Crossentropy loss function - What is a good performance goal?
Good Afternoon, Looking around ANSWER and exploring GOOGLE GROUPS i found this method by Dr. Greg Heath to define a valid training goal for the MSE performance function: [I,N]=size(x); [O,N]=size(t); MSE00a=mean(var(t,0,2)); Ntrn=floor(0.7*N); Hub=floor((Ntrn-O)/(I+1+O)); MSEgoal=0.01*(Ndof/Ntrneq)*MSE00a; And i was wondering if there is a similar method to set a Crossentropy reference goal for neural net performance, since i want to experiment different type of loss functions in order to get the best results.
Kshitij Singh answered .
2025-11-20
The cross-entropy operation is essential for computing the cross-entropy loss between network predictions and target values in both single-label and multi-label classification tasks.
The crossentropy function calculates the cross-entropy loss between predictions and targets represented as dlarray data in MATLAB. Using dlarray objects simplifies handling high-dimensional data by allowing dimension labeling. You can label dimensions for spatial, time, channel, and batch as "S", "T", "C", and "B", respectively. For unspecified dimensions, use the "U" label. When using dlarray functions that operate over specific dimensions, specify the labels directly within the dlarray object or by using the DataFormat option.