What can be the reason while Multi layer perceptron is not converging but SVM or Random forest is performing well on same dataset? My Data is 120 features having numeric values between -1 to 1 and need to predict any of 5 classes. Note: I am not aware about what data this is?
SVM accuracy 91% Random forest 86% 2 layer MLP acc 74% after 3500 epoch
that's not a wierd behaviour. In general that can happen, Neural Networks are also very good in classification and Feature Extraction as also SVC and Random Forrest Classifier. If you are using SKlearn though, neural network have limited design that's why Tensorflow is considered way better if you need to do something with neural networks. It can also depend on the data, you didnt show any code though that's why in general it can also depend on the Data and what you are trying to do with it. So it can be anything but as I said probably if you are using sklearn Random Forrest and SVC will give a better result. that's what I personally noticed from my Experience. hope it help
