Jump to content

Deeplearning4j

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by Like.liberation (talk | contribs) at 18:34, 15 January 2017. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Deeplearning4j
Original author(s)Adam Gibson, Chris Nicholson, Josh Patterson
Developer(s)various
Stable release
0.0.4 / 24 August 2015; 9 years ago (2015-08-24)
Repository
Written inJava, Scala, CUDA, C, C++
Operating systemLinux, OS X, Windows, Android
PlatformCross-platform
Available inEnglish
TypeNatural language processing, deep learning, machine vision, artificial intelligence
LicenseApache 2.0
Websitedeeplearning4j.org
Part of a series on
Machine learning
and data mining
Paradigms
Problems
Clustering
Dimensionality reduction
Structured prediction
Anomaly detection
Artificial neural network
Reinforcement learning
Learning with humans
Model diagnostics
Mathematical foundations
Journals and conferences
Related articles

Deeplearning4j is a deep learning programming library written for Java and the Java virtual machine (JVM)[1][2] and a computing framework with wide support for deep learning algorithms.[3] It has been called "the most accessible, powerful and well-documented DL framework for a static-typed" language.[4] Deeplearning4j includes implementations of the restricted Boltzmann machine, deep belief net, deep autoencoder, stacked denoising autoencoder and recursive neural tensor network, word2vec, doc2vec, and GloVe. These algorithms all include distributed parallel versions that integrate with Apache Hadoop and Spark.[5]

Deeplearning4j is open-source software released under Apache License 2.0,[6] developed mainly by a machine learning group in San Francisco led by Adam Gibson.[7][8] It is supported commercially by the startup Skymind.

Introduction

Deeplearning4j relies on the widely used programming language, Java, though it is compatible with Clojure and includes a Scala application programming interface (API). It is powered by its own open-source numerical computing library, ND4J, and works with both central processing units (CPUs) and graphics processing units (GPUs).[9][10]

Deeplearning4j has been used in several commercial and academic applications. The code is hosted on GitHub.[11] A support forum is maintained on Gitter.[12]

The framework is composable, meaning shallow neural nets such as restricted Boltzmann machines, convolutional nets, autoencoders, and recurrent nets can be added to one another to create deep nets of varying types. It also has extensive visualization tools,[13] and a computation graph.[14]

Distributed

Training with Deeplearning4j occurs in a cluster. Neural nets are trained in parallel via iterative reduce, which works on Hadoop-YARN and on Spark.[7][15] Deeplearning4j also integrates with CUDA kernels to conduct pure GPU operations, and works with distributed GPUs.

Scientific computing for the JVM

Deeplearning4j includes an n-dimensional array class using ND4J that allows scientific computing in Java and Scala, similar to the functions that NumPy provides to Python. It's effectively based on a library for linear algebra and matrix manipulation in a production environment.

DataVec vectorization library for machine-learning

DataVec vectorizes various file formats and data types using an input/output format system similar to Hadoop's use of MapReduce; that is, it turns various data types into columns of scalars termed vectors. DataVec is designed to vectorize CSVs, images, sound, text, video, and time series.

Text and NLP

Deeplearning4j includes a vector space modeling and topic modeling toolkit, implemented in Java and integrating with parallel GPUs for performance. It is designed to handle large text sets.

Deeplearning4j includes implementations of term frequency–inverse document frequency (tf–idf), deep learning, and Mikolov's word2vec algorithm,[16] doc2vec, and GloVe, reimplemented and optimized in Java. It relies on t-distributed stochastic neighbor embedding (t-SNE) for word-cloud visualizations.

Real-world use cases and integrations

Real-world use cases for Deeplearning4j include fraud detection for the financial sector,[17] anomaly detection in industries such as manufacturing, recommender systems in e-commerce and advertising,[18] and image recognition. Deeplearning4j has integrated with other machine-learning platforms such as RapidMiner and Prediction.io.[19]

See also

References

  1. ^ Metz, Cade (2014-06-02). "The Mission to Bring Google's AI to the Rest of the World". Wired.com. Retrieved 2014-06-28.
  2. ^ Vance, Ashlee (2014-06-03). "Deep Learning for (Some of) the People". Bloomberg Businessweek. Retrieved 2014-06-28.
  3. ^ Novet, Jordan (2015-11-14). "Want an open-source deep learning framework? Take your pick". VentureBeat. Retrieved 2015-11-24.
  4. ^ Twitter. 2017-01-12 https://twitter.com/rkfg_me/status/820233554898669568. Retrieved 2017-01-12. {{cite web}}: Missing or empty |title= (help)
  5. ^ TV, Functional (2015-02-12). "Adam Gibson, DeepLearning4j on Spark and Data Science on JVM with nd4j, SF Spark @Galvanize 20150212". SF Spark Meetup. Retrieved 2015-03-01.
  6. ^ "Github Repository".
  7. ^ a b "deeplearning4j.org".
  8. ^ "Crunchbase Profile".
  9. ^ Harris, Derrick (2014-06-02). "A startup called Skymind launches, pushing open source deep learning". GigaOM.com. Retrieved 2014-06-29.
  10. ^ Novet, Jordan (2014-06-02). "Skymind launches with open-source, plug-and-play deep learning features for your app". Retrieved 2014-06-29.
  11. ^ Deeplearning4j source code
  12. ^ Deeplearning4j Gitter Support Channel
  13. ^ Deeplearning4j Visualization Tools
  14. ^ Deeplearning4j Deeplearning4j Computation Graph
  15. ^ "Iterative reduce".
  16. ^ word2vec
  17. ^ http://www.skymind.io/finance/
  18. ^ http://www.skymind.io/commerce/
  19. ^ https://www.rapidminerchina.com/en/products/shop/product/deeplearning4j/
Retrieved from "https://en.wikipedia.org/enwiki/w/index.php?title=Deeplearning4j&oldid=760224307"