Community
cancel
Showing results for 
Search instead for 
Did you mean: 
mo_bri
New Contributor I
905 Views

101 Curie NN questions about effectiveness - incorrect classification on the SAME training data

Hi,

I have processed some OCR figures (I will post a paper on this soon on my blog), the images are now contained in a <127 uint 8 array, so they can be trained into the currie 101 NN hardware NN.

My question is this

I train my NN with a set of data, it learns 10 images, and has 10 committed neurons

I then test my NN with the same data, and it recognises 19 out of 20 images correctly, one it gets wrong.

Is this normal/ok ?

Also...

Can I reduce this error by repeatedly training the same images say 10 times, so learn with the same data 10 times etc

What is better KNN or RBF ?

If it gets one wrong by classifing it incorrectly should I use category 0 to unlearn it, it say it gets image 16 wrong, the image is of a cat 7, when I ask the NN to classify the same image it comes back with a cat 8.

Should I get this image that it classifies wrong, and learn it into cat 0 ? Will this mean that it no longer will give me an incorrect answer, is there a general strategy for this situation ?

Thanks.

Marcus

0 Kudos
1 Reply
idata
Community Manager
36 Views

Hi Marcus,

 

 

Thank you for contacting us.

 

 

About your first question, well it is normal and yes I think you should keep training it to reduce the error.

 

 

Regarding your doubts with KKN or RBF and classifying, I recommend you to check this link: https://www.general-vision.com/documentation/TM_NeuroMem_API.pdf, you should found a lot of helpful information there.

 

 

Have a nice weekend.

 

 

Regards,

 

-Leonardo
Reply