Eclipse Deeplearning4j is a programming

library A library is a collection of Book, books, and possibly other Document, materials and Media (communication), media, that is accessible for use by its members and members of allied institutions. Libraries provide physical (hard copies) or electron ...

written in

Java Java is one of the Greater Sunda Islands in Indonesia. It is bordered by the Indian Ocean to the south and the Java Sea (a part of Pacific Ocean) to the north. With a population of 156.9 million people (including Madura) in mid 2024, proje ...

for the

Java virtual machine A Java virtual machine (JVM) is a virtual machine that enables a computer to run Java programs as well as programs written in other languages that are also compiled to Java bytecode. The JVM is detailed by a specification that formally descr ...

(JVM). It is a framework with wide support for deep learning algorithms. Deeplearning4j includes implementations of the restricted Boltzmann machine, deep belief net, deep autoencoder, stacked denoising autoencoder and recursive neural tensor network,

word2vec Word2vec is a technique in natural language processing (NLP) for obtaining vector representations of words. These vectors capture information about the meaning of the word based on the surrounding words. The word2vec algorithm estimates these rep ...

, doc2vec, and

GloVe A glove is a garment covering the hand, with separate sheaths or openings for each finger including the thumb. Gloves protect and comfort hands against cold or heat, damage by friction, abrasion or chemicals, and disease; or in turn to provide a ...

. These algorithms all include

distributed Distribution may refer to: Mathematics *Distribution (mathematics), generalized functions used to formulate solutions of partial differential equations *Probability distribution, the probability of a particular value or value range of a varia ...

parallel versions that integrate with

Apache Hadoop Apache Hadoop () is a collection of open-source software utilities for reliable, scalable, distributed computing. It provides a software framework for distributed storage and processing of big data using the MapReduce programming model. Hadoop wa ...

and Spark. Deeplearning4j is

open-source software Open-source software (OSS) is Software, computer software that is released under a Open-source license, license in which the copyright holder grants users the rights to use, study, change, and Software distribution, distribute the software an ...

released under

Apache License The Apache License is a permissive free software license written by the Apache Software Foundation (ASF). It allows users to use the software for any purpose, to distribute it, to modify it, and to distribute modified versions of the software ...

2.0, developed mainly by a

machine learning Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of Computational statistics, statistical algorithms that can learn from data and generalise to unseen data, and thus perform Task ( ...

group headquartered in

San Francisco San Francisco, officially the City and County of San Francisco, is a commercial, Financial District, San Francisco, financial, and Culture of San Francisco, cultural center of Northern California. With a population of 827,526 residents as of ...

. It is supported commercially by the startup Skymind, which bundles DL4J,

TensorFlow TensorFlow is a Library (computing), software library for machine learning and artificial intelligence. It can be used across a range of tasks, but is used mainly for Types of artificial neural networks#Training, training and Statistical infer ...

Keras Keras is an open-source library that provides a Python interface for artificial neural networks. Keras was first independent software, then integrated into the TensorFlow library, and later added support for more. "Keras 3 is a full rewrite o ...

and other deep learning libraries in an enterprise distribution called the Skymind Intelligence Layer. Deeplearning4j was contributed to the

Eclipse Foundation The Eclipse Foundation AISBL is an independent, Europe-based not-for-profit organization that acts as a steward of the Eclipse open source software development community, with legal jurisdiction in the European Union. It is an organization supp ...

in October 2017.

Introduction

Deeplearning4j relies on the widely used programming language

, though it is compatible with

Clojure Clojure (, like ''closure'') is a dynamic programming language, dynamic and functional programming, functional dialect (computing), dialect of the programming language Lisp (programming language), Lisp on the Java (software platform), Java platfo ...

and includes a Scala

application programming interface An application programming interface (API) is a connection between computers or between computer programs. It is a type of software Interface (computing), interface, offering a service to other pieces of software. A document or standard that des ...

(API). It is powered by its own open-source numerical computing library, ND4J, and works with both

central processing unit A central processing unit (CPU), also called a central processor, main processor, or just processor, is the primary Processor (computing), processor in a given computer. Its electronic circuitry executes Instruction (computing), instructions ...

s (CPUs) and

graphics processing unit A graphics processing unit (GPU) is a specialized electronic circuit designed for digital image processing and to accelerate computer graphics, being present either as a discrete video card or embedded on motherboards, mobile phones, personal ...

s (GPUs). Deeplearning4j has been used in several commercial and academic applications. The code is hosted on

GitHub GitHub () is a Proprietary software, proprietary developer platform that allows developers to create, store, manage, and share their code. It uses Git to provide distributed version control and GitHub itself provides access control, bug trackin ...

. A support forum is maintained on Gitter. 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, and a computation graph.

Distributed

Training with Deeplearning4j occurs in a cluster. Neural nets are trained in parallel via iterative reduce, which works on

Hadoop Apache Hadoop () is a collection of Open-source software, open-source software utilities for reliable, scalable, distributed computing. It provides a software framework for Clustered file system, distributed storage and processing of big data usin ...

-YARN and on Spark. 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 NumPy (pronounced ) is a library for the Python programming language, adding support for large, multi-dimensional arrays and matrices, along with a large collection of high-level mathematical functions to operate on these arrays. The predeces ...

provides to Python. It's effectively based on a library for

linear algebra Linear algebra is the branch of mathematics concerning linear equations such as :a_1x_1+\cdots +a_nx_n=b, linear maps such as :(x_1, \ldots, x_n) \mapsto a_1x_1+\cdots +a_nx_n, and their representations in vector spaces and through matrix (mathemat ...

and

matrix Matrix (: matrices or matrixes) or MATRIX may refer to: Science and mathematics * Matrix (mathematics), a rectangular array of numbers, symbols or expressions * Matrix (logic), part of a formula in prenex normal form * Matrix (biology), the m ...

manipulation in a production environment.

DataVec vectorization library for machine-learning

DataVec vectorizes various file formats and data types using an

input/output In computing, input/output (I/O, i/o, or informally io or IO) is the communication between an information processing system, such as a computer, and the outside world, such as another computer system, peripherals, or a human operator. Inputs a ...

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 model Vector space model or term vector model is an algebraic model for representing text documents (or more generally, items) as vector space, vectors such that the distance between vectors represents the relevance between the documents. It is used in i ...

ing and

topic model In statistics and natural language processing, a topic model is a type of statistical model for discovering the abstract "topics" that occur in a collection of documents. Topic modeling is a frequently used text-mining tool for discovery of hidden ...

ing 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 In information retrieval, tf–idf (term frequency–inverse document frequency, TF*IDF, TFIDF, TF–IDF, or Tf–idf) is a measure of importance of a word to a document in a collection or Text corpus, corpus, adjusted for the fact that some words ...

deep learning Deep learning is a subset of machine learning that focuses on utilizing multilayered neural networks to perform tasks such as classification, regression, and representation learning. The field takes inspiration from biological neuroscience a ...

, and Mikolov's word2vec algorithm, 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 network intrusion detection and cybersecurity, fraud detection for the financial sector, anomaly detection in industries such as manufacturing, recommender systems in e-commerce and advertising, and image recognition. Deeplearning4j has integrated with other machine-learning platforms such as RapidMiner, Prediction.io, and

Weka The weka, also known as the Māori hen or woodhen (''Gallirallus australis'') is a flightless bird species of the rail family. It is endemic to New Zealand. Some authorities consider it as the only extant member of the genus '' Gallirallus''. ...

Machine Learning Model Server

Deeplearning4j serves machine-learning models for inference in production using the free developer edition of SKIL, the Skymind Intelligence Layer. A model server serves the parametric machine-learning models that makes decisions about data. It is used for the inference stage of a machine-learning workflow, after data pipelines and model training. A model server is the tool that allows data science research to be deployed in a real-world production environment. What a Web server is to the Internet, a model server is to AI. Where a Web server receives an HTTP request and returns data about a Web site, a model server receives data, and returns a decision or prediction about that data: e.g. sent an image, a model server might return a label for that image, identifying faces or animals in photographs. The SKIL model server is able to import models from Python frameworks such as Tensorflow, Keras, Theano and CNTK, overcoming a major barrier in deploying deep learning models.

Benchmarks

Deeplearning4j is as fast as Caffe for non-trivial image recognition tasks using multiple GPUs. For programmers unfamiliar with HPC on the JVM, there are several parameters that must be adjusted to optimize neural network training time. These include setting the heap space, the garbage collection algorithm, employing off-heap memory and pre-saving data (pickling) for faster ETL. Together, these optimizations can lead to a 10x acceleration in performance with Deeplearning4j.

API Languages: Java, Scala, Python, Clojure & Kotlin

Deeplearning4j can be used via multiple API languages including Java, Scala, Python, Clojure and Kotlin. Its Scala API is called ScalNet. Keras serves as its Python API. And its Clojure wrapper is known as DL4CLJ. The core languages performing the large-scale mathematical operations necessary for deep learning are C, C++ and CUDA C.

Tensorflow, Keras & Deeplearning4j

Tensorflow, Keras and Deeplearning4j work together. Deeplearning4j can import models from Tensorflow and other Python frameworks if they have been created with Keras.

References

{{Deep Learning Software Deep learning software Cluster computing Free data analysis software Free science software Free software programmed in Java (programming language) Java (programming language) software Free software programmed in Scala Free statistical software Hadoop Image processing Java (programming language) libraries Java platform Java programming language family Natural language processing Numerical programming languages Open-source artificial intelligence Scala (programming language) Software using the Apache license