Home > News content

Open source framework for 11 AI and machine learning models

via:博客园     time:2018/6/13 15:02:04     readed:103

Original English text:11 Open-Source Frameworks for AI and Machine Learning Models

The rapid growth of artificial intelligence over the past decade has stimulated a huge demand for AI and ML skills in the job market today. From finance to healthcare, almost all industries now use ML-based technologies. This article will introduce a series of best frameworks and libraries that can be used to build machine learning models.

orgsrc=https://images2018.cnblogs.com/news/66372/201806/66372-20180613144435836-962612119.png

1. TensorFlow

TensorFlowIs a Google developmentOpen source softwareLibrary, designed for deep learning or artificial neural networks. TensorFlow allows you to use flowcharts to create neural networks and calculation models. It is one of the best maintained and most popular open source libraries for deep learning. The TensorFlow framework can use either C++ or Python. Other similar Python-based deep learning frameworks includeTheano,Torch, Lasagne, Blocks, MXNet, PyTorch andCaffe. You can use TensorBoard to make simple visualizations and see the calculation pipeline. Its flexible architecture allows you to easily deploy on different types of devices. The downside is that TensorFlow has no symbolic loop and does not support distributed learning. In addition, it does not yet support Windows.

2. Theano

TheanoIs a Python library designed for deep learning. You can use this tool to define and evaluate mathematical expressions, including multidimensional arrays. Optimized for the GPU, this tool has features such as integration with NumPy, dynamic C code generation, and symbol differentiation. However, for a high degree of abstraction, the tool must be used with other libraries such as Keras, Lasagne, and Blocks. Theano supports Linux, Mac OS X and Windows platforms.

3. Torch

TorchIs an open source computing framework for ML algorithms that is easy to use. The tool provides efficient GPU support, N-dimensional arrays, numerical optimization routines, linear algebra routines, and routines for indexing, slicing, and permutation. Based on Lua's scripting language, this tool comes with a large number of pre-trained models. This flexible and efficient ML research tool supports mainstream platforms such as Linux, Android, Mac OS X, iOS and Windows.

4. Caffe

CaffeIs a popular deep learning tool for building applications. This tool was created by Jia Yangqing during his Ph.D. at the University of California, Berkeley, and has a good Matlab / C ++ / Python interface. This tool allows you to use text quickly to apply neural networks to problems without writing code. Caffe does not fully support multi-GPU training. The tool supports operating systems such as Ubuntu, Mac OS X, and Windows.

5. Microsoft CNTK

Microsoft Cognitive ToolkitIt is one of the fastest deep learning frameworks with C#/C++/Python interface support. This open source framework comes with a powerful C++ API that is faster and more accurate than TensorFlow. The tool also supports distributed learning of built-in data readers. It supports algorithms such as feedforward, CNN, RNN, LSTM, and sequence-to-sequence. The tool supports Windows and Linux.

6. Keras

Written in PythonKerasIs an open source library designed to simplify the creation of new DL models. This advanced neural network API can run on deep learning frameworks such as TensorFlow, Microsoft CNTK. The tool is known for its user-friendliness and modularity, making it ideal for rapid prototyping. This tool is optimized for the CPU and GPU.

7. scikit-learn

Scikit-learnIs an open source Python library designed for machine learning. Scikit-learn based on libraries such as NumPy, SciPy, and matplotlib can be used for data mining and data analysis. Scikit-learn is equipped with a variety of ML models, including linear and logistic regression, SVM classifiers, and random forests. This tool can be used for multiple ML tasks such as classification, regression and clustering. Scikit-learn supports operating systems such as Windows and Linux. The disadvantage is that the GPU is not very efficient.

8. Accord.NET

Accord.NETIt is an ML framework written in C# that is designed to build production-level computer vision, computer audition, signal processing, and statistical applications. It is a well-documented ML framework for easy audio and image processing. Accord.NET can be used for numerical optimization, artificial neural networks and visualization. It supports Windows.

9. Spark MLlib

Apache Spark's MLIib is an ML library for the Java, Scala, Python, and R languages. Because it is designed to handle large-scale data, this powerful library has many algorithms and utilities such as classification, regression, and clustering. This tool interoperates with NumPy in Python and R libraries. It can be easily inserted into a Hadoop workflow.

10. Azure ML Studio

Azure ML StudioIt is a modern cloud platform for data scientists. It can be used to develop ML models in the cloud. With extensive modeling options and algorithms, Azure is well suited for building larger ML models. This service provides 10GB of storage for each account. It can be used with R and Python programs.

11. Amazon Machine Learning

Amazon Machine Learning (AML)Is an ML service that provides tools and wizards for creating ML models. With visual aids and easy-to-use analytics, AML is designed to make it easier for developers to use ML. AML can connect to data stored on Amazon S3, Redshift, or RDS.

Machine learning frameworks have pre-built components that are easy to understand and code, so a good ML framework can reduce the complexity of defining ML models. Let us use these open source ML frameworks to help build ML models quickly and easily.

-

Translation Links:Http://www.codeceo.com/article/11-frameworks-for-ai-and-ml.html

Translation of:Code Network– Xiaofeng

China IT News APP

Download China IT News APP

Please rate this news

The average score will be displayed after you score.

Post comment

Do not see clearly? Click for a new code.

User comments