What is Machine Learning ? | Machine Learning Tutorial | Gautam Siwach
#machinelearning #sentinels #illustration #tutorial
What is machine learning? Is Machine Learning sentient already ?
Machine learning is a concept or a practice of implementing the probabilistic and statistical methods to devices which appear to function seamlessly in order to provide meaningful outcomes.
Dimensions are the capacity to represent the degree of data. For example, imagine a family chart and the features of each person in that as a degree. Compression also describes the dimensions to how many layers data Is encrypted.
The number of input variables or feature columns in the given data said are dimensions in machine learning for example salary of employees based on skills and years of experience.
What is Clustering in machine learning ?
In machine learning we often group examples as a first step to understand data sets, this grouping of unlabeled data points is clustering.
Some examples are ad campaigns, customer segmentation, and building recommender systems.
What is Classification in Machine Learning -
Classification is a technique which is used to identify and classify the objects with similar features. These classifications are then stored and used for further inferencing, for example using classification models for things like image recognition and customer retention. At times, classification is based on variables in the data sets. For example, establishing the class of an object based on the relationship between a dependent and a set of independent variables.
What is Regression in Machine Learning ?
Regression is a statistical method , Using this statistical method we can establish the strength in the relationship among two or more variables. For example, we can regress to predict the likelihood of attempting the login activity into an account, when the password is hacked.
Dimensions and clustering are both part of unsupervised learning.
Whereas, classification and regression are both part of supervised learning.
The main difference between supervise learning and unsupervised learning is that there is a set of rules to refer in case of a supervised learning or while running a supervisor model, like eye in an image has to be a match to eyes in another image or a dataset of images.
On the other hand Unsupervised learning is a model running without a set of rules and with a goal of identifying certain characteristics / unknown data points in unlabeled data set .
Both of these are a way of common machine learning techniques and are helpful in decision making .
Some of the common machine learning algorithm are
1. Linear model
2. Tree based
3. Neural networks
At the end of the day we know that Machine learning is a subset of artificial intelligence. With feature engineering, building models, training datasets, and targeted modeling etc., the ability of devices to communicate can be augmented.
