Understanding Machine Learning

Paras Patidar
Jan 14, 2019 · 2 min read

What is Machine Learning?

Machine Learning is one of the fastest growing areas of computer science with, far-reaching applications. Basically, Machine Learning is a system that has the ability to automatically learn and improve from past experiences without being explicitly programmed.

When Do We Need Machine Learning?

When do we need machine learning rather than directly program our computers to carry out the task at hand? Two aspects of a given problem may call for the use of programs that learn and improve on the basis of their “experience”:

  1. Tasks That Are Too Complex to Program

-> Tasks Performed by Animals/Humans:

Examples of such tasks include driving, speech recognition, and image understanding. In all of these tasks, state of the art machine learning programs, programs that “learn from their experience,” achieve quite satisfactory results, once exposed to sufficiently many training examples.

-> Tasks beyond Human Capabilities:

Another wide family of tasks that benefit from machine learning techniques is related to the analysis of very large and complex data sets: astronomical data, turning medical archives into medical knowledge, weather prediction, analysis of genomic data, Web search engines, and electronic commerce.

2. Adaptivity

One limiting feature of programmed tools is their rigidity — once the program has been written down and installed, it stays unchanged. However, many tasks change over time or from one user to another. Machine learning tools — programs whose behavior adapts to their input data — offer a solution to such issues; they are, by nature, adaptive to changes in the environment they interact with.

Types of Learning :

  1. Supervised Learning

In the Supervised Learning, the training data includes both the Features(Inputs) and the Labels.

-> Regression

In Regression Problem, we are trying to predict result with the Continuous Output.

-> Classification

In Classification Problem, we are trying to predict result with the Discrete Output.

2. Unsupervised Learning

In the Unsupervised Learning, the training data includes the Features(Inputs) and not the Labels. Here, we do not tell the system where to go the system has to understand from the data given.

It is difficult to implement then supervised learning because we do not know the desired output and its difficult to train the model.

3. Reinforcement Learning

In Reinforcement Learning, the machine is trained to make specific decisions. The machine is being exposed in an outside environment where it trains itself continually using trial and error.

So Let’s get started with Machine Learning. Keep watching this and follow CodinGurukul for more tech articles or you can reach out to me for any doubt and suggestions and the next blog series will be published soon.

Visit: MLAIT - We Code For Better Tomorrow

CodinGurukul

Coding Gurukul is an entrepreneurial journey nurtured by technological evangelist with a mission to create a developer ecosystem around the nation. Its prime focus in its initial journey is to break the inertia and merge the gaps between IT specialists and University students.

Paras Patidar

Written by

Machine Learning Enthusiast |Founder@MLAIT | Code-In Mentor@Tensorflow | ExploreML Facilitator | Core Member at DSC-LPU

CodinGurukul

Coding Gurukul is an entrepreneurial journey nurtured by technological evangelist with a mission to create a developer ecosystem around the nation. Its prime focus in its initial journey is to break the inertia and merge the gaps between IT specialists and University students.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade