# Search the Community

Showing results for tags 'artificial'.

• ### Search By Tags

Type tags separated by commas.

### Calendars

• Community Calendar

### Forums

• Welcome to Smart Mobile Studio
• News and Information
• Pre-Sales Questions
• Smart In the Media
• Smart Contests
• Meta
• Smart Mobile Studio Discussion
• General
• IDE
• RTL
• Code
• Client Server
• Platform
• Graphics
• Deployment
• Suggestion box
• Smart Mobile Studio support
• Support
• Bug report
• General Discussion
• Pascal
• Delphi
• Javascript
• HTML/HTML5
• CSS
• Resources
• Website

• 0 Replies

• 0 Reviews

• 0 Views

Found 5 results

1. ## Artificial intelligence - genetics

In the past I've written some posts on neural networks and how to implement them from first principles in smart pascal : - MNIST handwritten character recognition by neural network http://forums.smartmobilestudio.com/index.php?/topic/4230-recreating-early-ai-experiments- character-recognition/?hl=neural#entry17968 - Whats happening inside a neural network during training : visualisation through voronoi cells http://www.lynkfs.com/Experiments/Voronoi/ (use train-button, not the test-button) - A pre-trained neural network playing Pong http://www.lynkfs.com/Experiments/Pong/ (us
2. ## Neural network from first principles - 3

So setting up a neural network like this, in the end it all works out quite well. Training the network on the non-trivial question 'is it a bird, is it a plane ?' and training it on the following 2 examples : beak = 0, engine =1 : plane beak = 1, engine = 0 : bird just takes a second or so and fewer than 10000 iterations to reduce the error to less than 0.000x Increasing the nr of neurons in the hidden layers decreases the nr of iterations Interestingly once in a while the network is unable to converge and comes up with 0.5 as the answer, equivalent to 'I don't know' on a
3. ## Neural network from first principles - 2

The previous post laid out the the structure of a basic neural network. The example used was a 4 layer network with 12 neurons Setting it up like that there is enough information to dynamically generate a scaled version on a paintbox : Clicking on any node on this canvas gives a messagebox with the salient details of that particular neuron. (Clicked neuron 4). procedure TNeuralNetwork.InitializeObject; begin inherited; ... PaintBox1 := TW3PaintBox.Create(self); self.Handle.ReadyExecute( procedure () begin if (csReady in ComponentState) then begin b
4. ## Neural Network from first principles

These are exciting times. Hardly any day goes by without an announcement of another victory in artificial intelligence, deep learning or machine learning. As machine learning becomes more mainsteam, chances are that at some point in time it will become important to be able to incorporate this type of problem solving in projects, so I did some read-up on the subject. There is no lack of available tools. Google has opensourced TensorFlow, Facebooks's FAIR team has added amazing pre-trained networks on github, Microsoft has its Cortana Intelligence Suite on Azure and Amazon offers machi
5. ## Including a neural network

If you want to include a neural network into your app, you can use the unit below which basically is a wrapper around the brain.js library The unit exposes 'AddExample', 'Train' and 'Run' as the main procs, which speak for themselves. As an example the following neural network is defined with 3 inputs (r, g, b and 3 possible outputs (orange, green and purple). To train the network 4 examples are provided which should be enough to get reasonable results. Running the network on inputs r,g,b = 1,1,0 gives as outcome 'orange' as the best result (approx 80% certainty) procedure TForm1.
×