Eight Deep learning Software Libraries & Their Installation on Ubuntu

Photo Credit: Pixabay.com

Among all other machine learning algorithms such as SVM, Decision tree, Genetic algorithms and others, Deep learning has been seen to acquire media attention. There is plenty of technology that uses Deep Learning is already around us. Most popular devices which use this algorithm are Google assistant, Microsoft’s Cortana and Amazon Alexa. Apart from these examples, we have plenty of Chatbots and Virtual assistance systems unnoticed, and soon we will have self-driving cars. There is a wide range of problems in diverse domains which can be addressed using Deep learning. Deep learning architectures have been applied to fields in computer vision, speech recognition, natural language processing, audio recognition, social network, bioinformatics analysis, drug design and board game programs.

To be able to start building a better intelligent model using deep learning, one needs to know about at least a deep learning supported language and required hardware. Python is the most popular language to starts with since most of the Deep learning framework is available in Python. Apart from Python, many modules are also available in other languages such as MATLAB, R, GO, Java, etc. So before somebody starts, he or she should choose a language according to there, but still, python is recommended over all other because it is easy to grasp if already know any language and its free.

Here in this article, we are providing basic information about installation/setup for eight most popular Deep Learning framework on Ubuntu.


TensorFlow is an open-source math library, primarily used for machine learning. Originally developed by Google Brain for their use and released in 2015.

It has a flexible architecture which allows easy deployment of computation model across a variety of platforms (CPUs, GPUs, TPUs), and from clusters of servers to desktops and even to mobile and edge devices.

Installing TensorFlow on Ubuntu with GPU support


Theano allows us to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Theano is a written in python and CUDA, easy to implement in python.


Keras is written in Python and runs on top of TensorFlow, Microsoft Cognitive Toolkit and Theano.


PyTorch is machine learning library based upon Torch. Torch is a scientific computing framework that offers wide support for machine learning algorithms. It is a Lua-based deep learning framework. As opposed to Torch, PyTorch runs on Python. Given PyTorch framework’s architectural style, the entire deep modeling process is far simpler as well as transparent compared to Torch.


Caffe2 is a deep learning framework; You can bring your creations to scale using the power of GPUs in the cloud or to the masses on mobile with Caffe2’s cross-platform libraries.

Microsoft Cognitive Toolkit

Microsoft Cognitive Toolkit or CNTK or The Microsoft Cognitive Toolkit, is a deep learning framework developed by Microsoft Research. The Microsoft Cognitive Toolkit (CNTK) supports both 64-bit Windows and 64-bit Linux platforms.


Eclipse 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] 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.[4]

Deeplearning4j is open-source software released under Apache License 2.0,[5] developed mainly by a machine learning group headquartered in San Francisco and Tokyo and led by Adam Gibson.[6][7] It is supported commercially by the startup Skymind, which bundles DL4J, Tensorflow, Keras and other deep learning libraries in an enterprise distribution called the Skymind Intelligence Layer.[8] Deeplearning4j was contributed to the Eclipse Foundation in October 2017.[9][10]


MATLAB (matrix laboratory) is a commercial multi-paradigm numerical computing environment and proprietary programming language developed by MathWorks. MATLAB allows matrix manipulations, plotting of functions and data, implementation of algorithms, creation of user interfaces, and interfacing with programs written in other languages, including C, C++, C#, Java, Fortran and Python. Deep Learning in MATLAb comes under Neural Network Toolbox.

If you already have MATLAB (2015 x or later) and do not have “Neural Network Toolbox” go to APPS.  Than click on “Get more Apps” option. A explorar will pop-up search for “Neural Network Toolbox” and click to install.

Note: This is a guest post, and opinion in this article is of the guest writer. If you have any issues with any of the articles posted at www.marktechpost.com please contact at [email protected]

Top Artificial Intelligence Books to Read in 2018

Previous articleBlockchain May Be Fueling The Green Energy Revolution
Next article5 Barriers to Digital health (Part-2)
I am Nilesh Kumar, a graduate student at the Department of Biology, UAB under the mentorship of Dr. Shahid Mukhtar. I joined UAB in Spring 2018 and working on Network Biology. My research interests are Network modeling, Mathematical modeling, Game theory, Artificial Intelligence and their application in Systems Biology. I graduated with master’s degree “Master of Technology, Information Technology (Specialization in Bioinformatics)” in 2015 from Indian Institute of Information Technology Allahabad, India with GATE scholarship. My Master’s thesis was entitled “Mirtron Prediction through machine learning approach”. I worked as a research fellow at The International Centre for Genetic Engineering and Biotechnology, New Delhi for two years.