Application Artificial Intelligence using Machine Learning

Artificial Intelligence using Machine Learning.

Artificial Intelligence using Machine Learning.
Machine Learning Technologies

Artificial intelligence is not a new technology. Everything is now based on artificial intelligence. From shopping related products on Amazon, Google Maps, Waze, even getting an Uber everything is using artificial intelligence to make it smarter, easier and enhance user experience.

The base technology behind an artificial intelligence is machine learning. The technology is trained to learn pattern based on some test data. Then based on it, a new data used for predicting the future. There is a video made by Google developers to explain in further.

In this post, I will describe few tools/libraries commonly used for machine learning.

  • Tensor Flow
    TensorFlow™ is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them.
    More information https://www.tensorflow.org/
  • Apache Spark MLib
    Apache Spark MLib is one of the top Apache projects which is capable of doing data streaming. It is a fast and general-purpose cluster computing system. In addition to it, Apache Spark has a special machine learning library called MLib.
    More information https://spark.apache.org/docs/latest/ml-guide.html
  • IBM z/OS + Watson
    IBM Watson Analytics is a smart data analysis and visualisation service on the cloud that helps just about anyone quickly discover patterns and meanings in their data – all on their own.
    More information https://www.ibm.com/ms-en/marketplace/watson-analytics

  • Weka
    One of a simple library for machine learning is Weka. Weka is a collection of machine learning algorithms for data mining tasks. The algorithms can either be applied directly to a dataset or called from your own Java code. Weka contains tools for data pre-processing, classification, regression, clustering, association rules, and visualisation.
    More information http://www.cs.waikato.ac.nz/ml/weka/

In next blog post, I will elaborate more on the specific details for each library.