Quickml - An easy-to-use but powerful and fast machine learning library for Java Top 10 Machine Learning Projects on Github Open source software is an important piece of the data science puzzle. According to the most recent KDnuggets data science software poll results, 73% of data scientists used free software in the previous 12 months. While there are many sources of such tools on the internet, Github has become a de facto clearinghouse for all types of open source software, including tools used in the data science community. The importance, and central position, of machine learning to the field of data science does not need to be pointed out. The following is an overview of the top 10 machine learning projects on Github. 1. Machine learning in Python. The top project is, unsurprisingly, the go-to machine learning library for Pythonistas the world over, from industry to academia. 2. A curated list of awesome Machine Learning frameworks, libraries and software. This is a curated list of machine learning libraries, frameworks, and software. 3. PredictionIO is a general purpose framework. 4.
tensorflow/tensorflow: Computation using data flow graphs for scalable machine learning First Steps with TensorFlow: Toolkit | Machine Learning Crash Course | Google Developers Tensorflow is a computational framework for building machine learning models. TensorFlow provides a variety of different toolkits that allow you to construct models at your preferred level of abstraction. You can use lower-level APIs to build models by defining a series of mathematical operations. The following figure shows the current hierarchy of TensorFlow toolkits: Figure 1. The following table summarizes the purposes of the different layers: TensorFlow consists of the following two components: These two components are analogous to Python code and the Python interpreter. Which API(s) should you use? We'll use tf.estimator for the majority of exercises in Machine Learning Crash Course. tf.estimator is compatible with the scikit-learn API. Very broadly speaking, here's the pseudocode for a linear classification program implemented in tf.estimator: