I am doing thesis on baby cry detection, i build the model with CNN and KNN, i got train accuracy of CNN is 99% and Test accuarcy is 98% and KNN train accuarcy is 98% and Test accuracy 98%.
please suggest me which algorithms i should choose from both of them and why?
hello
The accuraies are almost the same however the computation time and complexity is more with CNN than KNN.
I will suggest you to compute the inference time, if you use KNN with 1 neighbor it tends to overfit but if you are using more neighbors then its OK i guess and the inference time will be lower. The accuracy is not significant in your case its almost the same.
i had used K =1 neighbor after grid search hyper parameter tuning .
I would suggest you to use the simpler one, which is by itself a good reason (Easier to code, fewer hyperparameters to adjust, reduced computational complexity). Another important justification is that you compared it with more powerful techniques, such as CNN, and obtained similar accuracy.
- Badges
- Science topic
- Similar topics
- Organizational Psychology
- Training