Machine Learning
Group Mates:-
Khushboo Fatima 43-BSCS-12
Fatima Riaz 61-BSCS-12
Madiha Arif 129-BSCS-12
Synopsis:-
Machine learning is a scientific discipline that
explores the research into artificial intelligence. It has strong ties to statistics and mathematical optimization, which deliver
methods, theory and application domains to the field. Field of study
that give computers the ability to learn without being explicitly programmed.
Our major area of discussion will be robotics, chatbots,
etc. Machine learning tasks are typically
classified into three broad categories which are supervised learning,
unsupervised
learning
and reinforcement
learning.
Machine learning
focuses on prediction, based on known properties learned from
the training data.
I have always been a fan of artificial intelligence and machine learning . Making a human-like non-living but living creature is one of the state-of-the art skills ,
ReplyDeleteBut i do have a few questions about it . The two things are totally different
1-the real world
2-the imaginative representation of the real world
the supervised learning is mostly done in the the imaginative representation of the real world (the 2nd one ) , sometimes it gives good results but sometimes it doesn't .
My question is why do we generalize the outcomes for the supervised learning platform over the real world platform knowing that they are two totally different things (practically speaking ) . And for me (as far as i know ) , unsupervised learning is better than supervised but why do we give more preference to the second one ? ...
Supervised learning is powerful when the classifications are known to be correct or when the classifications are simply arbitrary things that we would like the computer to be able to recognize for us. Supervised learning is often necessary when the decisions made by the algorithm will be required as input somewhere else. Otherwise, it wouldn't be easy for whoever requires that input to figure out what it means.
ReplyDeleteBoth techniques can be valuable and which one you choose should depend on the circumstances--what kind of problem is being solved, how much time is allotted to solving it (supervised learning or clustering is often faster than reinforcement learning techniques).