__Machine Learning, Types and its Applications__

Machine learning is a subset of computer science that can be evaluated from “computational learning theory” in “Artificial intelligence”. By definition it is a “Field of study that gives computers the ability to learn without being explicitly programmed”. Machine learning mainly focuses in the study and construction of algorithms and to make predictions on data through the use of computers.

Machine learning is also a method used to construct complex models and algorithms to make predictions in the field of data analytics. These analytical models allow researchers, data scientists, engineers and analysts to “produce reliable, repeatable decisions and results” and uncover “hidden insights” through learning.

__Types of Machine Learning:__

Machine learning types are typically classified into three broad categories, depending on the nature of the learning “signal” or “feedback” available to a learning system. These are:

- Supervised learning
- Unsupervised learning
- Semi-supervised learning
- Reinforcement learning
- Deep learning

Among all first two methods have more uses.

__Supervised learning:__

Supervised learning is the task of inferring a function from labelled training data that consists set of training examples, each example is a pair of an input object (typically a vector) and a desired output value (also called the *supervisory signal*). A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples. An optimal scenario will allow for the algorithm to correctly determine the class labels for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a “reasonable” way.

Methods used in supervised learning:

- Regression (Logistic Regression, Gaussian process regression, multinomial regression..etc)
- Bayesian statistics
- Artificial neural network (ANN)
- ANOVA (analysis of variance)
- Decision tree

__ __

__Unsupervised learning:__

Unsupervised learning is the machine learning task of inferring a function to describe hidden structure from unlabeled data. Since the examples given to the learner are unlabeled, there is no error or reward signal to evaluate a potential solution. In general No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end.

Methods used in unsupervised learning are:

- Clustering( K-means,mixture models,hierarchical clustering)
- Neural networks (hebbian learning)
- Expectation-maximization algorithm(EM)
- Method of moments
- Blind signal separation techniques(principal component analysis. independent component analysis, Non-negitive matrix factorization, singular value decomposition)

__Reinforcement learning:__

Reinforcement learning is concerned with how an *agent* probable to take *actions* in an *environment* so as to maximize some notion of long-term *reward*. Reinforcement learning algorithms attempt to find a *policy* that maps *states* of the world to the actions the agent probable to take in those states.

Methods used in reinforcement learning are:

- Criterion of optimality
- Brute force
- Monte Carlo methods
- Temporal difference methods
- Direct policy search

__Semi-supervised learning:__

It is a mixture of small amount of labeled data and large amount of unlabeled data .It is a class of supervised learning tasks and techniques that makes use of unlabeled data for training.

Methods used in Semi-supervised learning:

- Generative methods
- Low-density separation
- Graph based methods
- Heuristic approaches

__Deep learning:__

Deep learning consists of multiple hidden layers in an artificial neural network. This approach tries to model how the human brain processes light and sound into vision and hearing. Some successful applications of deep learning are computer vision and speech recognition. It is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using multiple processing layers, with complex structures.

__ __

__Applications of Machine learning:__

There are wide variety of applications of machine learning, some of them are:

- Detecting Credit Card fraud
- Stock market analysis
- Marketing Programs
- Bioinformatics
- Automatic speech recognition
- Image recognition
- Natural language processing
- Drug discovery and toxicology
- Search engines
- Adaptive websites etc

__Compiled By:__

P Srilakshmi

Srilakshmi is M.Sc Statitistics and possess 2 years of reach experience in her field. Currently she is working as Analyst Intern with NikhilGuru Consulting Analytics Service LLP, Bangalore.

__Source:__

https://en.wikipedia.org/wiki/Supervised_learning

https://en.wikipedia.org/wiki/Machine_learning

__Reviewed By:__

Dyuti Lal

CEO, Managing Partner

NikhilGuru Consulting Analytics Service LLP, Bangalore

## Be the first to comment on "Machine Learning, Types and its Applications"