How is the convolution operation carried out when multiple channels are present at the input layer? (e.g. RGB) In such a case you have one 2D kernel per input channel (a.k.a plane). So you perform each convolution (2D Input, 2D kernel) separately and you sum the contributions which gives the final output feature map. Please … Read more
As Russel and Norvig point out in Artificial Intelligence: A Modern Approach (the most commonly used AI textbook) it is challenging to come up with a heuristic that is admissible but not consistent. Obviously, you can select values for nodes in a graph such that the heuristic they represent is admissible but not consistent. This … Read more
Rather than re-inventing the wheel, I’d suggest you to use some readily available solution. There are several expert systems out there and I’ll focus on those which are either in Python or can be used via Python. CLIPS CLIPS is an expert system originally developed by NASA. It’s considered state of the art and used … Read more
In terms of the Siri work, the direct predecessor ( http://www.sri.com/about/siri-timeline.html), the Personalized Assistant that Learns (PAL) Program, did produce an “agent-based language/framework” SPARK (not to be confused with SPARK Ada). They have publicly available documentation on it http://www.ai.sri.com/~spark/, https://pal.sri.com/CALOfiles/cstore/PAL-publications/calo/2005/IntrotoSPARK.pdf, and http://www.ai.sri.com/pubs/files/1023.pdf (and an Eclipse plugin, apparently). This is very different from a general-purpose programming … Read more
I am a co-author of the PatchMatch paper previously mentioned here, and I led the development of the original Content-Aware Fill feature in Photoshop, along with Ivan Cavero Belaunde and Eli Shechtman in the Creative Technologies Lab, and Jeff Chien on the Photoshop team. Photoshop’s Content-Aware Fill uses a highly optimized, multithreaded variation of the … Read more
For a virtual earth application I’ve used the clustering described here. It’s lightning fast and easily extensible.
Opencv (image processing and computer vision library written in c) has implementation for hough transform (the simple hough transform find lines in an image, while the generalized one finds more complex objects) so that could be a good start. For the rectangles which do have closed corners there are also corner detectors such as cornerHarris … Read more
You probably want to look into Markov Chains as the basics for the bot AI. I wrote something a long time ago (the code to which I’m not proud of at all, and needs some mods to run on Python > 1.5) that may be a useful starting place for you: http://sourceforge.net/projects/benzo/ EDIT: Here’s a … Read more