Posted: January 28, 2012 at 11:12 am

Seems to me “three dimensions” is simply a mathematical notion, defined as three directions which are separated by 90 degree angles. The 90 degrees mean that these dimensions are independent and that one can vary without effecting the others. This strikes me as a cultural construction, not an insight into reality. Why? Because there are many parallel “directions” in which the properties of objects can vary without effecting the others. What about colour or orientation for example?

I suppose the physicist would say that orientation is reduced to 3 dimensional movement if the object is considered a group of related objects moving through space, and the same for colour as the bouncing of light rays off of objects. So the solution seems to be to break objects into smaller and smaller units (sound familiar?) where these smaller and smaller units have nothing but positions in space and time. Regarding 9 dimensional space, it seems obvious that 9 is the number of dimensions required to satisfy the mathematical models to explain the phenomena in question. So how many dimensions are there really? Well, it depends on the level of abstraction in the model/description.

Posted: January 28, 2012 at 11:09 am

My reply to Marius’s response:

A. I hope my discussion of a continuum between conceptual and formal was not missed. I do think there is a continuity of practise, and that it’s perhaps more a question of emphasis on form or content than anything. Most work would fall somewhere between the extreme poles. (more…)

Posted: January 28, 2012 at 11:08 am

At ISEA 2011 one of the fathers of generative art (or algorithmic art, or system art) Roman Verostko delivered a keynote. I have not strictly considered my work in relation to generative art until recently. (more…)

Posted: January 28, 2012 at 11:03 am

I’ve been quite interested in notions of free will. Rather, I’m more interested in the degree to which choices are made as a result of external factors or internal factors, the latter of which are reducible to external factors in a deterministic, and materialist, world.

There seem to be only two options:
1. All actions result from external forces. The moment of the big bang determined every “choice” we will ever make.

2. Actions are the result of “random” and unpredictable interactions.

#2 does not make sense in a deterministic world anyhow, since it too would simply be the result of initial conditions.

Seems the only escape is to reject determinism, that gives us randomness, but what about free will? Maybe we must reject materialism also. There is also this old paper I wrote musing about signal, noise and consciousness: http://www.ekran.org/ben/wp/2007/untitled-iterations-vagueterrain-2006/

Posted: January 28, 2012 at 11:02 am

There is much discussion on the creative power of making your own tools, but what are tools made from, but other tools? What does this mean for the apparent increase of freedom in with the increase of depth of knowledge? For example the lower level the language, the more busy work the program needs to do, like managing memory. If you go right down to machine code the whole program appears to do little but manage memory, occluding the high level concept of what this program means and does. What is the appropriate level of abstraction (depth) of description for a particular project? Are some concepts ideally represented in machine code? Are other concepts clearest in OOP, or data-flow languages?

Posted: January 28, 2012 at 10:59 am

I was just thinking about a conversation I had with Matthew Forsythe during Interactive Screen 1.0, in Banff. I had been thinking a while about the cost of the things we use, I don’t just mean material costs, but also ecological and geological cost. The problem of calculating the cost of a particular product is quite difficult because of the arbitrary horizon (scope) of the calculation.

For example, lets take a pencil, the obvious costs include the wood and graphite, the cost of producing those components could be included. What is the cost of mining the graphite? What about the logging of the wood? What about the people paid to mine and log? What about the equipment needed? Not only that, what about the cost of all the machines used in those processes? What about the machines used to make those machines? We could go even further, what is the cost (in time) of the growth of that wood? What is the geological cost of the production of graphite?

Calculating the “true” cost of anything becomes a problem akin to measuring the length of a coastline. The closer you move the horizon of measurement to “reality” the longer the coastline, and the greater the cost. Perhaps the cost of everything (in infinite quantity) is infinite. The whole history of the universe is required for anything/everything to exist. That is expensive.

Posted: January 9, 2012 at 3:47 pm

Above is a reconstruction of approximately 20 frames of video test footage. (more…)

Posted: December 9, 2011 at 5:21 pm

I wanted to post my progress on segmentation before I start working on clustering and video sequences. Here are images that show the current state of segmentation (down to under 2s per frame) of a more realistic Vancouver scene captured on video: (reconstruction, mean-shift filtering, original image)

(more…)

Posted: November 26, 2011 at 3:40 pm

In playing with code for deep learning (DBNs in particular) I’ve had to install CUDA to do matrix processing on the GPU. So I went ahead and recompiled openCV to use CUDA. Following is a similar segmentation image to the one in previous posts. This one was computed in 2.7s on the GPU, and on a different machine. The non GPU version did it in 6s, and the old machine did it in 9s. This machine is already a few years old, and has an older 8600GTS that barely supports CUDA. A faster machine, or perhaps just a faster GPU, may get these numbers down to something more real-time.

Posted: November 11, 2011 at 12:32 pm

I’m continuing to listen to some of Franklin’s lectures about LIDA and cognitive modelling in general. Yesterday I got through the one explaining Global Workspace Theory (GWT). Little did I know, but I had already come across this theory during my Masters research, and discounted it due to its causal disconnection between consciousness and cognitive processes. While I continue to find this problematic as a model of sentient creatures, the notion of “functional consciousness” is certainly interesting and useful in the case of machines and AI.

(more…)

Posted: November 5, 2011 at 11:19 am

(more…)

Posted: November 4, 2011 at 5:02 pm

In attempting to think through a possible integration of LIDA and the current conception of the dreaming system, I’ve stumbled upon the above question. In the previous sketch, the content of memory (the current state of the “conceptual system”) is used to generate visual sensory data that is the dream content. In LIDA, it becomes somewhat unclear from which module(s) the content of the dream would arise. Clearly, it would involve longer term memory structures, such as those in episodic memory, which are only explicitly manifest in the workspace and then “broadcast” into the global workspace. So where does the dream occur? In the workspace or in the global workspace? Since the agent is only conscious of what is in the global workspace, then that appears to be the logical location. (more…)

Posted: November 1, 2011 at 4:39 pm

In this post I will describe the conceptual subsystem, as I have imagined it up to this point, before looking more closely into the LIDA architecture. The central feature of this conception is that each high level feature, for example location in space, or colour (or redness), is considered independent. This contrasts with many systems that concatenate all these features in order to create a cluster representation that encapsulates overall similarity. This is conceptualized as a highly shallow system where features are meant to be high level. In fact no clustering is needed at all, as only a distance function can be used to determine the distance between precepts in terms of each individual feature. (more…)

Posted: October 31, 2011 at 4:55 pm

This is an excerpt from my email I wrote regarding next steps:

1. Make a diagram of the conception of the system as it was before, including how I was thinking of links between high level neurons having different weights for each high level feature (which may be made up of a vector of lower level features, eg. histogram). This would be the context in which to situate discussions of machine learning systems.

2. Read more about LIDA to understand better how percepts and knowledge from memory stores are structured, and if a subset of the architecture can be used.

3. Wish list for machine learning / clustering (in no particular order)

• Unsupervised

• Ideally statistical (stores a distribution of patterns, not all the patterns themselves, but this is flexible)

• Output could be manifest in connection weights between neuron-like structures that represent higher level concepts. (concept as distribution of activation) Each item should belong to a concept to a degree, not Boolean.

• If it is deep learning and I can forgo the feature extraction, it must be elegant (simple enough for me to understand) and be feasible for high resolution colour input images.

• If it is deep learning it should be generative: can learn high level abstractions (concepts) from sensory data, and also construct sensory data from those high level abstractions.

Thank is all I can think of off hand. (more…)

Posted: October 28, 2011 at 12:42 pm

On one hand we have the deep machine learning systems discussed in the previous post, which are quite complex (from a mathematical perspective) and only roughly informed by neuro and cognitive sciences. On the other hand are cognitive architectures that are inspired by biological knowledge (BICAs). These are systems that attempt to balance high level (psychological knowledge) with low level (neurological knowledge) in a tractable system that models mind-brains. These systems can be purely symbolic, connectionist (sub-symbolic) or hybrids of the two. While they are biologically inspired they favour a high level abstraction of cognition over fine details of brain (neuron) function. (more…)

Posted: October 28, 2011 at 9:53 am

As part of stepping back to see the big picture I’ve turned a second look at deep machine learning systems and biologically inspired cognitive architectures (as suggested by my supervisor), the latter of which will be discussed in another post.

Deep machine learning systems attempt to resolve an issue with “shallow” learning which has increasingly become the following process: Input → Feature Extraction → Machine Learning. An argument against this approach is that the “intelligence” shifts from the machine learning system to the human-centred, and domain specific, art of feature extraction. Deep learning systems excise the middle man, allowing Input → Machine Learning, without the intermediary. (more…)

Posted: October 20, 2011 at 1:41 pm

After writing the previous post I had a meeting with my supervisor yesterday. He suggested that the answers to these questions of feature abstraction should be contextualized by the machine learning method used to organize these perceptual units. So I’m putting further development on the back burner to look at the big picture and do more reading. Following is a figure of the overall structure of the whole system, as I currently imagine it. (more…)

Posted: October 20, 2011 at 11:55 am

Since it’s time to explore some clustering methods for these perceptual patches, I first calculated a RGB histogram for each patch, making use of the mask. In attempting to make sense of the structure of the openCV hist (1 channel, but 3 dimensions) I realized that perhaps the hist is not appropriate for this project. The central question is: what is important about colour for the purpose of associating perceptual units? Perhaps the histogram should be abstracted into a set of concepts (for lack of a better term) representing major colour clusters. (more…)

Posted: October 5, 2011 at 3:01 pm

I’ve finally managed to get the segmentation data into a useful form. Following is a reconstruction of the original image from extracted patches, and a corresponding image that shows the segments, filled in random colours.

(more…)

Posted: September 1, 2011 at 6:05 pm

Now that I’ve passed my comps I’ve been getting back into working on image segmentation.

Here is the current state of segmentation (using the same test image as in previous posts), where every region, no matter now small, is coloured in a random colour:

(more…)