Android Learning Essentials--java Tools 15

Weka1. Weka integrates a machine learning algorithm for data mining work. These algorithms can be applied directly to a dataset or you can write your own code to invoke it. Weka includes a range of tools, such as data preprocessing, classification, regression, clustering, association rules, and visualization. Massiveonlineanalysis2. Massiveonlineanalysis (MOA) is a popular open source framework for data stream mining, with a very active growth community. It includes a range of machine learning algorithms (classification, regression, clustering, anomaly detection, concept drift detection and referral systems), and evaluation tools. Associated with the Weka project, Moa is also written in Java, which is more extensible. Meka3. The Meka project provides an open source implementation for multi-label learning and evaluation methods. In the multi-label category, we want to predict multiple output variables for each input instance. This differs from the case where only one single target variable is involved in the "normal" case. In addition, Meka is based on the Weka Machine Learning Toolkit. ADAMS4. Advanceddataminingandmachinelearningsystem (ADAMS) is a new type of flexible workflow engine that is designed to quickly build and maintain a complex knowledge stream of the real world, based on GPLv3 distribution. Elki5. environmentfordevelopingkdd-applicationssupportedbyindex-Structure (Elki) is a Java-based open source (AGPLV3) data mining software. Elki mainly focuses on algorithm research, focusing on unsupervised methods and anomaly detection in cluster analysis. Mallet6. Mallet is a Java-oriented machine learning toolkit for text-based files. Mallet supports classification algorithms such as maximum entropy, naive Bayesian, and decision tree classification. ENCOG7. ENCOG is an advanced machine learning framework that integrates support vector machines (SVM), artificial neural networks, genetic algorithms, Bayesian networks, Hidden Markov models (HMM), genetic programming, and genetic algorithms. Datumbox8. The Datumbox machine learning Framework is an open source framework written in Java that allows rapid development of machine learning and statistical applications. The core focus of the framework is a large number of machine learning algorithms and statistical testing that can handle medium-sized datasets. Deeplearning4j9. DEEPLEARNING4J is the first commercially-available, open-source, distributed in-depth learning library written in Java and Scala. It is designed to be used in a business environment, not as a research tool. MahoutTen. Mahout is a machine learning framework with built-in algorithms. mahout-Samsara helps people create their own math and provides some ready-made algorithm implementations. RapidMiner One. RapidMiner was developed by the German University of Technology at Monterey. It provides a GUI (graphical user interface) and JAVAAPI for developers to develop applications. It also provides a number of machine learning algorithms for data processing, visualization, and modeling. Apachesamoa A. Apachesamoa is a machine learning (ML) framework that embeds programming abstractions for distributed stream ML algorithms and allows the underlying distributed stream processing engine (dspee, such as Apachestorm, ApacheS4 and Apachesamza) in the case of complexity, develop a new ML algorithm. The user can develop a distributed stream ml algorithm and can execute on multiple dspes. Neuroph -. Neuroph simplifies neural network development by providing Java network libraries and GUI tools that support the creation, training, and preservation of neural networks. Oryx2 -. Oryx2 is a lambda architecture built on Apachespark and Apachekafka, but gradually began to specialize with real-time, large-scale machine learning. This is a framework for building applications, but it also includes packaging, as well as end-to-end applications for collaborative filtering, classification, regression, and clustering. Stanfordclassifier the. Stanfordclassifier is a machine learning tool that enables data items to be collocated into a category. A probability classifier, such as this one, can give a probability distribution of the class allocation for a data item. The software is a Java implementation of the maximum entropy classifier.

Android Learning Essentials--java Tools 15