All entries.
Showing Items 531-540 of 674 on page 54 of 68: First Previous 49 50 51 52 53 54 55 56 57 58 59 Next Last

Logo Oboe A Chinese Syntactic Parser 1.0

by openpr_nlpr - April 9, 2012, 09:08:35 CET [ Project Homepage BibTeX Download ] 4551 views, 984 downloads, 1 subscription

About: Oboe is a software for Chinese syntactic parsing, and it can display syntactic trees in a graphical view with two kinds of representation: phrase tree and dependency tree. So it is very helpful for NLP researchers, especially for researchers focusing on syntax-based methods.

Changes:

Initial Announcement on mloss.org.


Logo bayes scala 0.5-SNAPSHOT

by danielkorzekwa - January 9, 2015, 19:23:48 CET [ Project Homepage BibTeX Download ] 3150 views, 983 downloads, 2 subscriptions

About: It is a Scala library for building Bayesian Networks with discrete/continuous variables and running deterministic Bayesian inference

Changes:

Initial Announcement on mloss.org.


About: FAST is an implementation of Hidden Markov Models with Features. It allows features to modify both emissions and transition probabilities.

Changes:

Initial Announcement on mloss.org.


About: Ran He, Wei-Shi Zheng,Tieniu Tan, and Zhenan Sun. Half-quadratic based Iterative Minimization for Robust Sparse Representation. Submitted to IEEE Trans. on Pattern Analysis and Machine Intelligence.

Changes:

Initial Announcement on mloss.org.


Logo ADENINE 0.1.4

by samuelefiorini - February 17, 2017, 14:50:49 CET [ Project Homepage BibTeX Download ] 3971 views, 967 downloads, 2 subscriptions

About: ADENINE (A Data ExploratioN pIpeliNE) is a machine learning framework for data exploration that encompasses state-of-the-art techniques for missing values imputing, data preprocessing, unsupervised feature learning and clustering tasks.

Changes:
  • Adenine can now distribute the execution of its pipelines on multiple machines via MPI
  • kNN data imputing strategy is now implemented
  • added python 2.7 and 3.5 support
  • stability improved and bug fixed

About: This program is used to extract HOG(histograms of oriented gradients) features from images. The integral histogram is used for fast histogram extraction. Both APIs and binary utility are provided.

Changes:

Initial Announcement on mloss.org.


Logo CN24 Convolutional Neural Networks for Semantic Segmentation 1.0

by erik - February 23, 2015, 09:02:06 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 4437 views, 960 downloads, 1 subscription

About: CN24 is a complete semantic segmentation framework using fully convolutional networks.

Changes:

Initial Announcement on mloss.org.


Logo SkyVoice TTS and SDK 1.0

by openpr_nlpr - September 10, 2012, 03:48:47 CET [ Project Homepage BibTeX Download ] 4174 views, 958 downloads, 1 subscription

About: Text-to-Speech (TTS) is a kind of speech processing technology that converts text into speech. It involves phonetics, linguistics, digital signal processing technology, computer technology, multimedia technology, and other technologies. It is a frontier technology in Chinese information processing field. With TTS technology, any text used to be read by eyes can also be listened by ears.

Changes:

Initial Announcement on mloss.org.


Logo JEMLA 1.0

by bathaeian - January 4, 2015, 08:34:49 CET [ Project Homepage BibTeX Download ] 3061 views, 952 downloads, 3 subscriptions

About: Java package for calculating Entropy for Machine Learning Applications. It has implemented several methods of handling missing values. So it can be used as a lab for examining missing values.

Changes:

Discretizing numerical values is added to calculate mode of values and fractional replacement of missing ones. class diagram is on the web http://profs.basu.ac.ir/bathaeian/free_space/jemla.rar


About: Robust sparse representation has shown significant potential in solving challenging problems in computer vision such as biometrics and visual surveillance. Although several robust sparse models have been proposed and promising results have been obtained, they are either for error correction or for error detection, and learning a general framework that systematically unifies these two aspects and explore their relation is still an open problem. In this paper, we develop a half-quadratic (HQ) framework to solve the robust sparse representation problem. By defining different kinds of half-quadratic functions, the proposed HQ framework is applicable to performing both error correction and error detection. More specifically, by using the additive form of HQ, we propose an L1-regularized error correction method by iteratively recovering corrupted data from errors incurred by noises and outliers; by using the multiplicative form of HQ, we propose an L1-regularized error detection method by learning from uncorrupted data iteratively. We also show that the L1-regularization solved by soft-thresholding function has a dual relationship to Huber M-estimator, which theoretically guarantees the performance of robust sparse representation in terms of M-estimation. Experiments on robust face recognition under severe occlusion and corruption validate our framework and findings.

Changes:

Initial Announcement on mloss.org.


Showing Items 531-540 of 674 on page 54 of 68: First Previous 49 50 51 52 53 54 55 56 57 58 59 Next Last