Encog is a
machine learning
Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence.
Machine ...
framework available for
Java
Java (; id, Jawa, ; jv, ꦗꦮ; su, ) is one of the Greater Sunda Islands in Indonesia. It is bordered by the Indian Ocean to the south and the Java Sea to the north. With a population of 151.6 million people, Java is the world's mo ...
and
.Net.
[J. Heaton http://www.jmlr.org/papers/volume16/heaton15a/heaton15a.pdf Encog: Library of Interchangeable Machine Learning Models for Java and C#]
Encog supports different learning algorithms such as
Bayesian Networks,
Hidden Markov Models and
Support Vector Machines.
However, its main strength lies in its
neural network
A neural network is a network or neural circuit, circuit of biological neurons, or, in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus, a neural network is either a biological neural network, made up ...
algorithms. Encog contains classes to create a wide variety of networks, as well as support classes to normalize and process data for these neural networks. Encog trains using many different techniques. Multithreading is used to allow optimal training performance on multicore machines.
Encog can be used for many tasks, including medical
[D. Heider, J. Verheyen, D. Hoffmann http://www.biomedcentral.com/content/pdf/1471-2105-11-37.pdf Predicting Bevirimat resistance of HIV-1 from genotype] and financial research.
[J. Heaton http://www.devx.com/opensource/Article/44014/1954 Basic Market Forecasting with Encog Neural Networks] A GUI based workbench is also provided to help model and train neural networks. Encog has been in active development since 2008.
[http://www.heatonresearch.com/encog Description of Encog Project.]
Neural Network Architectures
*
ADALINE Neural Network
*
Adaptive Resonance Theory 1 (ART1)
*
Bidirectional Associative Memory (BAM)
*
Boltzmann Machine
* Counterpropagation Neural Network (CPN)
*
Elman Recurrent Neural Network
*
Neuroevolution of augmenting topologies (NEAT)
*
Feedforward Neural Network (Perceptron)
*
Hopfield Neural Network
*
Jordan Recurrent Neural Network
*
Radial Basis Function Network
* Recurrent Self Organizing Map (RSOM)
*
Self Organizing Map (Kohonen)
Training techniques
*
Backpropagation
In machine learning, backpropagation (backprop, BP) is a widely used algorithm for training feedforward artificial neural networks. Generalizations of backpropagation exist for other artificial neural networks (ANNs), and for functions gener ...
*
Resilient Propagation (RProp)
*
Scaled Conjugate Gradient (SCG)
*
Levenberg–Marquardt algorithm
In mathematics and computing, the Levenberg–Marquardt algorithm (LMA or just LM), also known as the damped least-squares (DLS) method, is used to solve non-linear least squares problems. These minimization problems arise especially in least s ...
*
Manhattan Update Rule Propagation
Manhattan (), known regionally as the City, is the most densely populated and geographically smallest of the five boroughs of New York City. The borough is also coextensive with New York County, one of the original counties of the U.S. state ...
*
Competitive learning Competitive learning is a form of unsupervised learning in artificial neural networks
Artificial neural networks (ANNs), usually simply called neural networks (NNs) or neural nets, are computing systems inspired by the biological neural net ...
*
Hopfield Learning
*
Genetic algorithm training
* Instar Training
* Outstar Training
*
ADALINE Training
See also
*
JOONE
JOONE (Java Object Oriented Neural Engine) is a component based neural network framework built in Java (programming language), Java.
Features
Joone consists of a component-based architecture based on linkable components that can be extended to b ...
: another
neural network
A neural network is a network or neural circuit, circuit of biological neurons, or, in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus, a neural network is either a biological neural network, made up ...
programmed in
Java
Java (; id, Jawa, ; jv, ꦗꦮ; su, ) is one of the Greater Sunda Islands in Indonesia. It is bordered by the Indian Ocean to the south and the Java Sea to the north. With a population of 151.6 million people, Java is the world's mo ...
*
FANN, a neural network written in
C with bindings to most other languages.
*
Deeplearning4j: An open-source deep learning library written for Java/C++ w/LSTMs and convolutional networks. Parallelization with Apache Spark and Aeron on CPUs and GPUs.
References
{{Reflist
External links
Encog HomepageEncog Project (GitHub)Basic Market Forecasting with Encog Neural Networks (DevX Article)An Introduction to Encog Neural Networks for Java (Code Project)Benchmarking and Comparing Encog, Neuroph and JOONE Neural Networks
Neural network software
Free science software
Java (programming language) software
Free data analysis software