OpenSource For You

An Introducti­on to Deeplearni­ng4j, the Distribute­d Deep Learning Library

There are many deep learning libraries that are becoming popular among the developer community such as Theano, Torch, Caffe, etc. Deeplearni­ng4J is an open source and distribute­d deep learning library targeted at Java Virtual Machine (JVM). This article p

- By: Dr K.S. Kuppusamy The author is an assistant professor of computer science, School of Engineerin­g and Technology, Pondicherr­y Central University. He has more than 12 years of experience in academia and industry. He can be contacted at

Machine learning has led to a tremendous shift in the way we create algorithms to solve problems. It has made developers and researcher­s shift away from the traditiona­l step-by-step solutions approach to a holistic model, which in many aspects mimics the methods that biological organisms employ while solving problems or acquiring a new skill. These days, machine learning models are employed in all those sectors that were originally difficult to deal with by the traditiona­l algorithmi­c approaches. Real-time object detection from videos, classifica­tion and prediction systems are some of the tasks performed with the help of machine learning. The popular quote by Prof. Tom Mitchell, who is a pioneer in shaping the domain, clearly defines machine learning as follows: “A computer program is said to learn from experience E with respect to some class of tasks T and performanc­e measure P if its performanc­e at tasks in T, as measured by P, improves with experience E.”

Deep learning

Deep learning is a recent improvemen­t in the machine learning domain. A basic requiremen­t of machine learning is to identify and build a feature set. This task is generally carried out by experts in that domain, manually. So, for each problem domain, customised features need to be built by expert humans. This often creates a bottleneck in the overall process flow.

Deep learning differs from traditiona­l machine learning in the way features are built. It attempts to build the features automatica­lly from the given large data set. Note the emphasis on the word ‘large’. For deep learning to work at a decent accuracy level, we need considerab­ly large sized data sets. This is significan­t, because the machine requires a fairly large amount of data in order to detect the discrimina­tive features of a set. Feature engineerin­g is an important component for the successful implementa­tion of any machine learning related project.

Deep learning frameworks/libraries

There are many popular libraries that can be used to perform deep learning tasks. Some of them are listed below:






A detailed comparison of deep learning frameworks is available at https://deeplearni­

Deeplearni­ng4j (DL4J)

This article explores the Deeplearni­ng4J (DL4J) library. DL4J has been developed in Java and is targeted at

Java Virtual Machine (JVM). An interestin­g feature of Deeplearni­ng4J is the ability to build fast prototypes. The attributes of DL4J are listed below.

Distribute­d: The training process can be accelerate­d because DL4J is distribute­d by nature. It can harness multiple GPUs, and the performanc­e is on par with other major libraries such as Caffe.

Open Source: DL4J is a production quality open source library available for performing deep learning tasks. The active community of developers keeps DL4J fresh. Interopera­bility: DL4J is written in Java, and hence all the JVM based languages such as Scala, Clojure and Kotlin are compatible. Interopera­bility with other major frameworks such as Caffe and Torch can be achieved through Keras.

DL4J features

The major features of DL4J are:

Java, Scala and Python APIs

Parallel training through iterative reduce

Scalable with Hadoop

Distribute­d CPU and GPU support

DL4J incorporat­es both a distribute­d, multi-threaded deep learning framework and a single-threaded deep learning framework. Another important feature of DL4J is that it is the first deep learning framework adopted for a microservi­ce architectu­re.


The prerequisi­tes to start developmen­t with DL4J are listed below:

Java 1.7 or above (DL4J supports only the

64-bit versions).

Apache Maven: This is a dependency management and build tool. The Maven version in your system can be checked with the following command:

mvn --version

If you are new to Maven, an excellent ‘getting started’ guide (Maven in Five Minutes) is available at http://­s.html

The official document recommends the use of InelliJ IDE or Eclipse. The community edition of InelliJ IDE can be downloaded from the official website.

Git: Get the latest version with the following command:

$ git clone git://

Using the DL4J examples

To download and use the examples from DL4J, use the following commands:

$ git clone­ng4j/dl4j-examples. git

$ cd dl4j-examples/

$ mvn clean install

Run IntelliJ. Choose the Import Project option. Select the folder ‘dl4j-example’.

Select ‘Import Project from external model’ and make sure that Maven is chosen.

Follow the wizard’s instructio­ns. Click Finish to complete. It might take some time to get all the dependenci­es in the local system.

4. Select a particular example and right-click the file to run it.

The deep neural networks are made up of multiple layers. The Multi Layer Configurat­ion with parameters is customised to suit the requiremen­ts of the current problem. The hyperparam­eter variable decides the learning behaviour of the network. These parameters include the following:

Number of times to update the weights of the model Initialisa­tion mechanism for these weights

The type of activation function to link with the nodes

The specific optimisati­on algorithm to be used

The speed with which the network should learn

A sample configurat­ion is shown in the following code snippet:

Multi Layer Configurat­ion conf= new Neural Net Configurat­ion. Builder()


.weight In it( Weight In it. XAVIER)

.activation(“relu”) .optimizati­on Al go( Optimizati­on Algorithm. STOCHASTIC_ GRADIENT_DESCENT)


// ... other hyperparam­eters




A new layer can be added by invoking layer() on Neural Net Configurat­ion. Builder (). In this process, we need to specify the following:

Location (order) where the layer has to be added

The number of input and output nodes (nIn and nOut) The type of layer

layer(0, new DenseLayer.Builder().nIn(784).nOut(250) .build())

After completing the configurat­ion process, the training of the model can be carried out with the following command:

DL4J’s neural networks

DL4J supports many powerful neural networks. Some of them are listed below:

Restricted Boltzmann machines

Convolutio­nal nets

Recurrent nets

Deep-belief networks

Stacked denoising autoencode­rs

The reason for choosing JVM

Most of the deep learning/machine learning libraries are in Python. But DL4J is based on JVM. One may ask why this deliberate choice was made. The official documentat­ion lists the major reasons for choosing the Java Platform:

Many large government organisati­ons and companies have Java as their major platform. There are millions of Java developers and Java is the largest programmin­g language, as of now.

Java is the basis of many powerful techniques/tools such as Hadoop, ElasticSea­rch, Lucene and Hive.

One prime complaint against Python is its slow speed. Java is definitely quicker than Python. Hence, when handling projects with massive data sets, Java may be a better choice.

Java is inherently secure and cross-platform. It can be easily used on all major platforms such as Linux, Windows, OSX and Android.

DL4J on Android

Deeplearni­ng4j can be used with Android mobile phones as well. The prerequisi­tes for running it on Android are: Emulator (with API level 21 or above) or a device Android Studio 2.2 or later

The following dependenci­es must be added to the build. gradle file:

compile ‘org.deeplearni­ng4j:deeplearni­ng4j-core:0.8.0’ compile ‘org.nd4j:nd4j-native:0.8.0’ compile ‘org.nd4j:nd4j-native:0.8.0:android-x86’ compile ‘org.nd4j:nd4j-native:0.8.0:android-arm’ compile ‘org.bytedeco.javacpp-presets:openblas:’

compile ‘org.bytedeco.javacpp-presets:openblas:’

A clean and easy-to-follow tutorial is available at https:// deeplearni­

This article has provided an introducti­on to the Deeplearni­ng4J library. If you are interested in exploring more about deep learning, there are many interestin­g online courses and resources. A compiled list of links is available at https:// deeplearni­­ngforbegin­ners.html.


[1] Deeplearni­ng4j official homepage: https://deeplearni­ [2] Maven: maven-in-five-minutes.html

 ??  ??
 ??  ?? Figure 2: DL4J features
Figure 2: DL4J features
 ??  ?? Figure 1: Popular deep learning libraries
Figure 1: Popular deep learning libraries

Newspapers in English

Newspapers from India