Message:

<p>[QUOTE=&quot;messydesk, post: 3914667, member: 1765&quot;]In a system where the current subjectivity is learned and made repeatable, you would still have to deal with two things that would perpetuate the need for grading.</p><p><br /></p><p><b>Defects.&nbsp; </b>A neural network can only learn to be as good as the ground truth allows. This ground truth is arrived at by a committee of graders, each of which is considered to be doing a good job if they&#039;re in agreement with the consensus more than 75% of the time.&nbsp; If the resulting neural network learns how to do a good job, or even a very good job (80%+), it will still be assigning grades that the market will reject.&nbsp; Classifying grades is not the same as the &quot;toy&quot; classification task of identifying hand-written numerals (Google search for MNIST for this example).&nbsp; There is a very fuzzy area of right and wrong with grades that is nearly non-existent with identifying numbers.&nbsp; A postal worker sorting mail with handwritten addresses is right over 99% of the time.&nbsp; If they only had a 75% success rate, then they&#039;d be out of a job (if not for the union, but I digress).&nbsp; The way &quot;wrong&quot; answers are dealt with in a neural network is by some combination of restructuring the network and retraining it with more, and better, data.&nbsp; While this may boost the performance to a slightly higher number, it will potentially produce different results for some coins, putting us right back to the appearance of shifting sands of grading standards.</p><p><br /></p><p><b>Technological shifts in data acquisition. </b> When I replaced my Nikon D80 with a Nikon D610, I was able to take slightly better pictures of my coins due to changes in detector technology.&nbsp; Upgrading lights and lenses can have a similar effect, and this is only for static 2D images.&nbsp; For the imagery required for grading, which is at least 3-dimensional, there are many opportunities to devise a way to improve how an attribute is captured, whether it&#039;s simple detail, surface qualities, color, luster depth, or detecting problems.&nbsp; This could lead to a difference in what the network sees, thus giving a different result, which would lead to retraining and/or restructuring, which would again lead to resubmissions.[/QUOTE]</p><p><br /></p>

Your name or email address:

Do you already have an account?

• No, create an account now.
• Yes, my password is:
• Forgot your password?

Stay logged in