What's going on lately?
The second SIGI conference was postponed - not enough commitment from the circle.
But I am working on making the conference more interesting when it happens:
I've been into a Mathematical research mode lately, I started it as "Incremental Arithmetic" in an unpublished paper (shared with one person only) in 2011, some insights from 2010-2011 were around that theme. More explicitly on this - when I have beautiful results and demos. :)
Other AGI research/observation/preparations and Neuroscience-my-theory-of-intelligence-matching - it's in parallel with the above.
Drawing, sequential art, visual art/processing, image processing/visual effects/filmmaking software
I've always been a "visual" person (besides all other "persons" living in me), drawing runs in the blood of my family. Drawing/painting - rendering - is useful for focusing on the details of rendering and vision, and it goes from the smallest scale of a pixel to the largest scale of scenes, viewer's position, scene composition, lightning, characters, the world where the illustrated action happens, the story of it, etc. etc... The whole spectrum of generalizing sensorimotor hierarchies. It's cool.
I'm refreshing and upgrading my skills into a more systematic way and I'm aiming to polish my talent. One of the useful reasons is in order to render my graphical/movie stories better... :) The VFX/filmmaking software's one of the many purposes is to improve and speed up the process.
Vector transformations
In another "unpublished paper" from a few months ago, which would turn into a digest one day eventually (it's a "published email discussion), I explained and shared some elegant fundamental AGI operations/generalizations which are based on simple visual 3D transformations.
"Everything" is a bunch of vector transformations and the core of the general intelligence are the simplest representations of those "visual" representations, which are really simple/basic/general.
And "visual" in human terms actually means just:
Something that encompasses features and operations in 1D, 2D, 3D and 4D (video) vector (Euclidian) spaces, and the vectors in these dimensions can be of dimensionality usually of up to 4 or 5, such as: //e.g. (Luma, R,G,B)
1D - luminance
2D - luminance + uniform 1D color space
3D/4D - luminance + splitted/"component" color space
+ Perspective projection, which is a vector transform, it can be represented as a multiplication of matrices - that is - the initial sources of visual data are of higher dimensionality than the stored representation, 3D is projected into 2D (a drawback of the way of sensing)/
Also, of course, there is topology, humans work fine with blended and deformed images - curved spaces, and curves, not simple linear vectors. However the topology is induced from the basic vector spaces, the simplest topological representation is just the adjacency of coordinates in a matrix.
The above may seem obvious, but the goal is namely to make things as explicit as possible.
More on it - later.
The software and music - I don't have enough time for R&D, I'll probably tell more when there are results/pieces which I can show, such as tech demos or new demo records of my music... [Edit+ 2/10/2012:] But the music will probably wait untl I finally develop one software aid for the drums and start playing with it. :)
Read More
The second SIGI conference was postponed - not enough commitment from the circle.
But I am working on making the conference more interesting when it happens:
I've been into a Mathematical research mode lately, I started it as "Incremental Arithmetic" in an unpublished paper (shared with one person only) in 2011, some insights from 2010-2011 were around that theme. More explicitly on this - when I have beautiful results and demos. :)
Other AGI research/observation/preparations and Neuroscience-my-theory-of-intelligence-matching - it's in parallel with the above.
Drawing, sequential art, visual art/processing, image processing/visual effects/filmmaking software
I've always been a "visual" person (besides all other "persons" living in me), drawing runs in the blood of my family. Drawing/painting - rendering - is useful for focusing on the details of rendering and vision, and it goes from the smallest scale of a pixel to the largest scale of scenes, viewer's position, scene composition, lightning, characters, the world where the illustrated action happens, the story of it, etc. etc... The whole spectrum of generalizing sensorimotor hierarchies. It's cool.
I'm refreshing and upgrading my skills into a more systematic way and I'm aiming to polish my talent. One of the useful reasons is in order to render my graphical/movie stories better... :) The VFX/filmmaking software's one of the many purposes is to improve and speed up the process.
 |
| Thanks to http://www.youtube.com/user/thevirtualinstructor for one of his lessons and suggestions, practiced in these drawings. |
Vector transformations
In another "unpublished paper" from a few months ago, which would turn into a digest one day eventually (it's a "published email discussion), I explained and shared some elegant fundamental AGI operations/generalizations which are based on simple visual 3D transformations.
"Everything" is a bunch of vector transformations and the core of the general intelligence are the simplest representations of those "visual" representations, which are really simple/basic/general.
And "visual" in human terms actually means just:
Something that encompasses features and operations in 1D, 2D, 3D and 4D (video) vector (Euclidian) spaces, and the vectors in these dimensions can be of dimensionality usually of up to 4 or 5, such as: //e.g. (Luma, R,G,B)
1D - luminance
2D - luminance + uniform 1D color space
3D/4D - luminance + splitted/"component" color space
+ Perspective projection, which is a vector transform, it can be represented as a multiplication of matrices - that is - the initial sources of visual data are of higher dimensionality than the stored representation, 3D is projected into 2D (a drawback of the way of sensing)/
Also, of course, there is topology, humans work fine with blended and deformed images - curved spaces, and curves, not simple linear vectors. However the topology is induced from the basic vector spaces, the simplest topological representation is just the adjacency of coordinates in a matrix.
The above may seem obvious, but the goal is namely to make things as explicit as possible.
More on it - later.
The software and music - I don't have enough time for R&D, I'll probably tell more when there are results/pieces which I can show, such as tech demos or new demo records of my music... [Edit+ 2/10/2012:] But the music will probably wait untl I finally develop one software aid for the drums and start playing with it. :)
