Introduction - Data Science - Part 2

Hi Everyone, in this article I am going to talk about Machine Learning (ML), which is neural system of Data Science. Why ML is Neural System of DataScience, because we can’t perform any of the DS activity without ML.

Machine Learning is the process to educate computer to take their own decisions by feeding them data and information in the form of observations and real-world interactions. Simply computer learn from experience same as humans. Machine learning is closely related to computational statistics, which focuses on making predictions using computers. Machine learning algorithms use computational methods to learn information directly from data and the algorithms adaptively improve their performance as the number of samples available for learning increases.

There are a 3 kind of Machine Learning approach

Unsupervised Learning – Unsupervised learning finds hidden patterns or intrinsic structures in data. In unsupervised learning, the learning algorithm has only the input data & knowledge is extracted from these data. These algorithms create a new representation of the data & help to improve the accuracy. Dimensionality reduction algorithm & Clustering are the common Unsupervised learning algorithm. We should Unsupervised learning when we need to explore our data and want to train a model to find a good internal representation, such as splitting data up into clusters.

Supervised Learning – In Supervised learning, machine helps the algorithms, learn to predict the output from the input data. This approach basically teaches machines by example. Supervised learning algorithms are used when we have labelled data and trying to find a relationship model from the data. Supervised learning uses classification and regression techniques to develop predictive models. We should choose supervised learning when need to train a model to make a prediction (for example, the future value of a continuous variable, such as temperature or a stock price) or a classification (for example, identify makes of cars from webcam video footage).

Reinforcement Learning - Reinforcement learning is the training of machine learning models to make a sequence of decisions. An example of reinforcement learning is Google DeepMind's Deep Q-network, which has beaten humans in a wide range of vintage video games. The system is fed pixels from each game and determines various information about the state of the game, such as the distance between objects on screen. It then considers how the state of the game and the actions it performs in game relate to the score it achieves. 

Use of Machine Learning – There are few use cases of ML.

·        Prediction

·        Image/Audio Recognition

·        Videos Surveillance

·        Spam and Malware

·        Traffic Prediction

·        Email Spam and Malware Filtering

·        Medical Diagnosis

·        Automatic Language Translation

·        Chatbot

·        Stock Market trading

There are lot of things need to cover under DS which I will continue in my upcoming articles.