Keene Macheene

I intend to use the Chinese character(s) for 'think' as a kind of logo for the Cognate system. I am a native English speaker from the United States and see from google translate the following. 1. 认为 think ,  believe ,  consider ,  feel ,  deem ,  hold 2. 思考 think ,  ponder ,  reflect ,  reflect on 3. 想 want ,  think ,  wish ,  suppose ,  believe ,  miss 4. 想到 think ,  expect ,  imagine ,  conceive ,  remember ,  recall 5. 思 think ,  consider ,  deliberate 6. 想起 think ,  remember ,  recall ,  remind ,  recollect ,  evoke 7. 以为 think ,  believe ,  consider 8. 想象 think ,  visualize ,  picture ,  fancy ,  believe ,  envisage 9. 看 see ,  look ,  watch ,  view ,  read ,  think I am not sure which ha...

One feature of an SRS (see previous post) is that the 3D regular array of neurons (the cortex) can recognize a fragmented pattern in the subsumptive system, stimulate the subsumptive system into that pattern to a small degree, and then on the next time tick, recognize the now stronger pattern and repeat the process.  The entire system will rapidly avalanche into the state where the pattern is fully matched and the subsumptive system is fully in the match state. This system will then be locked into that state. Several factors can get the system out of the state and allow 'thinking' to continue. The pattern matcher will recognize the locked in state and begin predicting the next state. If one simulates the neurons getting 'tired' or 'bored' they can stop matching the locked in state and more easily match to the next state.  I call this Neural Fatigue.  An analog in biological neurons is the refractory period (maybe). Some external stimulus to the system li...

Subsumptive Regular System (RSR): A subsumptive spiking neural network with inputs, hard-wired processing, and outputs; combined with a regular (uniform)   3D array of learning and pattern recognizing neurons that is trying to predict the next state of the subsumptive, all asynchronously free running. The subsumptive system is the cerebrum, and the regular system is the cortex.

Got the ConceptMap editor working such that one can create Concept Maps, drag connections and make connections.  Also have the ImageInputDrive (a sub-class of Concept Map) pretty much working. Got stuck for a bit in some WinForm layout issues and scrolling the editing area.

In computer programming Object Oriented Programming (OOP) gave programmers a neat way to compartmentalize programs, rather than having a mess of disorganized code and data.  One can neatly make an object, treat it as a black-box and reduce the cognitive load on the programmer.  Nifty. In reactive neural networks where one is taking world inputs and generating response outputs Subsumption vastly simplifies the work of designing the neural processing. From dictionary.com: verb (used with object),   sub·sumed,   sub·sum·ing. to  consider  or  include  (an  idea,   term,   proposition,   etc.)  as  part  of a  more   comprehensive   one. to  bring  (a  case,   instance,   etc.)   under  a  rule. to  take  up  into  a  more   inclusive   classification. Subsumption in the context of neural networks is where some ...

Current neural network systems have a general paradigm of being given some input, and then producing a resulting output. A true general AI should act like a biological system and be self-sequencing. The neural system should just free-run, responding to inputs and creating outputs and learning. One method I am experimenting with in Cognate and NuTank is having a hard-wired set of concept maps (a N-dimensional set of neurons used to embody a concept, e.g. foveolar edge angles.) that take inputs from the external world and produce hard-wired reactions as outputs to control a real or simulated robot. Such a system also uses subsumption to aid in much easier design. This is the Concept Map System (CMS) for the purposes of this post. For now lets ignore the idea that the hard-wired concept map system might also be adapting and evolving over time simulating neroplasticity. One then has a large 3D array of neurons that are in acting as a pattern matcher on the entire CMS.  What this ...

Neural systems in the style of Convolutional Neural Networks et. al. use matrix math and tensors to simulate the overall activity level of neurons. The reason for "overall activity level" rather than individual pulses from neurons is that the overall activity is simply the integration over time of what would be pulses in real neurons. Overall activity also is amenable to calculus with derivatives for back propagation. The reason for matrix math is locality of memory reference and simplicity of written equations for what the system is doing. Microprocessors have local CPU memory cache, and main memory. Getting data from main memory to local cache is very slow relative to processor instruction times. Matrix math tends to make operations happen in address sequential order so is efficient in cache.  Also GPU design favors sequential and matrix operation and is ultra-fast. All the above makes tensor style processing for AI efficient. Pulsed neurons are more object oriented, s...

Working on the editor.  Writing in C# so using WinForm style UI code. Got Concept Map all draggable as a UI element.  In the middle of Connections in the UI.

So, I got past the hurdle in the ConceptMap and ConnectionDef code where one N-Dimensional map can be connected to another N-Dimensional map. The connection can have source and destination ranges of map points on any and all dimensions, with weights interpolated forward or backward on all dimensions.  This ends up being a nasty confusion of interpolation, except if you make single dimensional iterators. Then you nest the iterators and it works. Next is getting a first cut UI working in Win Forms C# to edit maps and connections, and visually show activation levels and firing 'sparkle'.