Message:

<p>[QUOTE=&quot;Publius2, post: 3914681, member: 105571&quot;]This is a fascinating thread and touches on a conversation I had with a collector at our local coin club.&nbsp; The OP&#039;s effort to build a neural net to learn how to grade from photos would probably suffer from most if not all the weaknesses previously alluded - you know - the GIGO problem.&nbsp; One of the goals of machine learning is to minimize to near elimination the GI part the equation.&nbsp; Everyone is familiar with the &quot;driverless car&quot; development.&nbsp; Do you think the driving environment is less complicated or with fewer unexpected situations than that of coin grading?&nbsp; The time and expense of training these systems to drive cars is massive.</p><p><br /></p><p>This, I think, is where the flaw lies in machine grading of coins from photographs.&nbsp; Many of the critical components of grading are hidden by the actual photographic techniques employed, as described by previous posters.&nbsp; And it would not really be practical to take enough photographs to display all the different aspects of a coin under a wide enough spectrum of lighting regimes.&nbsp; But, I think I have at least a potential answer to this problem:</p><p><br /></p><p>After the fundamentals of a coin grading neural net are built, at least to the point where it can perform the least subjective portions of grading, it would be time to introduce the machine system to an automated physical handling sub-system controlled by the AI and programmed to subject the coin to a specified variety of base and optional angle/rotation/lighting conditions.&nbsp; Properly designed and using conservative values of performance, I can see the entire cycle from loading the coin/slab to removing it being about 5 minutes.&nbsp; This system could probably fulfill a matrix of 25 X 25 or 625 different combinations of angle/rotation/lighting at 1/2 second per shot.&nbsp; It should be possible to train the system to evaluate coins in this manner at least fairly close to the results obtained from good human graders.&nbsp; The task, as with all machine learning environments, is the fairly massive number and type of examples that must be fed into it in order to teach the idiot savant what it&#039;s looking at.</p><p><br /></p><p>I agree that aside from the expense and time of such an effort, it is not in the financial best interest of the TPGs nor of many dealers/collectors to remove or reduce the uncertainty and variability of grading.&nbsp; And as a collector, some of the&nbsp; fun of the hobby would be diminished.&nbsp; As with cars, once the machines are driving, where&#039;s the fun?[/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