Supervised Machine Learning with a Novel Kernel Density Estimator

Oct 16, 2007

Yen-Jen Oyang, Darby Tien-Hao Chang, Yu-Yen Ou, Hao-Geng Hung, Chih-Peng Wu, Chien-Yu Chen

In recent years, kernel density estimation has been exploited by computer scientists to model machine learning problems. The kernel density estimation based approaches are of interest due to the low time complexity of either O(n) or O(n*log(n)) for constructing a classifier, where n is the number of sampling instances. Concerning design of kernel density estimators, one essential issue is how fast the pointwise mean square error (MSE) and/or the integrated mean square error (IMSE) diminish as the number of sampling instances increases. In this article, it is shown that with the proposed kernel function it is feasible to make the pointwise MSE of the density estimator converge at O(n^-2/3) regardless of the dimension of the vector space, provided that the probability density function at the point of interest meets certain conditions.
Oct 16, 2007

Yen-Jen Oyang, Darby Tien-Hao Chang, Yu-Yen Ou, Hao-Geng Hung, Chih-Peng Wu, Chien-Yu Chen

* The new version includes an additional theorem, Theorem 3

**Click to Read Paper and Get Code**

Improving Orbit Prediction Accuracy through Supervised Machine Learning

Jan 15, 2018

Hao Peng, Xiaoli Bai

Jan 15, 2018

Hao Peng, Xiaoli Bai

* 30 pages, 21 figures, 4 tables, Preprint submitted to Advances in Space Research, on December 14, 2017

**Click to Read Paper and Get Code**

* Accepted by IJCAI 2015

**Click to Read Paper and Get Code**

Backpropagating through Structured Argmax using a SPIGOT

May 12, 2018

Hao Peng, Sam Thomson, Noah A. Smith

May 12, 2018

Hao Peng, Sam Thomson, Noah A. Smith

* ACL 2018

**Click to Read Paper and Get Code**

"You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debates

Feb 23, 2018

Chenhao Tan, Hao Peng, Noah A. Smith

Feb 23, 2018

Chenhao Tan, Hao Peng, Noah A. Smith

* 10 pages, 5 figures, to appear in Proceedings of WWW 2018, data and more at https://chenhaot.com/papers/debate-quotes.html

**Click to Read Paper and Get Code**

Asynchronous Distributed Variational Gaussian Processes for Regression

Jun 12, 2017

Hao Peng, Shandian Zhe, Yuan Qi

Jun 12, 2017

Hao Peng, Shandian Zhe, Yuan Qi

* International Conference on Machine Learning 2017

**Click to Read Paper and Get Code**

Deep Multitask Learning for Semantic Dependency Parsing

Apr 25, 2017

Hao Peng, Sam Thomson, Noah A. Smith

Apr 25, 2017

Hao Peng, Sam Thomson, Noah A. Smith

* Proceedings of ACL 2017

**Click to Read Paper and Get Code**

A Convolutional Attention Network for Extreme Summarization of Source Code

May 25, 2016

Miltiadis Allamanis, Hao Peng, Charles Sutton

May 25, 2016

Miltiadis Allamanis, Hao Peng, Charles Sutton

* Code, data and visualization at http://groups.inf.ed.ac.uk/cup/codeattention/

**Click to Read Paper and Get Code**

Despite the tremendous empirical success of neural models in natural language processing, many of them lack the strong intuitions that accompany classical machine learning approaches. Recently, connections have been shown between convolutional neural networks (CNNs) and weighted finite state automata (WFSAs), leading to new interpretations and insights. In this work, we show that some recurrent neural networks also share this connection to WFSAs. We characterize this connection formally, defining rational recurrences to be recurrent hidden state update functions that can be written as the Forward calculation of a finite set of WFSAs. We show that several recent neural models use rational recurrences. Our analysis provides a fresh view of these models and facilitates devising new neural architectures that draw inspiration from WFSAs. We present one such model, which performs better than two recent baselines on language modeling and text classification. Our results demonstrate that transferring intuitions from classical models like WFSAs can be an effective approach to designing and understanding neural models.

* EMNLP 2018

* EMNLP 2018

**Click to Read Paper and Get Code**
Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource

Apr 17, 2018

Qiang Ning, Hao Wu, Haoruo Peng, Dan Roth

Apr 17, 2018

Qiang Ning, Hao Wu, Haoruo Peng, Dan Roth

* 13 pages, 3 figures, accepted by NAACL'18

**Click to Read Paper and Get Code**

Learning Joint Semantic Parsers from Disjoint Data

Apr 17, 2018

Hao Peng, Sam Thomson, Swabha Swayamdipta, Noah A. Smith

Apr 17, 2018

Hao Peng, Sam Thomson, Swabha Swayamdipta, Noah A. Smith

* NAACL 2018

**Click to Read Paper and Get Code**

View Extrapolation of Human Body from a Single Image

Apr 11, 2018

Hao Zhu, Hao Su, Peng Wang, Xun Cao, Ruigang Yang

Apr 11, 2018

Hao Zhu, Hao Su, Peng Wang, Xun Cao, Ruigang Yang

* Accepted to CVPR 2018

**Click to Read Paper and Get Code**

Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications

Mar 24, 2018

Zheng Qin, Zhaoning Zhang, Shiqing Zhang, Hao Yu, Yuxing Peng

Mar 24, 2018

Zheng Qin, Zhaoning Zhang, Shiqing Zhang, Hao Yu, Yuxing Peng

* 8 pages, 4 figures

**Click to Read Paper and Get Code**

Computer-aided diagnosis in histopathological images of the endometrium using a convolutional neural network and attention mechanisms

Apr 24, 2019

Hao Sun, Xianxu Zeng, Tao Xu, Gang Peng, Yutao Ma

Apr 24, 2019

Hao Sun, Xianxu Zeng, Tao Xu, Gang Peng, Yutao Ma

* 22 pages, 8 figures, and 4 tables

**Click to Read Paper and Get Code**

Graph Convolutional Neural Networks via Motif-based Attention

Nov 11, 2018

Hao Peng, Jianxin Li, Qiran Gong, Yuanxing Ning, Lihong Wang

Nov 11, 2018

Hao Peng, Jianxin Li, Qiran Gong, Yuanxing Ning, Lihong Wang

**Click to Read Paper and Get Code**

Fast K-Means Clustering with Anderson Acceleration

May 27, 2018

Juyong Zhang, Yuxin Yao, Yue Peng, Hao Yu, Bailin Deng

May 27, 2018

Juyong Zhang, Yuxin Yao, Yue Peng, Hao Yu, Bailin Deng

**Click to Read Paper and Get Code**

Deep Learning for Sensor-based Activity Recognition: A Survey

Dec 14, 2017

Jindong Wang, Yiqiang Chen, Shuji Hao, Xiaohui Peng, Lisha Hu

Dec 14, 2017

Jindong Wang, Yiqiang Chen, Shuji Hao, Xiaohui Peng, Lisha Hu

* 10 pages, 2 figures, and 5 tables; submitted to Pattern Recognition Letters (second revision)

**Click to Read Paper and Get Code**

NAS-FCOS: Fast Neural Architecture Search for Object Detection

Jun 12, 2019

Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen

Jun 12, 2019

Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen

* 9 pages, 9 figures

**Click to Read Paper and Get Code**

Global Momentum Compression for Sparse Communication in Distributed SGD

May 30, 2019

Shen-Yi Zhao, Yin-Peng Xie, Hao Gao, Wu-Jun Li

May 30, 2019

Shen-Yi Zhao, Yin-Peng Xie, Hao Gao, Wu-Jun Li

**Click to Read Paper and Get Code**

Text Generation with Exemplar-based Adaptive Decoding

Apr 10, 2019

Hao Peng, Ankur P. Parikh, Manaal Faruqui, Bhuwan Dhingra, Dipanjan Das

Apr 10, 2019

Hao Peng, Ankur P. Parikh, Manaal Faruqui, Bhuwan Dhingra, Dipanjan Das

* NAACL 2019

**Click to Read Paper and Get Code**