Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

LANCE: efficient low-precision quantized Winograd convolution for neural networks based on graphics processing units

Mar 19, 2020
Guangli Li, Lei Liu, Xueying Wang, Xiu Ma, Xiaobing Feng

Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry. In this paper, we propose an efficient low-precision quantized Winograd convolution algorithm, called LANCE, which combines the advantages of fast convolution and quantization techniques. By embedding linear quantization operations into the Winograd-domain, the fast convolution can be performed efficiently under low-precision computation on graphics processing units. We test neural network models with LANCE on representative image classification datasets, including SVHN, CIFAR, and ImageNet. The experimental results show that our 8-bit quantized Winograd convolution improves the performance by up to 2.40x over the full-precision convolution with trivial accuracy loss.

* Accepted by ICASSP 2020 

  Access Paper or Ask Questions

Fault Handling in Large Water Networks with Online Dictionary Learning

Mar 18, 2020
Paul Irofti, Florin Stoican, Vicenç Puig

Fault detection and isolation in water distribution networks is an active topic due to its model's mathematical complexity and increased data availability through sensor placement. Here we simplify the model by offering a data driven alternative that takes the network topology into account when performing sensor placement and then proceeds to build a network model through online dictionary learning based on the incoming sensor data. Online learning is fast and allows tackling large networks as it processes small batches of signals at a time and has the benefit of continuous integration of new data into the existing network model, be it in the beginning for training or in production when new data samples are encountered. The algorithms show good performance when tested on both small and large-scale networks.

* Submitted to Journal of Process Control 

  Access Paper or Ask Questions

On the Role of Time in Learning

Jul 14, 2019
Alessandro Betti, Marco Gori

By and large the process of learning concepts that are embedded in time is regarded as quite a mature research topic. Hidden Markov models, recurrent neural networks are, amongst others, successful approaches to learning from temporal data. In this paper, we claim that the dominant approach minimizing appropriate risk functions defined over time by classic stochastic gradient might miss the deep interpretation of time given in other fields like physics. We show that a recent reformulation of learning according to the principle of Least Cognitive Action is better suited whenever time is involved in learning. The principle gives rise to a learning process that is driven by differential equations, that can somehow descrive the process within the same framework as other laws of nature.

* 7 pages 

  Access Paper or Ask Questions

Predicting Gender from Iris Texture May Be Harder Than It Seems

Nov 25, 2018
Andrey Kuehlkamp, Kevin Bowyer

Predicting gender from iris images has been reported by several researchers as an application of machine learning in biometrics. Recent works on this topic have suggested that the preponderance of the gender cues is located in the periocular region rather than in the iris texture itself. This paper focuses on teasing out whether the information for gender prediction is in the texture of the iris stroma, the periocular region, or both. We present a larger dataset for gender from iris, and evaluate gender prediction accuracy using linear SVM and CNN, comparing hand-crafted and deep features. We use probabilistic occlusion masking to gain insight on the problem. Results suggest the discriminative power of the iris texture for gender is weaker than previously thought, and that the gender-related information is primarily in the periocular region.

* Paper accepted for publication at the IEEE Winter Conference on Applications of Computer Vision - 2019 

  Access Paper or Ask Questions

Automatic Exploration of Machine Learning Experiments on OpenML

Oct 19, 2018
Daniel Kühn, Philipp Probst, Janek Thomas, Bernd Bischl

Understanding the influence of hyperparameters on the performance of a machine learning algorithm is an important scientific topic in itself and can help to improve automatic hyperparameter tuning procedures. Unfortunately, experimental meta data for this purpose is still rare. This paper presents a large, free and open dataset addressing this problem, containing results on 38 OpenML data sets, six different machine learning algorithms and many different hyperparameter configurations. Results where generated by an automated random sampling strategy, termed the OpenML Random Bot. Each algorithm was cross-validated up to 20.000 times per dataset with different hyperparameters settings, resulting in a meta dataset of around 2.5 million experiments overall.

* 6 pages, 0 figures 

  Access Paper or Ask Questions

Asymptotic Bayesian Generalization Error in a General Stochastic Matrix Factorization

Jun 23, 2018
Naoki Hayashi, Sumio Watanabe

Stochastic matrix factorization (SMF) can be regarded as a restriction of non-negative matrix factorization (NMF). SMF is useful for inference of topic models, NMF for binary matrices data, Markov chains, and Bayesian networks. However, SMF needs strong assumptions to reach a unique factorization and its theoretical prediction accuracy has not yet been clarified. In this paper, we study the maximum the pole of zeta function (real log canonical threshold) of a general SMF and derive an upper bound of the generalization error in Bayesian inference. The results give a foundation for a widely applicable and rigorous factorization method of SMF and mean that the generalization error in SMF becomes smaller than regular statistical models by Bayesian inference.

* Resubmitted to JMLR this revised version. Containing 43 pages, 1 figure 

  Access Paper or Ask Questions

Tweet Acts: A Speech Act Classifier for Twitter

May 17, 2016
Soroush Vosoughi, Deb Roy

Speech acts are a way to conceptualize speech as action. This holds true for communication on any platform, including social media platforms such as Twitter. In this paper, we explored speech act recognition on Twitter by treating it as a multi-class classification problem. We created a taxonomy of six speech acts for Twitter and proposed a set of semantic and syntactic features. We trained and tested a logistic regression classifier using a data set of manually labelled tweets. Our method achieved a state-of-the-art performance with an average F1 score of more than $0.70$. We also explored classifiers with three different granularities (Twitter-wide, type-specific and topic-specific) in order to find the right balance between generalization and overfitting for our task.

* ICWSM'16, May 17-20, Cologne, Germany. In Proceedings of the 10th AAAI Conference on Weblogs and Social Media (ICWSM 2016). Cologne, Germany 

  Access Paper or Ask Questions - Turning a Computer Vision algorithm into a World Wide Web Service

Apr 11, 2015
Ahmad Pahlavan Tafti, Hamid Hassannia, Zeyun Yu

Image features detection and description is a longstanding topic in computer vision and pattern recognition areas. The Scale Invariant Feature Transform (SIFT) is probably the most popular and widely demanded feature descriptor which facilitates a variety of computer vision applications such as image registration, object tracking, image forgery detection, and 3D surface reconstruction. This work introduces a Software as a Service (SaaS) based implementation of the SIFT algorithm which is freely available at for any academic, educational and research purposes. The service provides application-to-application interaction and aims Rapid Application Development (RAD) and also fast prototyping for computer vision students and researchers all around the world. An Internet connection is all they need!

* 8 pages, 7 figures 

  Access Paper or Ask Questions

Feature Selection Based on Confidence Machine

Jan 13, 2015
Chang Liu, Yi Xu

In machine learning and pattern recognition, feature selection has been a hot topic in the literature. Unsupervised feature selection is challenging due to the loss of labels which would supply the related information.How to define an appropriate metric is the key for feature selection. We propose a filter method for unsupervised feature selection which is based on the Confidence Machine. Confidence Machine offers an estimation of confidence on a feature'reliability. In this paper, we provide the math model of Confidence Machine in the context of feature selection, which maximizes the relevance and minimizes the redundancy of the selected feature. We compare our method against classic feature selection methods Laplacian Score, Pearson Correlation and Principal Component Analysis on benchmark data sets. The experimental results demonstrate the efficiency and effectiveness of our method.

* 10 pages 

  Access Paper or Ask Questions

Use of semantic technologies for the development of a dynamic trajectories generator in a Semantic Chemistry eLearning platform

Dec 07, 2010
Richard Huber, Kirsten Hantelmann, Alexandru Todor, Sebastian Krebs, Ralf Heese, Adrian Paschke

ChemgaPedia is a multimedia, webbased eLearning service platform that currently contains about 18.000 pages organized in 1.700 chapters covering the complete bachelor studies in chemistry and related topics of chemistry, pharmacy, and life sciences. The eLearning encyclopedia contains some 25.000 media objects and the eLearning platform provides services such as virtual and remote labs for experiments. With up to 350.000 users per month the platform is the most frequently used scientific educational service in the German spoken Internet. In this demo we show the benefit of mapping the static eLearning contents of ChemgaPedia to a Linked Data representation for Semantic Chemistry which allows for generating dynamic eLearning paths tailored to the semantic profiles of the users.

* in Adrian Paschke, Albert Burger, Andrea Splendiani, M. Scott Marshall, Paolo Romano: Proceedings of the 3rd International Workshop on Semantic Web Applications and Tools for the Life Sciences, Berlin,Germany, December 8-10, 2010 

  Access Paper or Ask Questions