How do Artificial Neural Networks Learn ?
2.6 هزار بار بازدید -
4 سال پیش
-
AN03 How do Artificial Neural
AN03 How do Artificial Neural Networks Learn
How does learning happen in ANN?
When an ANN is generated all the weights and biases are initialized randomly. Predicted output of such ANN for any input will in general have large error with respect to actual or target output. So next question is “How does an ANN learn to predict correct output ?”
Learning of ANN is also inspired by the way humans learn. One of way in which humans learn is under guidance or supervision of a guide or a teacher. For example, when we learn to solve new type of problem we first go through some solved examples where we know both the question and answer to learn how we get output from input. Then we attempt unsolved questions and check the answer in the answer key to see if our answer is same as actual or expected answer given in the answer key. If our answer is correct then we move to next question. If our answer is incorrect then we go back and revise the concepts or review the solved examples and try to find where we went wrong. And we attempt the question again till we get the correct answer. This type of learning under supervision of actual of expected answer is called supervised learning. In the same way an ANN learns under supervision of actual or expected output in supervised manner.
Unlike learning to solve well defined mathematical problems where our answer is exactly same as actual or expected answer, ANNs in general may not be able to predicts exact same output as actual or expected output for all the inputs. In general, there will always be some error and our objective of learning is to come up with weights for links and biases for nodes that will minimize the cumulative error for all input output pairs in our training dataset.
The function that measures the cumulative error is called Loss Function or Cost Function. And our objective is to minimize the Loss Function or Cost Function. Therefore, the loss function is also called objective function. There are several loss functions that we can use for training ANNs depending on the type of problem we are solving.
Mean Absolute Error (MAE or L1 Loss)
Mean Squared Error (MSE or L2 Loss)
Mean Squared Error Mean Absolute Error
Sensitive to outliers ( Non very robust) Not sensitive to outliers ( Robust)
Stable Not stable
Always one solution Possibly multiple solutions
Cross Entropy Loss Function
Cross-entropy loss, or log loss, is used to measures the performance of binary classification models whose outputs are probabilities. Cross-entropy loss increases as the predicted probability diverges from the actual label.
How does learning happen in ANN?
When an ANN is generated all the weights and biases are initialized randomly. Predicted output of such ANN for any input will in general have large error with respect to actual or target output. So next question is “How does an ANN learn to predict correct output ?”
Learning of ANN is also inspired by the way humans learn. One of way in which humans learn is under guidance or supervision of a guide or a teacher. For example, when we learn to solve new type of problem we first go through some solved examples where we know both the question and answer to learn how we get output from input. Then we attempt unsolved questions and check the answer in the answer key to see if our answer is same as actual or expected answer given in the answer key. If our answer is correct then we move to next question. If our answer is incorrect then we go back and revise the concepts or review the solved examples and try to find where we went wrong. And we attempt the question again till we get the correct answer. This type of learning under supervision of actual of expected answer is called supervised learning. In the same way an ANN learns under supervision of actual or expected output in supervised manner.
Unlike learning to solve well defined mathematical problems where our answer is exactly same as actual or expected answer, ANNs in general may not be able to predicts exact same output as actual or expected output for all the inputs. In general, there will always be some error and our objective of learning is to come up with weights for links and biases for nodes that will minimize the cumulative error for all input output pairs in our training dataset.
The function that measures the cumulative error is called Loss Function or Cost Function. And our objective is to minimize the Loss Function or Cost Function. Therefore, the loss function is also called objective function. There are several loss functions that we can use for training ANNs depending on the type of problem we are solving.
Mean Absolute Error (MAE or L1 Loss)
Mean Squared Error (MSE or L2 Loss)
Mean Squared Error Mean Absolute Error
Sensitive to outliers ( Non very robust) Not sensitive to outliers ( Robust)
Stable Not stable
Always one solution Possibly multiple solutions
Cross Entropy Loss Function
Cross-entropy loss, or log loss, is used to measures the performance of binary classification models whose outputs are probabilities. Cross-entropy loss increases as the predicted probability diverges from the actual label.
4 سال پیش
در تاریخ 1399/02/06 منتشر شده
است.
2,665
بـار بازدید شده