difference between machine learning and traditional programming. In traditional programming we tell the machine what to do or the decision making process to reach a certain goal. Like in order to identify a person, look for nose, look for eye, look ear, look for mouth and etc.
but with machine learning we don't tell the machine what to do how to reach a goal. So, if the goal is to recognize human face then we give the machine many faces of human being and let the machine learn it on its own, instead of telling the machine what to do.
This is much like the learning process of human being, where to accomplish a skill we could tell the human specific instructions of what to do or we could just give them the outcome and let the human figure out how to do it.
this could be done through trial and error, and through error human could learn. So for example instead of tellling human what to in order to set up a succesfull business steo by step. Say, think about product and service that are 10x better than the market, assemble a good team, get a good financing, get the marketing going, and so on.
Then in 'machine learning' the human could just have that being 'successful' as the goal and just let the human figure out what to do ... and learn from trial and error.
but with machine learning we don't tell the machine what to do how to reach a goal. So, if the goal is to recognize human face then we give the machine many faces of human being and let the machine learn it on its own, instead of telling the machine what to do.
This is much like the learning process of human being, where to accomplish a skill we could tell the human specific instructions of what to do or we could just give them the outcome and let the human figure out how to do it.
this could be done through trial and error, and through error human could learn. So for example instead of tellling human what to in order to set up a succesfull business steo by step. Say, think about product and service that are 10x better than the market, assemble a good team, get a good financing, get the marketing going, and so on.
Then in 'machine learning' the human could just have that being 'successful' as the goal and just let the human figure out what to do ... and learn from trial and error.
Comments
Post a Comment