Technical discussions about the implementation and research of speech recognition algorithms.
=A0Hello everybody, =A0I am doing a research on classification of audio signals using neural ne= tworks. My question is : On what basis we determine the maximum number of e= pochs needed for training the NN? and also how do we choose the value of the performance function(e.g. mse)? =A0 I appreciate very much the help of you. =A0 =A0 =A0 =A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0= =A0=20 =A0 =A0 =A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0= =A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=20 =20=20=20=20=20=20 _____________________________________