79 citations
- University of AmsterdamNL18 papers
- Qualcomm (United States)US11 papers
- Market MattersUS4 papers
- University of California, IrvineUS4 papers
- Amsterdam University of Applied SciencesNL3 papers
- Amsterdam University of the ArtsNL3 papers
- The University of Texas at AustinUS3 papers
- École Polytechnique Fédérale de LausanneCH2 papers
- Indian Institute of Science BangaloreIN2 papers
- Indian Institute of Technology KanpurIN2 papers
- Intel (United States)US2 papers
- Shandong University of Political Science and LawCN2 papers
10 papers · 1 filter
Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks
Andrey Kuzmin, Markus Nagel, Saurabh Pitre +3
The success of deep neural networks in many real-world applications is leading to new challenges in building more efficient architectures. One effective way of making networks more…
Capacity scaling in a Non-coherent Wideband Massive SIMO Block Fading Channel
Felipe Gomez-Cuba, Mainak Chowdhury, Alexandros Manolakos +2
The scaling of coherent and non-coherent channel capacity is studied in a single-input multiple-output (SIMO) block Rayleigh fading channel as both the bandwidth and the number of…
Feedback Recurrent AutoEncoder
Yang Yang, Guillaume Sautière, J. Jon Ryu +1
In this work, we propose a new recurrent autoencoder architecture, termed Feedback Recurrent AutoEncoder (FRAE), for online compression of sequential data with temporal dependency.…
Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning
Hyoungwoo Park, Sungrack Yun, Jungyun Eum +2
This paper considers a semi-supervised learning framework for weakly labeled polyphonic sound event detection problems for the DCASE 2019 challenge's task4 by combining both the tr…
Massive Access for Future Wireless Communication Systems
Yongpeng Wu, Xiqi Gao, Shidong Zhou +3
Multiple access technology played an important role in wireless communication in the last decades: it increases the capacity of the channel and allows different users to access the…
Batch-Shaping for Learning Conditional Channel Gated Networks
Babak Ehteshami Bejnordi, Tijmen Blankevoort, Max Welling
We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learnin…