ANN is an effort to simulate our brain's act of learning and recognition. So as we learn things when we see/listen/taste/feel first time, and then are able to recognize next time, similarly ANN learns first what information we feed it, then in recognition phase it will recognize that thing even it is not exactly same but must belong to same type of data for which it was trained. For that purpose we need to train it once for a particular case and no need to train it again and again. For example, if you train ANN for an image having cars and trucks, then in training phase you will give the data/ features of different models of cars and trucks. You can save the trained file/weights and can use anywhere under same conditions for similar recognition purpose. However, if you want to add more models or more objects then you must train it again.
Dear ANN experts,In one of my projects I need to use Artificial Neural Networks (ANN). I need to study the subject in depth but could you please give some quick info. regarding the following:How ANN works? I mean how do we train ANN? For example if we train an ANN on some pattern (e.g. image) for a given case do we need to train again the network when we deal a new similar case or could be save this training information and use it when needed later? In short could we remember training information or we need to retrain every time we need to compare a given pattern with another pattern?Could you please comment urgently to clarify the above?Best,Uzma
No comments:
Post a Comment