The base technique of a traditional machine learning or artificial intelligence
algorithm has a target for learning and the learning technique based on mainly
pattern matching, like artificial neural network has a target and for every
learning attempt it matches it’s input with the target and adjust the weights
to get the target. If we consider genetic algorithm, we have to calculate
fitness function and evaluate the function for the target….. And so on.
Thinking simply these algorithms are working / learning based on pattern
matching. Or if we think more simply, these techniques are like that some data
stored in database, machines are doing nothing but finding, probability calculating,
predicting some results based on matching .
When we are using search engines, we just enter some keywords and the search engines show you the result. When you search (or ask) something to a human, most of the times he may inquiry about your question several times and after confirming about your question, he will say you a result. If you search with the keyword “apple store” search engine will not understand what you are searching for (fruit store or mac store), as well as this search query also confuse a human also, that’s why he ask you 2nd time. Personally I always wanted the search engines with discussing feature. And the discussion will not with some predefined questions. A dynamic discussion between user and search engine such like you are talking with an intelligent agent.
No comments:
Post a Comment