My Favorite Technology
One of the trending words among youth nowadays, especially among people associated with IT industry, is ARTIFICIAL INTELLIGENCE and it is my favorite technology too. It may be defined as the ability of machines to think and act rationally. If a machine can carry out a conversation with a human being without letting a human being that he/she is talking to a machine and not a real human, the machine passes the Turing Test. One such machine is Google Duplex.
Artificial Intelligence is of following types:
1 WEAK OR NARROW AI
AI trained to perform a single task within a pre-defined range.
2 GENERAL OR STRONG AI
AI which can think itself with full cognitive abilities like humans.
3 SUPER AI
It denotes hypothetical agent that possesses intelligence surpassing human intelligence.
A subset of ARTIFICIAL INTELLIGENCE is MACHINE LEARNING. It may be defined as the ability of machines to take decisions without explicitly being programmed. A machine automatically learns from experience.
Following are the stages of Machine Learning:
Sufficient data is given to machine to train it.
Testing with a subset of real data called the validation set and choosing best fit algorithm.
3 TEST AND DEPLOY
The final algorithm is tested with another subset of data called test set. It is then deployed and observed in live scenario.
Following are the types of MACHINE LEARNING:
1 SUPERVISED ML
It is a branch of ML that learns on the basis of labelled training data. For example, a chatbot recognizes greetings such as ‘HELLO’, ‘HI’ etc based on classified text.
2 UNSUPERVISED ML
Unsupervised ML learns from test data that has not been labelled. It works on the basis of clustering. For example, grouping similar resumes based on text patterns.
3 REINFORCEMENT LEARNING
It is about taking suitable action to maximize reward in a particular situation. For example, how to play chess.