Jump to content

Search the Community

Showing results for tags 'ai'.

  • Search By Tags

    Type tags separated by commas.
  • Search By Author

Content Type


There are no results to display.


  • 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
    • Download Smart Mobile Studio

Find results in...

Find results that contain...

Date Created

  • Start


Last Updated

  • Start


Filter by number of...


  • Start



Website URL



Company name


Found 6 results

  1. lynkfs

    font choice

    Styling on the web is really messy, and takes a lot of effort to get it right. As a matter of personal interest, I'm collecting as many 'design rules' underpinning good styling as I can. Like : In the typography area, I came across this site. It uses machine learning to identify font-families which work well together. It uses Google fonts as its domain, and outputs a header, sub-header and text font (similar to h1, h2 and p) I really like its recommendations (usually using the 'similar' setting)
  2. lynkfs


    edited Been a while since I had a look at Googles Tensorflow deep learning library (js version) In the meantime this library has expanded quite a bit, most notably it enables using pre-built models for a variety of tasks. This one takes any image and detects up to 90 categories of objects in the image (persons, dogs, traffic lights etc) The library correctly identifies 2 objects of type "person" in the above image (image 620*408 pixels, bbox coordinates x,y,width,height) Usage is incredibly simple : load the libraries, display an image in the browser and issue a
  3. 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
  4. lynkfs

    Going Retro

    Looks like going retro is the way to go these days Sony just introduced the new=old walkman, selling for some $4K Arca Noae has developed a new full distro of IBM's OS/2 I've heard some people are even dabbling with AmigaOs ... This reminds me of the first book I ever bought on the subject of AI : "Build your own expert system" by Chris Naylor, printed 1983 A very entertaining publication, well written and featuring code in Apple Basic and Sinclair Spectrum (!) At some stage I converted that to Delphi and lately to SMS, just to see how the early AI compares to todays AI One of t
  5. This afternoon I came across API.ai, a service that allows developers to build natural language processing artificial intelligence system which can be trained up with custom functionality. I had thought about pursuing something like this and briefly looked at Watson/Bluemix, however this service (API.ai) seemed right in my alley. So I signed up (freemium model). As it turns out the service comes pre-loaded with a couple of general knowledge domains so if you don't add your own knowledge base at least there is something. Their API is pretty easy and below is the code for a simple
  6. 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.
  • Create New...