Message:

<p>[QUOTE=&quot;Sulla80, post: 6593444, member: 99456&quot;]Well, well, well -</p><p>#1 Cucumbor&#039; Ptolemy II Philadelphos Obol</p><p>#2 Theodosius’ AR Tetradrachm, Syracuse Agathokles</p><p>#3 Bcuda’s sentimental pick of a Severus Alexander AE Sestertius</p><p>#4 Curtisimo’s EL 50 Litrae, Syracuse mint</p><p>#5 ....</p><p><br /></p><p>Having removed all of the 無駄 (uselessness) from the predictive bot&#039;s logic, and tweaked the NLP engine to better support Aramaic and related alphabets.&nbsp; The process now looks much simpler (thanks, [USER=51347]@Alegandron[/USER]!)</p><p>[ATTACH=full]1265597[/ATTACH]</p><p><br /></p><p>Here are the predictions - still powered by the past posts of the esteemed CT members. Unfortunately it is clear that I lost something in the rewrite as the most probable owners do not fit with my previous picks:</p><p>&nbsp;</p><p>The estimated probabilities of ownership for Coin #5 are:</p><ul> <li>66.2% probability [USER=77077]@Theodosius[/USER]<br /> </li> <li>22.4% probability [USER=83845]@Curtisimo[/USER]</li> <li>11.4% probability <b>[USER=81887]@Parthicus[/USER]</b></li> </ul><p>[USER=81887]@Parthicus[/USER] is my pick for Coin #5, because he is the last option I have left, and as you can see it is the <b>bolder</b> prediction.&nbsp; The remaining question - do I rerun all 5 coins with the final optimized version of the bot....I do have a coin of this type, so I will share it:</p><p>[ATTACH=full]1265600[/ATTACH]</p><p><b>Pontos, Amisos</b>, circa 90-85 BC, AE</p><p><b>Obv:</b> Aegis</p><p><b>Rev:</b> Nike advancing right, holding palm tied with fillet over left shoulder[/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