Top 15 Frameworks for Machine Learning Experts

Either you are a researcher, start-up or big organization who wants to use machine learning, you will need the right tools to make it happen. Here is a list of the most popular frameworks for machine learning.


Machine learning engineers are part of the engineering team who build the product and the algorithms, making sure that it works reliably, quickly, and at-scale. They work closely with data scientist to understand the theoretical and business aspect of it. In the context of machine learning, the main summary of the differences is the following:

  • Machine learning engineers build, implement, and maintain production machine learning systems.
  • Data scientists conduct research to generate ideas about machine learning projects, and perform analysis to understand the metrics impact of machine learning systems.

Below is a list of frameworks for machine learning engineers:

  • Apache Singa is a general distributed deep learning platform for training big deep learning models over large datasets. It is designed with an intuitive programming model based on the layer abstraction. A variety of popular deep learning models are supported, namely feed-forward models including convolutional neural networks (CNN), energy models like restricted Boltzmann machine (RBM), and recurrent neural networks (RNN). Many built-in layers are provided for users.
  • Amazon Machine Learning  is a service that makes it easy for developers of all skill levels to use machine learning technology. Amazon Machine Learning provides visualization tools and wizards that guide you through the process of creating machine learning (ML) models without having to learn complex ML algorithms and technology.  It connects to data stored in Amazon S3, Redshift, or RDS, and can run binary classification, multiclass categorization, or regression on said data to create a model.
  • Azure ML Studio allows Microsoft Azure users to create and train models, then turn them into APIs that can be consumed by other services. Users get up to 10GB of storage per account for model data, although you can also connect your own Azure storage to the service for larger models. A wide range of algorithms are available, courtesy of both Microsoft and third parties. You don’t even need an account to try out the service; you can log in anonymously and use Azure ML Studio for up to eight hours.
  • Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by the Berkeley Vision and Learning Center (BVLC) and by community contributors. Yangqing Jia created the project during his PhD at UC Berkeley. Caffe is released under the BSD 2-Clause license.  Models and optimization are defined by configuration without hard-coding & user can switch between CPU and GPU. Speed makes Caffe perfect for research experiments and industry deployment. Caffe can process over 60M images per day with a single NVIDIA K40 GPU.
  • H2O makes it possible for anyone to easily apply math and predictive analytics to solve today’s most challenging business problems. It intelligently combines unique features not currently found in other machine learning platforms including: Best of Breed Open Source Technology, Easy-to-use WebUI and Familiar Interfaces, Data Agnostic Support for all Common Database and File Types. With H2O, you can work with your existing languages and tools. Further, you can extend the platform seamlessly into your Hadoop environments.
  • Massive Online Analysis (MOA) is the most popular open source framework for data stream mining, with a very active growing community. It includes a collection of machine learning algorithms (classification, regressionclusteringoutlier detection, concept drift detection and recommender systems) and tools for evaluation. Related to the WEKA project, MOA is also written in Java, while scaling to more demanding problems.
  • MLlib (Spark) is Apache Spark’s machine learning library. Its goal is to make practical machine learning scalable and easy. It consists of common learning algorithms and utilities, including classification, regression, clustering, collaborative filtering, dimensionality reduction, as well as lower-level optimization primitives and higher-level pipeline APIs.
  • mlpack, a C++-based machine learning library originally rolled out in 2011 and designed for “scalability, speed, and ease-of-use,” according to the library’s creators. Implementing mlpack can be done through a cache of command-line executables for quick-and-dirty, “black box” operations, or with a C++ API for more sophisticated work. Mlpack provides these algorithms as simple command-line programs and C++ classes which can then be integrated into larger-scale machine learning solutions.
  • Pattern is a web mining module for the Python programming language. It has tools for data mining (Google, Twitter and Wikipedia API, a web crawler, a HTML DOM parser), natural language processing (part-of-speech taggers, n-gram search, sentiment analysis, WordNet), machine learning (vector space model, clustering, SVM), network analysis and <canvas> visualization.
  • Scikit-Learn leverages Python’s breadth by building on top of several existing Python packages — NumPy, SciPy, and matplotlib — for math and science work. The resulting libraries can be used either for interactive “workbench” applications or be embedded into other software and reused. The kit is available under a BSD license, so it’s fully open and reusable. Scikit-learn includes tools for many of the standard machine-learning tasks (such as clustering, classification, regression, etc.). And since scikit-learn is developed by a large community of developers and machine-learning experts, promising new techniques tend to be included in fairly short order.
  • Shogun is among the oldest, most venerable of machine learning libraries, Shogun was created in 1999 and written in C++, but isn’t limited to working in C++. Thanks to the SWIG library, Shogun can be used transparently in such languages and environments: as Java, Python, C#, Ruby, R, Lua, Octave, and Matlab. Shogun is designed for unified large-scale learning for a broad range of feature types and learning settings, like classification, regression, or explorative data analysis.
  • TensorFlow is an open source software library for numerical computation using data flow graphs. TensorFlow implements what are called data flow graphs, where batches of data (“tensors”) can be processed by a series of algorithms described by a graph. The movements of the data through the system are called “flows” — hence, the name. Graphs can be assembled with C++ or Python and can be processed on CPUs or GPUs.
  • Theano is a Python library that lets you to define, optimize, and evaluate mathematical expressions, especially ones with multi-dimensional arrays (numpy.ndarray). Using Theano it is possible to attain speeds rivaling hand-crafted C implementations for problems involving large amounts of data. It was written at the LISA lab to support rapid development of efficient machine learning algorithms. Theano is named after the Greek mathematician, who may have been Pythagoras’ wife. Theano is released under a BSD license.
  • Torch is a scientific computing framework with wide support for machine learning algorithms that puts GPUs first. It is easy to use and efficient, thanks to an easy and fast scripting language, LuaJIT, and an underlying C/CUDA implementation. The goal of Torch is to have maximum flexibility and speed in building your scientific algorithms while making the process extremely simple. Torch comes with a large ecosystem of community-driven packages in machine learning, computer vision, signal processing, parallel processing, image, video, audio and networking among others, and builds on top of the Lua community.
  • Veles is a distributed platform for deep-learning applications, and it’s written in C++, although it uses Python to perform automation and coordination between nodes. Datasets can be analyzed and automatically normalized before being fed to the cluster, and a REST API allows the trained model to be used in production immediately. It focuses on performance and flexibility. It has little hard-coded entities and enables training of all the widely recognized topologies, such as fully connected nets, convolutional nets, recurent nets etc.

Tell us more about your favorate machine learning framework in comments.

Bio: Devendra Desale(@DevendraDesale) is a data science graduate student currently working on text mining and big data technologies. He is also interested in enterprise architectures and data-driven business. When away from the computer, he also enjoys attending meetups and venturing into the unknown.