Supervised Machine Learning: The point where your AI journey starts

mediumThis post was originally published by Harsh Ris at Medium [AI]

Image for post
Are you new or have already embarked on this journey

Machine Learning

Machine Learning, Deep Learning and Artificial Intelligence are a few terms which are used interchangeably and often lead even practitioners with excellent industry and research experience pondering over when to use which term.

With the rise in the digital era, Artificial Intelligence has acted as fuel to fire where it’s being applied to almost every domain we know of today.

Image for post
Let’s get back to early definitions

It was a term coined by John Mccarthy in 1956 at a workshop at Dartmouth College to distinguish the field from cybernetics.

Artificial Intelligence refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The term may also be applied to any machine that exhibits traits associated with a human mind such as learning and problem-solving.

Image for post

The term machine learning was coined in 1959 by Arthur Samuel, an American IBMer and pioneer in the field of Computer Gaming and Artificial Intelligence

Tom M Mitchell provided a widely quoted, more formal definition of the algorithms studied in the machine learning field

Machine learning (ML) is the study of computer algorithms that improve automatically through experience. It is seen as a subset of artificial Machine learning algorithms build a model based on sample data, known as “training data”, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or infeasible to develop conventional algorithms to perform the needed tasks.

Image for post

Rina Dechter in her article “Learning While Searching in Constraint-Satisfaction Problems” published in 1986, where she introduced the concept of Deep Learning. She called deep learning the idea of getting to know all the possible information out of a dead-end, meaning recording all the search space explored in order to improve the learning performance.

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction.

The AI Roadmap

Image for post
You need to know it all with time not immediately

The image you see above is really helpful in situations where you have to decide what problem to counteract with which type of AI use case and algorithm it can be clearly seen how machine learning is divided into classical machine learning, Deep Learning, Ensemble Methods and Reinforcement Learning.

In this article, we would only be covering supervised Machine Learning.

Image for post
Mapping inputs to outputs

Supervised Machine Learning is where we have input variable(x) and output variable(y) and we try to compute a function that maps x to y such that: Y=f(x).

Our end goal is to approximate a mapping function so well that when a new input is passed it can predict the new output with minimal errors.

It is further divided into two categories.

1. Classification

2. Regression


Classification is a problem where the output variables are categories and are discrete in nature such as red, blue or patient having fever and no fever.

Some of the Classification Algorithms include:

  1. Naive Bayes
  2. KNN
  3. SVM
  4. Decision Trees
  5. Logistic Regression


A regression problem is when the output variable is a real value and can be continuous in nature, such as “dollars” or “weight”.

Some types of regression algorithms are

1. Linear Regression

2. Multivariate Regression

3. Ridge/Lasso Regression

4. Bayesian Linear Regression

Do note that by continuous in the two examples we mean that the weight can be 15 kg and 15.2,15.4,15.7 and can take decimal values similarly dollars can take values as $20.25 etc.

Stay tuned for more such content and in-depth knowledge of each topic.

Spread the word

This post was originally published by Harsh Ris at Medium [AI]

Related posts