Review: The best frameworks for machine learning and deep learning

TensorFlow, Spark MLlib, Scikit-learn, MXNet, Microsoft Cognitive Toolkit, and Caffe do the math

Become An Insider

Sign up now and get FREE access to hundreds of Insider articles, guides, reviews, interviews, blogs, and other premium content. Learn more.
At a Glance
  • Caffe 1.0 RC3

    InfoWorld Rating
    Learn more
    on Berkeley Artificial Intelligence...
  • Microsoft Cognitive Toolkit v2.0 Beta 1

    InfoWorld Rating
    Learn more
    on Microsoft
  • MXNet v0.7

    InfoWorld Rating
    Learn more
    on Distributed Machine Learning...
  • Scikit-learn 0.18.1

    InfoWorld Rating
    Learn more
    on Scikit-learn
  • Spark MLlib 2.01

    InfoWorld Rating
    Learn more
    on Apache Software Foundation
  • TensorFlow r0.10

    InfoWorld Rating
    Learn more
    on Google

Over the past year I've reviewed half a dozen open source machine learning and/or deep learning frameworks: Caffe, Microsoft Cognitive Toolkit (aka CNTK 2), MXNet, Scikit-learn, Spark MLlib, and TensorFlow. If I had cast my net even wider, I might well have covered a few other popular frameworks, including Theano (a 10-year-old Python deep learning and machine learning framework), Keras (a deep learning front end for Theano and TensorFlow), and DeepLearning4j (deep learning software for Java and Scala on Hadoop and Spark). If you’re interested in working with machine learning and neural networks, you’ve never had a richer array of options.  

There's a difference between a machine learning framework and a deep learning framework. Essentially, a machine learning framework covers a variety of learning methods for classification, regression, clustering, anomaly detection, and data preparation, and it may or may not include neural network methods. A deep learning or deep neural network (DNN) framework covers a variety of neural network topologies with many hidden layers. These layers comprise a multistep process of pattern recognition. The more layers in the network, the more complex the features that can be extracted for clustering and classification.

To continue reading this article register now

Shop Tech Products at Amazon