What is machine learning and why it is becoming sensation ?


The term “Machine Learning” is becoming quite popular now a days that made me think what and how this method of computation is trying to solve a problem.


in progress 0
Computer anonymous 1 year 1 Answer 842 views 0

Answer ( 1 )

  1. Ever seen the ads section of your Facebook profile? Or what items Amazon/ Snapdeal or Flipkart recommends you if you log in? Did you wonder how the recommendations seem to always be about such items that you have been wanting to buy? That is one example of Artificial Intelligence (AI) or Machine Learning (ML).

    Machine Learning is the computer science algorithm by which computer itself learn it by the previous experience and make proper conclusion and improvement. It is advanced version/ extension of artificial intelligence. When Computer was invented, it was said to be Machines don’t”learn” in the way you and I do. But now We have amazing pattern matching abilities that allow us to “encode useful patterns.” Machines don’t largely have a notion of “useful”. But there is a notion of feedback, and in some ways, the idea is mildly similar.

    Machine learning relies entirely on data. The more data (and the higher the quality of data) an algorithm has, the more accurate it becomes. Machines “learn” when they take a series of input data items and, based on some mathematical criteria, they correctly chose an algorithm (a pattern of sorts) to apply to that input so that the output is acceptable to the user. Being accepted or not accepted is important because that feedback information accumulates and feeds into the selection criteria used to select the algorithm to use. It’s a closed feedback loop.

    Now a days, it is widely used for various purposed. Some application domains of Machine Learning are:
    Machine perception, Computer vision, including object recognition, Natural language processing, Syntactic pattern recognition, Search engines, Medical diagnosis, Bioinformatics, Brain-machine interfaces, Cheminformatics, Detecting credit card fraud, Stock market analysis, Classifying DNA sequences, Sequence mining, Speech and handwriting recognition, Game playing, Software engineering, Adaptive websites, Robot locomotion, Computational advertising
    Computational finance, Structural health monitoring, Sentiment analysis (or opinion mining), Affective computing
    Information retrieval, Recommender systems, Optimization

    So, basically you can use it to solve any of your problems that lie in any of these domains :).

Leave an answer