpe, S Matlage, ... US Patent App. 17/478,676, 2022 | | 2022 |
| Concepts for distributed learning of neural networks and/or transmission of parameterization updates therefor W Samek, S Wiedemann, F Sattler, KR Müller, T Wiegand US Patent App. 17/096,887, 2021 | | 2021 |
Wojciech SamekProfessor at TU Berlin, Head of AI Department at Fraunhofer HHI, BIFOLD FellowVerified email at hhi.fraunhofer.de
