More than one output node not possible? - Grasshopper2024-03-29T07:58:46Zhttps://www.grasshopper3d.com/forum/topics/more-than-one-output-node-not-possible?groupUrl=owl&feed=yes&xn_auth=noThanks for the link, it is us…tag:www.grasshopper3d.com,2023-07-21:2985220:Comment:22988152023-07-21T13:32:14.290ZGabrielaSullivanhttps://www.grasshopper3d.com/profile/GabrielaSullivan
<p>Thanks for the link, it is useful for me. I am new here as well. Is anyone in this room a fan of playing the 3 Reel Slots Online? In such case, <a href="https://bestcasinoplay.ca/online-slots/3-reel-slots/" target="_blank" rel="noopener">click over here now</a> and visit this amazing site and find online real-money gaming sites that have reviews that will help you a lot in putting your trust in them.</p>
<p>Thanks for the link, it is useful for me. I am new here as well. Is anyone in this room a fan of playing the 3 Reel Slots Online? In such case, <a href="https://bestcasinoplay.ca/online-slots/3-reel-slots/" target="_blank" rel="noopener">click over here now</a> and visit this amazing site and find online real-money gaming sites that have reviews that will help you a lot in putting your trust in them.</p> For anyone who finds themselv…tag:www.grasshopper3d.com,2018-06-06:2985220:Comment:19133602018-06-06T08:59:00.349ZSam Gregsonhttps://www.grasshopper3d.com/profile/SamGregson
For anyone who finds themselves following my monologue I have managed to get this to work.<br />
<br />
The key problem was that neural networks are very sensitive to their hyper parameters (e.g. learning rate, alpha value for the Sigmoid function).<br />
<br />
I ended up reducing my training data set size (to speed up training) and then used an optimisation algorithm (e.g the Nelder-Mead plugin - shameless plug) to optimise these parameters. This method reasonably quickly gave me decent results (>90% accuracy on…
For anyone who finds themselves following my monologue I have managed to get this to work.<br />
<br />
The key problem was that neural networks are very sensitive to their hyper parameters (e.g. learning rate, alpha value for the Sigmoid function).<br />
<br />
I ended up reducing my training data set size (to speed up training) and then used an optimisation algorithm (e.g the Nelder-Mead plugin - shameless plug) to optimise these parameters. This method reasonably quickly gave me decent results (>90% accuracy on my validation set).<br />
<br />
I have since found a slightly different approach here: <a href="http://www.grasshopper3d.com/group/owl/forum/topics/examples-discussion" target="_blank">http://www.grasshopper3d.com/group/owl/forum/topics/examples-discussion</a> File size was a problem with…tag:www.grasshopper3d.com,2018-05-25:2985220:Comment:19115242018-05-25T14:12:13.689ZSam Gregsonhttps://www.grasshopper3d.com/profile/SamGregson
<p>File size was a problem with the large dataset internalised. Here's an image instead:…</p>
<p></p>
<p><a href="http://storage.ning.com/topology/rest/1.0/file/get/2769358355?profile=original" target="_self"></a><a href="http://storage.ning.com/topology/rest/1.0/file/get/2769358804?profile=original" target="_self"><img class="align-center" src="http://storage.ning.com/topology/rest/1.0/file/get/2769358804?profile=RESIZE_1024x1024" width="721"></img></a></p>
<p>File size was a problem with the large dataset internalised. Here's an image instead:</p>
<p></p>
<p><a href="http://storage.ning.com/topology/rest/1.0/file/get/2769358355?profile=original" target="_self"></a><a href="http://storage.ning.com/topology/rest/1.0/file/get/2769358804?profile=original" target="_self"><img width="721" src="http://storage.ning.com/topology/rest/1.0/file/get/2769358804?profile=RESIZE_1024x1024" width="721" class="align-center"/></a><a href="http://storage.ning.com/topology/rest/1.0/file/get/2769358355?profile=original" target="_self"></a></p> ...However I am still struggl…tag:www.grasshopper3d.com,2018-05-25:2985220:Comment:19115112018-05-25T12:01:12.597ZSam Gregsonhttps://www.grasshopper3d.com/profile/SamGregson
<p>...However I am still struggling to get reliable results. My set-up is based on the article here: <a href="http://neuralnetworksanddeeplearning.com/chap1.html" target="_blank">http://neuralnetworksanddeeplearning.com/chap1.html</a></p>
<p></p>
<p>I have attached my GH file for reference.</p>
<p></p>
<p>Thanks,</p>
<p>Sam</p>
<p>...However I am still struggling to get reliable results. My set-up is based on the article here: <a href="http://neuralnetworksanddeeplearning.com/chap1.html" target="_blank">http://neuralnetworksanddeeplearning.com/chap1.html</a></p>
<p></p>
<p>I have attached my GH file for reference.</p>
<p></p>
<p>Thanks,</p>
<p>Sam</p> Apologies, I've just answered…tag:www.grasshopper3d.com,2018-05-25:2985220:Comment:19110062018-05-25T09:08:25.356ZSam Gregsonhttps://www.grasshopper3d.com/profile/SamGregson
<p>Apologies, I've just answered my own question... it is possible, I just hadn't matched the no. of outputs correctly.</p>
<p></p>
<p>Thanks,</p>
<p>Sam</p>
<p>Apologies, I've just answered my own question... it is possible, I just hadn't matched the no. of outputs correctly.</p>
<p></p>
<p>Thanks,</p>
<p>Sam</p>