{"id":3442,"date":"2024-09-01T16:29:38","date_gmt":"2024-09-01T16:29:38","guid":{"rendered":"https:\/\/workhouse.sweetdishy.com\/?p=3442"},"modified":"2024-09-01T16:29:39","modified_gmt":"2024-09-01T16:29:39","slug":"artificial-neural-networks-anns","status":"publish","type":"post","link":"https:\/\/workhouse.sweetdishy.com\/index.php\/2024\/09\/01\/artificial-neural-networks-anns\/","title":{"rendered":"Artificial Neural Networks\u00a0(ANNs)"},"content":{"rendered":"\n

At the most basic level, an artificial neural network (ANN) is a function that includes units (which may also be called neurons, perceptrons, or nodes). Each unit will have a value and a weight, which indicates the relative importance, and will go into the hidden layer. The hidden layer uses a function, with the result becoming the output. There is also another value, called bias, which is a constant and is used in the calculation of the function.<\/p>\n\n\n\n

This type of training of a model is called a feed-forward neural network. In other words, it only goes from input to the hidden layer to the output. It does not cycle back. But it could go to a new neural network, with the output becoming the input.<\/p>\n\n\n\n

Figure\u00a04-1\u00a0shows a chart of a feed-forward neural\u00a0network.<\/p>\n\n\n\n

\"..\/images\/480660_1_En_4_Chapter\/480660_1_En_4_Fig1_HTML.jpg\"\/
Figure 4-1.<\/em><\/strong>A basic feed-forward neural network<\/figcaption><\/figure>\n\n\n\n

Let\u2019s go deeper on this by taking an example. Suppose you are creating a model to predict whether a company\u2019s stock will increase. The following are what the variables represent as well as the values and weights assigned:<\/p>\n\n\n\n

    \n
  • X1<\/sub>: Revenues are growing at a minimum of 20% a year. The value is 2.<\/li>\n\n\n\n
  • X2<\/sub>: The profit margin is at least 20%. The value is 4.<\/li>\n\n\n\n
  • W1<\/sub>: 1.9.<\/li>\n\n\n\n
  • W2<\/sub>: 9.6.<\/li>\n\n\n\n
  • b: This is the bias (the value is 1), which helps smooth out the calculations.<\/li>\n<\/ul>\n\n\n\n

    You\u2019ll then sum the weights, and then the function will process the information. This will often involve an activation function, which is non-linear. This is more reflective of the real world since data is usually not in a straight line.<\/p>\n\n\n\n

    Now there are a variety of activation functions to choose from. One of the most common is the sigmoid. This compresses the input value into a range of 0\u20131. The closer it is to 1, the more accurate the model.<\/p>\n\n\n\n

    When you\u00a0graph\u00a0this function, it will look like an S shape. See Figure\u00a04-2.<\/p>\n\n\n\n

    \"..\/images\/480660_1_En_4_Chapter\/480660_1_En_4_Fig2_HTML.jpg\"\/
    Figure 4-2.<\/em><\/strong>A typical sigmoid activation function<\/figcaption><\/figure>\n\n\n\n

    As you can see, the system is relatively simplistic and will not be helpful in high-end AI models. To add much more power, there usually needs to be multiple hidden layers. This results in a multilayered perceptron (MLP). It also helps to use something called backpropagation, which allows for the output to be circled back into the neural network .<\/p>\n","protected":false},"excerpt":{"rendered":"

    At the most basic level, an artificial neural network (ANN) is a function that includes units (which may also be called neurons, perceptrons, or nodes). Each unit will have a value and a weight, which indicates the relative importance, and will go into the hidden layer. The hidden layer uses a function, with the result […]<\/p>\n","protected":false},"author":1,"featured_media":3327,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[442],"tags":[],"class_list":["post-3442","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-deep-learning"],"jetpack_featured_media_url":"https:\/\/workhouse.sweetdishy.com\/wp-content\/uploads\/2024\/08\/deep-learning-1.png","_links":{"self":[{"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/posts\/3442","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/comments?post=3442"}],"version-history":[{"count":1,"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/posts\/3442\/revisions"}],"predecessor-version":[{"id":3443,"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/posts\/3442\/revisions\/3443"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/media\/3327"}],"wp:attachment":[{"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/media?parent=3442"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/categories?post=3442"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/workhouse.sweetdishy.com\/index.php\/wp-json\/wp\/v2\/tags?post=3442"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}