Monday, 26 December 2016


Why do we believe strangers?

"Absence of evidence is not evidence of absence!"  -- Carl Sagan, Astronomer
This is what our brains are simply not wired to understand.

We have commonly seen while travelling unknown places we usually ask strangers for direction to the destined place and believe them whatever they say. Its, not the lack of our knowledge that makes it easy to believe them but our inherent behaviour. The more trustworthy the appearance of that person the easier it is to believe (Topic for next blog). It's not optimism. Another place where we usually see this unusual sense of belief is when a salesman presents you with the product you have never seen before. We instantly think that at least the product deserves a try with the subconscious belief for it to be good. There are a countless number of experiences that prove that it is second to our nature to believe people.

What is it that makes us so goody goody beings? Human brain perceives the real world in terms of information and tries to figure out the responses necessary. Whenever it is presented with the set of facts it first assumes it to be true and then tries to disprove it by retrieving the relevant information from the memory. And when the information required for disproving that fact is absent it ends up believing the fact to be true. This is the flaw or shortcut in the working of our brain that makes us believe in new things no matter how faulty they are.

Let's see once more what had happened earlier. When you ask a stranger about the direction your brain is presented with a choice to either believe or disbelieve. Your brain takes the input and at first, assumes it to be true. After this it tries to search the memory for the related thoughts like have I been fooled by someone similar to him in anyways. It also tries to match everything that is possible to get even a clue of not believing him. Once this task is over and no incidents or relation are found brain registers it to be truth and believes the stranger (kind of similar to giving the benefit of the doubt). Proof by contradiction is the primary method that brain uses whenever it is presented with any new information.

It can result in positive or negative results depending on the situation you are in. If stakes are too high for mistakes it's better to dig up information or take help of others in deciding about it. It can also be used to your advantage if you are a salesman or startup pitcher :P

It's a really subtle thing to note but weighs a lot if you want to be analytical about your judgement. Yes, it cannot be eliminated completely but more you know the better about why you think what you think. And it is not only limited to this but to all scenarios that involve belief.

Tuesday, 17 May 2016

Regression ( Part - 1 )


Under machine learning there are two prominent categories of algorithms or technique :
Regression : Predict real-valued output
Classification : Predict discrete-valued output

What I am gonna discuss in this post is the Idea of regression and the various ways in which we can really picture that what is actually going on. This will be a long post ( Relatively :-D )

Friday, 29 April 2016

Data and Variables

What do we really mean by data?
Data are pieces of information about individuals organized into variables. By an individual, we mean a particular person or object. By a variable, we mean a particular characteristic of the individual.

 A dataset is a set of data identified with particular circumstances. Datasets are typically displayed in tables, in which rows represent individuals and columns represent variables.


Variables can be classified into one of two types: categorical or quantitative.
  • Categorical variables take category or label values and place an individual into one of several groups. Each observation can be placed in only one category, and the categories are mutually exclusive.
    In our example of medical records, Smoking is a categorical variable, with two groups, since each participant can be categorized only as either a nonsmoker or a smoker. Gender and Race are the two other categorical variables in our medical records example. (Notice that the values of the categorical variable Smoking have been coded as the numbers 1 or 2. It is common to code the values of a categorical variable as numbers, but you should remember that these are just codes. They have no arithmetic meaning (i.e., it does not make sense to add, subtract, multiply, divide, or compare the magnitude of such values).
  • Quantitative variables take numerical values and represent some kind of measurement.
    In our medical example, Age is an example of a quantitative variable because it can take on multiple numerical values. It also makes sense to think about it in numerical form; that is, a person can be 18 years old or 80 years old. Weight and Height are also examples of quantitative variables.
               

Wednesday, 27 April 2016

 

Getting Started in Machine Learning ?


Machine Learning is one of the most intriguing field of computer science. You do not need a degree to learn and practice machine learning. In fact, you don’t need a degree if you want to explore research in machine learning. It's fun to learn.

MOOCs are the best ways to kick start in some field with a good book of that to read when free.

Some great examples of Machine Learning MOOCs include :

Examples of good textbooks are:

 

Once you get started with the courses and books you should start looking out for data to practice on. "Learn and Implement" is the best way to ensure whether you know your stuff or not.
Data can be collected from various sources like Kaggle and TunedIt.

The skills that you learn are applicable in industry, but real-world problems do require more than that. This area of learning is not for everyone, but does offer a lot for those whom it does suit.

Competitions are often held in conjunction with academic conferences. Recent companies have opened up their data to competitions to get more out of the best brains of this world.

Saturday, 23 April 2016

What is Machine Learning?

 

You :  Ha Ha ! So what exactly is machine learning. 

Me  :  Machine Learning, a subfield of computer science.

You :   -_-   I knew this already !

Me  :  Okay, Let me think......

Me  :  It is a field of study which give machines, power to learn from the patterns and analogies and figure out a way to infer or predict from data. It's powerful.


You : What is "data" in your context ?

Me  : Data refers to facts and statistics collected together for reference or analysis.
 

You : You spoke of predictions. How are machine learning and statistics related  then ? 

Me  : Machine learning and statistics are closely related fields. Mathematical models and tools of ML have had a long pre-history in statistics.



You : You brag about it so much, where is it used ?

Me  : Ummm... You found this page with the help of Google it uses ML to suggest you this page out of the millions of pages out there. You buy goods online they implement some form of ML to recommend goods to you. And not to forget facebook's news-feed it also uses ML to show the relevant news or activities.


You : When you say power to machines what do you mean ?

Me  : I mean by machine learning we are able to get machines to think.


You : How is this possible, machines aren't intelligent and can't think ?

Me  : Lets say machines are not intelligent because they do not take decisions on their own, but can't we say the same for us. Aren't we doing the same thing. In our life our every decisions are backed up by the experiences ( Data ).

 
My Question : Do we have a proper concept of intelligence ?

Wednesday, 20 April 2016

I will now be blogging about my work on Machine Learning and Data Science.
As the things get along I will also implement strategies or methods to real life problems that are on kaggle and topcoder.

Vijay Krishnavanshi


I am a computer science undergraduate from India.


















I love to teach, travel and play guitar