{"id":1764,"date":"2016-07-26T12:17:16","date_gmt":"2016-07-26T12:17:16","guid":{"rendered":"http:\/\/sites.uac.pt\/amendes\/?p=1764"},"modified":"2016-07-26T12:17:16","modified_gmt":"2016-07-26T12:17:16","slug":"tinker-neural-network","status":"publish","type":"post","link":"https:\/\/sites.uac.pt\/amendes\/visualizacao\/tinker-neural-network\/","title":{"rendered":"Tinker With a Neural Network"},"content":{"rendered":"
\"clique<\/a>

clique na imagem para seguir o link<\/p><\/div>\n

Uma excelente aplica\u00e7\u00e3o web para perceber como as redes neuronais funcionam<\/span><\/p>\n

\n

Um, What Is a Neural Network?<\/h2>\n

It\u2019s a technique for building a computer program that learns from data. It is based very loosely on how we think the human brain works. First, a collection of software \u201cneurons\u201d are created and connected together, allowing them to send messages to each other. Next, the network is asked to solve a problem, which it attempts to do over and over, each time strengthening the connections that lead to success and diminishing those that lead to failure. For a more detailed introduction to neural networks, Michael Nielsen\u2019s Neural Networks and Deep Learning<\/a> is a good place to start. For a more technical overview, try Deep Learning<\/a> by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.<\/div>\n

\n

This Is Cool, Can I Repurpose It?<\/h2>\n

Please do! We\u2019ve open sourced it on GitHub<\/a> with the hope that it can make neural networks a little more accessible and easier to learn. You\u2019re free to use it in any way that follows our Apache License<\/a>. And if you have any suggestions for additions or changes, please let us know<\/a>.<\/p>\n

We\u2019ve also provided some controls below to enable you tailor the playground to a specific topic or lesson. Just choose which features you\u2019d like to be visible below then save this link<\/a>, or refresh<\/a> the page.<\/p>\n

\n

What Do All the Colors Mean?<\/h2>\n

Orange and blue are used throughout the visualization in slightly different ways, but in general orange shows negative values while blue shows positive values.<\/p>\n

The data points (represented by small circles) are initially colored orange or blue, which correspond to positive one and negative one.<\/p>\n

In the hidden layers, the lines are colored by the weights of the connections between neurons. Blue shows a positive weight, which means the network is using that output of the neuron as given. An orange line shows that the network is assiging a negative weight.<\/p>\n

In the output layer, the dots are colored orange or blue depending on their original values. The background color shows what the network is predicting for a particular area. The intensity of the color shows how confident that prediction is.<\/p><\/div>\n

\n

What Library Are You Using?<\/h2>\n

We wrote a tiny neural network library<\/a> that meets the demands of this educational visualization. For real-world applications, consider the TensorFlow<\/a> library.<\/div>\n

\n

Credits<\/h2>\n

This was created by Daniel Smilkov and Shan Carter. This is a continuation of many people\u2019s previous work \u2014 most notably Andrej Karpathy\u2019s convnet.js demo<\/a> and Chris Olah\u2019s articles<\/a> about neural networks. Many thanks also to D. Sculley for help with the original idea and to Fernanda Vi\u00e9gas and Martin Wattenberg and the rest of the Big Picture<\/a> and Google Brain<\/a> teams for feedback and guidance.<\/div>\n","protected":false},"excerpt":{"rendered":"

Uma excelente aplica\u00e7\u00e3o web para perceber como as redes neuronais funcionam Um, What Is a Neural Network? It\u2019s a technique for building a computer program that learns from data. It is based very loosely on how we think the human brain works. First, a collection of software \u201cneurons\u201d are created and connected together, allowing them […]<\/p>\n","protected":false},"author":159,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[103,137,80],"tags":[191,198],"class_list":["post-1764","post","type-post","status-publish","format-standard","hentry","category-data-mining","category-software","category-visualizacao","tag-machine-learning","tag-web-apps"],"_links":{"self":[{"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/posts\/1764","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/users\/159"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/comments?post=1764"}],"version-history":[{"count":2,"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/posts\/1764\/revisions"}],"predecessor-version":[{"id":1767,"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/posts\/1764\/revisions\/1767"}],"wp:attachment":[{"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/media?parent=1764"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/categories?post=1764"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sites.uac.pt\/amendes\/wp-json\/wp\/v2\/tags?post=1764"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}