Original article was published by Divyanshu Parkhe on Artificial Intelligence on Medium
Let’s ask very small questions to ourselves, When We were Kid, how we learn things?
We used to curious about everything which is happening surround us, why it is happening and what’s the name of the things, we do ask various curious questions to our parents, grandparents or relatives they teach you and give your question’s answer, the similar way in present era for us to make our life more easier “Artificial Intelligence” comes in to assist in our day to day Life/activity/action/movement etc..
Near my home there were two different animals, I ask my friend what is this and that, my friend pointed on one beautiful Animal and he told me this is a Cow so he labeled a name that if you see this kind of animal then we will call as Cow and pointed to other animal and he said that is Cat so he labeled next name that if you see this kind of small animal which looks with this properties then will call it as Cat.
Now you may get some idea from my small story, that how I learned and made a classification between two animals, that’s how we learn in day to day life and there will be someone or some source from where we can learn if we make any mistake in our day to day life.
The Similar way How kids learn, Machines also can learn from data… and that’s the World of Machine Learning…
here some Standard Definitions I’m presenting to you >>
The term “Machine Learning” was coined by Arthur Samuel in 1952. Arthur Samuel describes Machine Learning as-
Machine Learning — “Field of study that gives computers the ability to learn without being explicitly programmed”
Tom Mitchell provides a more modern definition:
“A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.”
For example, your Email Spam filter is a Machine Learning Program that can learn Label Spam (flagged: given by the user) whether Spam or ham(not spam).
So I hope we understand now As defined by Professor Tom Mitchell, Machine learning refers to a scientific branch of AI(Artificial intelligence (AI), as defined by Professor Andrew Moore, is the science and engineering of making computers behave in ways that, until recently, we thought required human intelligence), which focuses on the study of computer algorithms(An algorithm is a process that follows a set of rules, a problem solver — mainly used by computers) that allow computer programs to automatically improve through experience.
I think above line is bit complicated and covered multiple things, just read 2–3 times!
Now We will learn where Machine Learning can play a great role-
> Complex Problem where traditional method can’t find good solution then we can approach Machine Learning algorithms to accomplish task.
>Getting Insights of large amount of data.
>Machines can learn the data and algorithms responsible for causing faults in the system and use this information to identify problems before they arise.
>Image & Video Recognition.
>Recommendation Systems….. and so on..
Types Of Machine Learning –
In general, any machine learning problem can be assigned to one of two broad classifications:
Supervised learning — In supervised learning, we are given a data set and already know what our correct output should look like, having the idea that there is a relationship between the input and the output.
The training data you feed to algorithm includes the desired solution ,called label.
Supervised learning problems are categorized into “regression” and “classification” problems.
Regression — In a regression problem, we are trying to predict results within a continuous output, meaning that we are trying to map input variables to some continuous function.
Example: Given a picture of a person, we have to predict their age on the basis of the given picture
Classification — In a classification problem, we are instead trying to predict results in a discrete output. In other words, we are trying to map input variables into discrete categories.
Example– Given a patient with a tumor, we have to predict whether the tumor is malignant or benign.
Unsupervised learning — Unsupervised learning allows us to approach problems with little or no idea what our results should look like. We can derive structure from data where we don’t necessarily know the effect of the variables.
We can derive this structure by clustering the data based on relationships among the variables in the data.
So here the training data is unlabeled ,the system tries to learn without a teacher.
Example — Clustering: Take a collection of 1,000,000 different Animals, and find a way to automatically group these Animals into groups that are somehow similar or related by different variables, such as size , shape, look, and so on.
Machine Learning is comes with great opportunity to learn and explore to make it happen you should be Curious , Judgmental & Story Teller.
Lots of research is going on , day to day new ideas are coming, you also come up with something and do something exciting to change the world of AI. if you are really want to make it happen some magic in your life join Machine Learning ,AI world with full dedication and Love.
Note: This is my first article On Medium as well on Machine Learning, If any suggestion you are very welcome!!