To Keep Up With Cutting Edge of Technology

(A guide to machine learning algorithms and their applications)
Mr. Akshay A. Jadhav(jadhavaa@coe.sveri.ac.in)

(Assistant Professor E&TC Department, SVERI's College of Engineering Pandharpur) 

    The term ‘machine learning’ is usually incorrectly, interchanged with AI [JB1], but machine learning is really a sub field/type of AI. Machine learning is additionally often mentioned as predictive analytics, or predictive modeling. Machine learning’ is defined as a “computer’s ability to find out without being explicitly programmed.” There are four sorts of machine learning algorithms: supervised, semi-supervised, and unsupervised and reinforcement.

 

Supervised learning

    In supervised learning, the machine is taught by example. The operator provides the machine learning algorithm with a known dataset that has desired inputs and outputs, and therefore the algorithm must find a way to work out the way to reach those inputs and outputs. While the operator knows the right answers to the matter , the algorithm identifies patterns in data, learns from observations and makes predictions.
Under the umbrella of supervised learning fall: Classification, Regression and Forecasting. 

1. Classification:
    In classification tasks, the machine learning program must draw a conclusion from observed values and determine to what category new observations belong. for instance , when filtering emails as ‘spam’ or ‘not spam’, the program must check out existing observational data and filter the emails accordingly.
 

2. Regression:
    In regression tasks, the machine learning program must estimate – and understand – the relationships among variables. multivariate analysis focuses on one variable and a series of other changing variables – making it particularly useful for prediction and forecasting.
 

3. Forecasting:
    Forecasting is that the process of creating predictions about the longer term supported the past and present data, and is usually wont to analyze trends.
 

Semi-supervised learning
    Semi-supervised learning is analogous to supervised learning, but instead uses both labeled and unlabelled data. Labeled data is actually information that has meaningful tags in order that the algorithm can understand the info , whilst unlabelled data lacks that information. By using this mix , machine learning algorithms can learn to label unlabelled data.
 

Unsupervised learning
    Here, the machine learning algorithm studies data to spot patterns. there's no answer key or human operator to supply instruction. Instead, the machine determines the correlations and relationships by analyzing available data. In an unsupervised learning process, the machine learning algorithm is left to interpret large data sets and address that data accordingly.
Under the umbrella of unsupervised learning, fall: 

1. Clustering:
    Clustering involves grouping sets of comparable data (based on defined criteria). It’s useful for segmenting data into several groups and performing analysis on each data set to seek out patterns.
 

2. Dimension reduction:
    Dimension reduction reduces the amount of variables being considered to seek out the precise information required.
 

Reinforcement learning 

    Reinforcement learning focuses on regimented learning processes, where a machine learning algorithm is given a group of actions, parameters and end values. 

What machine learning algorithms are you able to use? 

    Choosing the proper machine learning algorithm depends on several factors, including, but not limited to: data size, quality and variety , also as what answers businesses want to derive from that data
What are the foremost common and popular machine learning algorithms? 

1) Naïve Bayes Classifier Algorithm (Supervised Learning - Classification) 

2) K Means Clustering Algorithm (Unsupervised Learning - Clustering) 

3) Support Vector Machine Algorithm (Supervised Learning - Classification) 

4) rectilinear regression (Supervised Learning/Regression) 

5) Logistic Regression (Supervised learning – Classification) 

6) Artificial Neural Networks (Reinforcement Learning) 

7) Decision Trees (Supervised Learning – Classification/Regression)
 

References:

1)https://towardsdatascience.com/machine-learning-algorithms-in-laymans-terms-part-1-d0368d769a7b

2) https://www.edureka.co/blog/machine-learning-algorithms/
3) https://towardsdatascience.com/top-10-machine-learning-algorithms-for-data-science-cdb0400a25f9
4) https://en.wikipedia.org/wiki/Machine_learning