http://kailashnadh.name/blog/research.php en http://backend.userland.com/rss092 Sun, 22 Feb 2009 15:06:24 +0000 kailash@bnsoft.net kailash@bnsoft.net

Four rooms

Four coloured doors

Capable of remembering sequences

In the exploration mode, the bot starts off in a room (can be any room) and keeps going from room to room, until it reaches the starting point. Whenever it is in a room that it hasn't been in before, the room is learned (on the fly, creating a cell assembly for that room). When the bot passes through a door and enters the next room, it learns the door, the next room and runs an association routine where by the previous room, the door and the current room are associated in a sequence. So for all the rooms:

• room1-door1-room2
• room2-door2-room3
• room3-door3-room4
• room4-door4-room1

In the test mode, an external activation is applied on the target room (where you want the bot to go to). From the chain of sequences it has learned, the bot picks up the color of the door of the target room and goes to it!]]> http://kailashnadh.name/blog/post/research/216/Cognitive--spatial-mapping-prototype-2 Sun, 22 Feb 2009 15:05:58 +0000 General http://kailashnadh.name/blog/post/research/216/Cognitive--spatial-mapping-prototype-2#cmt assumptions were made (such as assuming a perfect vision system was available etc.) in getting the demo working, but the underlying idea of associating landmarks and features to learn and in turn, use that to navigate, worked well (in an oversimplified way, of course).



The CONTROL module is complete symbolic where as all other areas are neural nets composed of (fLIF neurons.

The vision system can be considerd as an example for the height of over simplification. There is the RETINA that is hardwired to recognize doors,walls and rooms, directly interfacing witht the symbolic CONTROL with no Visual Cortex whatsoever.

The RETINA has connections to a COLOURS network which enables it to identify three colours (red,green,blue), which in the simulation, are the colours of doors.

The KNOWN OBJECTS network has three pre-known concepts (door, wall, room) which gets excitation directly from the RETINA, when ever it sees one of those objects.

The NEW INSTANCES network is blank to begin with and that is where rooms and door-colour associations are stored as the bot explores the world and spots new rooms.

1. There are only two rooms in the simulation, separated by a red door
2. The bot starts in room1 in exploration mode
3. It keeps moving forward until it comes across a door
4. When it passes through a door, it knows that (symbolic) it just came from a room, passed an X coloured door and is right now in a different room
5. Then it learns this as a new instance and stores it in the instance ne ..]]> http://kailashnadh.name/blog/post/research/215/Cognitive--spatial-mapping-prototype-1 Thu, 27 Nov 2008 17:01:16 +0000 General http://kailashnadh.name/blog/post/research/215/Cognitive--spatial-mapping-prototype-1#cmt
   Right now, I am working on building a simulation of a virtual agent in a 3D environment capable of doing basic cognitive mapping. The aim is to get the agent to learn paths and navigate between rooms.
   
   Building the 3D world
   I looked around a lot to find a simple 3D engine which would fit my purpose of building a 3D environment comprising of a few rooms and doors.
   
   I tried JPCT (java) which looked promising but completely lacked support resources and a good documentation. Crystal Space (C++), I found to be too big and complex for my purpose. Same with JMonkeyEngine(java). At last, I came across Irrlicht (C++) an amazingly compact and immensely powerful 3D engine that has a huge community, plenty of support resources, good documentation and even a java binding called Jirr. I have nothing but words of praise for Irrlicht.
   
   After fiddling around a bit with it and modeling my rooms in Anim8or, I finally got the 3D world working, which looks like this:
   
   
   I am working on the neural side of things, where the the agent has:
   • A simple vision system
   ..]]> http://kailashnadh.name/blog/post/research/214/Cognitive--spatial-mapping Mon, 17 Nov 2008 16:03:06 +0000 General http://kailashnadh.name/blog/post/research/214/Cognitive--spatial-mapping#cmt type of relationship between two concepts in memory) in simulated memories is a problem. It is somewhat easy to encode two concepts in CAs and associate them. But what kind of association? How to define the type? Shouldn't a definition somehow be formed implicitly?
   
   For instance, imagine a wooden table and a chair in a room. We perceive many kinds of association when looking at them.
   
   • They are both pieces of furniture.
   • They are both made out of wood.
   • They are placed near to each other.
   • They are both in the same room.
     and so on..
   Inspired by the famous Pavlov’s dog experiment, I devised an experiment (called the Psuedo-Pavlov experiment) to simulate, dare I say, classical conditioning / association.
   
   A neural network was trained with the patterns food, hungry, not hungry, salivate, lie down.
   
   During the learning phase, hunger was repeatedly presented with food and salivate, invoked (Ofcourse, we don't have to force a dog to salivate when its hungry and sees food, in real life).
   
   Again, not hungry was repeatedly presented with food and lie down invoked (assuming that a dog food lie down inspite of the presence of food, when it's not hungry).
   
   In the testing phase, when food was presented in the context hungry, the resultant activation was salivate (obviously) and when th ..]]> http://kailashnadh.name/blog/post/research/213/Context-sensitive-association Sat, 01 Nov 2008 19:47:11 +0000 General http://kailashnadh.name/blog/post/research/213/Context-sensitive-association#cmt
   The Sharks and Jets experiment [McClelland, 1981] was designed to demonstrate how a network could function as a content-addressable memory system. The information to be encoded was two groups (Sharks and Jets), group members
   and some demographic attributes of theirs. The goal of the experiment was to store, associate and retrieve patterns in a network.
   
   My CA implementation of the model learned, grouped and associated members of a group. Associations between different patterns were defined as overlapping neurons in the CA network. The associations were learnt through a series of cycles. The model was tested by presenting a randomly chosen pattern of all the ones learnt. For instance, when a member of a group was presented, activation was observed in that member and the areas of his demographic characteristics. When a parent group was presented, activation was observed in a large scale where many members of that group and their attributes ignited and in many cases, a particular member had the most activation, assumed to be the prototypical representation of that group.
   
   While the network in the original experiment was specialised to the goal, the CA implementation was conducted based on the general behaviour of CAs (having distance biased neuron connections). Even though the highly interesting dynamics observed in the original experiment were not recreated in the implementation, the goal of observing associative behaviour in CAs was attained with fair success.
   
   [McClelland, 1981] McClelland, J. L. (1981). Retrieving general and specific information from stored knowledge of specifics. In Proceedings of the Third Annual Conference of the Cognitive Science Society, pages 170–2.
   ]]> http://kailashnadh.name/blog/post/research/212/Sharks-and-Jets Mon, 06 Oct 2008 23:31:52 +0000 General http://kailashnadh.name/blog/post/research/212/Sharks-and-Jets#cmt http://kailashnadh.name/blog/post/research/211/CANT-model Thu, 02 Oct 2008 14:15:12 +0000 General http://kailashnadh.name/blog/post/research/211/CANT-model#cmt » download pdf]]> http://kailashnadh.name/blog/post/research/210/Undergraduate-theseis--PP-attachment-ambiguity-resolution Mon, 28 Apr 2008 19:09:09 +0000 General http://kailashnadh.name/blog/post/research/210/Undergraduate-theseis--PP-attachment-ambiguity-resolution#cmt