【51CTO.com Quick Translation】It turns out that we can navigate the world of machine learning without mastering the difficult data science. Of course, this journey inevitably requires the help of various big data, artificial intelligence, deep learning, and large-scale statistical and analytical tools.
In today’s article, we will take a look at three of the most popular Python machine learning libraries, which we believe will help you have a smoother data science exploration experience. 1. Theano Theano, a machine learning solution that was born about ten years ago, is currently one of the most widely used CPU and GPU mathematical compilers in the field of machine learning. In the paper "Theano: A Python Framework for Fast Mathematical Expression Computation", the authors give a comprehensive overview of the library. "Theano includes multiple packages to enhance its functionality. It provides a high-level user interface that is sufficient to handle a variety of specific goals," the paper explains: "Lasagne and Keras can effectively simplify the architectural expression of deep learning models and training algorithms as mathematical expressions. In fact, the probabilistic programming framework PyMC3 uses Theano to automatically generate expressions and quickly execute the generated C code. (Keras and Lasagne run on both TensorFLow and Theano.)" Theano currently has over 25,000 commits and nearly 300 contributors on GitHub, and the number of forks is approaching 2,000. 2. TensorFlow TensorFlow is an open source library for numerical computation using data flow graphs. Although it is a newcomer in the open source field, this project led by Google already has nearly 15,000 submissions and more than 600 GitHub contributors, and the model library has a star rating of nearly 12,000. In the first Open Source Yearbook, TensorFlow was selected as the most worthy fork project in 2016. In the latest Open Source Yearbook, TensorFlow also appeared many times. The Magenta project based on TensorFlow is even trying to connect machine intelligence with the art field, exploring how to use it to achieve music and art creation, and thus establish a mixed community of artists, programmers and machine learning researchers. In addition, Tensorflow supports multiple front-end languages, but its support for Python is the best, and Python is also listed in the 2017 hot programming trend rankings. TensorFlow 1.0 was launched in mid-February this year. Google wrote in its developer blog: "Although it is only a year old, TensorFlow has helped researchers, engineers, artists, students and other users to complete various tasks, ranging from language translation, early diagnosis of skin cancer to prevention of concurrent blindness in diabetic patients." 3. scikit-learn This solution is based on NumPy, SciPy and Matplotlib, and is used by engineers at Spotfiy for music recommendations. At OkCupid, it is responsible for evaluating and improving the matching system. At Birchbox, staff are exploring how to use scikit-learn to support the development of new products. Scikit-learn currently has nearly 22,000 commits and 800 contributors on GitHub. [Translated by 51CTO. Please indicate the original translator and source as 51CTO.com when reprinting on partner sites] |
<<: Aiti Tribe Stories (10): Voices from Technical Promotion Managers
>>: How to build an Android MVVM application
Cars can navigate in cities by relying on landmar...
In 2023, China officially entered the manned spac...
Toutiao's information flow advertising is a f...
In the actual delivery, how do we find the proble...
Take watermelon rind to the canteen to get food U...
...
Introduction: Behind every event, there is a trut...
Black holes distort the universe to form multiple...
We have seen that many popular short video accoun...
In December 2023, there was such a sad and infuri...
Regarding the origin of mitochondria, scientists ...
At 5:30 in the morning of April 20, the rising su...
The matter began with a platform turnover statist...
Domestic Douyin merchants have been pushed to the...
Resource introduction of Feng Qingyang's 2nd p...