198 citations
- Duke UniversityUS37 papers
- Duke University HospitalUS5 papers
- Massachusetts Institute of TechnologyUS3 papers
- Peking UniversityCN3 papers
- Tsinghua UniversityCN3 papers
- A. Alikhanyan National LaboratoryAM2 papers
- Brookhaven National LaboratoryUS2 papers
- Central China Normal UniversityCN2 papers
- Chinese Academy of SciencesCN2 papers
- Columbia UniversityUS2 papers
- Department of Mathematical SciencesRU2 papers
- Duquesne UniversityUS2 papers
10 papers · 1 filter
Cyclostationary Statistical Models and Algorithms for Anomaly Detection Using Multi-Modal Data
Taposh Banerjee, Gene Whipps, Prudhvi Gurram +1
A framework is proposed to detect anomalies in multi-modal data. A deep neural network-based object detector is employed to extract counts of objects and sub-events from the data.…
Cover Song Synthesis by Analogy
Christopher J. Tralie
In this work, we pose and address the following "cover song analogies" problem: given a song A by artist 1 and a cover song A' of this song by artist 2, and given a different song…
ASIC Implementation of Time-Domain Digital Backpropagation with Deep-Learned Chromatic Dispersion Filters
Christoffer Fougstedt, Christian Häger, Lars Svensson +2
We consider time-domain digital backpropagation with chromatic dispersion filters jointly optimized and quantized using machine-learning techniques. Compared to the baseline implem…
Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
Yingzhou Li, Xiuyuan Cheng, Jianfeng Lu
Deep networks, especially convolutional neural networks (CNNs), have been successfully applied in various areas of machine learning as well as to challenging problems in other scie…
Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning
Wei Zhu, Qiang Qiu, Bao Wang +3
Deep neural networks (DNNs) typically have enough capacity to fit random data by brute force even when conventional data-dependent regularizations focusing on the geometry of the f…
DNN or k-NN: That is the Generalize vs. Memorize Question
Gilad Cohen, Guillermo Sapiro, Raja Giryes
This paper studies the relationship between the classification performed by deep neural networks (DNNs) and the decision of various classical classifiers, namely k-nearest neighbou…