Haikonen’s Doctoral Thesis – Part III

Pentti Haikonen is one of the most salient researchers on Machine Consciousness. His PhD Thesis entitled:

“An Artificial Cognitive Neural System Based on a Novel Neuron Structure and a Reentrant Modular Architecture with Implications to Machine Consciousness”

is one of the first doctoral dissertations in the field of Machine Consciousness. In this thesis, Haikonen introduces the Haikonen Associative Neurons and his Cognitive Architecture.

Part III of Haikonen’s thesis is available here:

Haikonen, Pentti O. A., An Artificial Cognitive Neural System Based on a Novel Neuron Structure and a Reentrant Modular Architecture with Implications to Machine Consciousness. Helsinki University of Technology, Applied Electronics Laboratory, Series B: Research Reports, Espoo 1999, 156 pp. ISBN 951-22-4730-5, ISSN 1456-1174.

Continue reading “Haikonen’s Doctoral Thesis – Part III”

Haikonen’s comment on article by Doan

Pentti Haikonen comments invited by Conscious-Robots.com editor on the recent article about Haikonen’s Architecture for Conscious Machines written by Trung Doan.

I wish to thank Trung Doan for his analysis of my approach towards machine consciousness here. Trung Doan has done a lot of work here as he illustrates the main principles with practical examples, which are worked out along the principles that I present in my book “Robot Brains”.

I would like to add some comments. My realization relies on associative neurons, which form associative memories. An associative memory is a rather old invention, but it has not gained much popularity because of the so-called interference problem, which limits the capacity of the memory. My contribution relates to the interference problem and in my book I describe methods, which allow the interference-free use of the full capacity; the capacity of the associative memory can be the same as the capacity of similar complexity random access memory. However, if only partial capacity is used, then the associative memory also performs the act of classification.

Trung Doan notes correctly that the neural machinery does not operate with numeric values, instead the individual signals represent elementary features of sensed entities and these are the basic meaning of these signals. It is useful to note that in the machinery groups of signals that represent some sensed entity may be used to stand for completely different things; these signal groups act as symbols for these things. This is a necessary prerequisite for e.g. natural language and inner speech.

Continue reading “Haikonen’s comment on article by Doan”

Pentti Haikonen’s architecture for conscious machines

Pentti Haikonen’s architecture for conscious machines

By Trung Doan (doanviettrung a_t gmail dot com).

Haikonen’s contribution to the machine-consciousness endeavor is an architecture based on cognitive principles. He also developed some electronic microchips as a first step to building a machine based on that architecture.

Below, we look at how a Haikonen machine might achieve consciousness once built, by examining some of its cognitive capabilities, and in the process will briefly discuss the Haikonen architecture.

The Haikonen machine perceives

Say the Haikonen machine’s cameras are  focusing on a yellow ball. The cameras’ pixel pattern is fed into a preprocessor circuit which produces an array of, say, 10,000 signals, each signal carried by, for example, a wire. One wire is the output from the preprocessor’s “roundness” circuitry and, in this case, the signal is On. Another wire, from the “squareness” circuitry, would be Off, i.e. carrying no voltage. A group of wires is the output from the spectrum-analysis circuitry, the wire corresponding to frequencies which we humans recognise as “yellow” is On while “red”, “blue”, etc., wires are Off. There would be many other groups of wires depicting size, brightness, edges, etc.

The machine does not internally represent the ball as a round graphic, nor a set of numbers representing diameter, color, etc., but by this signal array. Haikonen calls this a “distributed signal representation”.

Suppose the machine is shown several balls of different sizes, colors, etc., one at a time, and each time its microphone hears the sound pattern we humans understand as the word “ball”. Because they appear at the same time repeatedly, the machine associates the sound pattern and the visual pattern together. The making of associations is how the machine’s perception is done.

After several different balls are associated with that sound pattern, the machine finally learns to associate the “ball” sound pattern with anything that is round.

Continue reading “Pentti Haikonen’s architecture for conscious machines”

The Cognitive Approach to Conscious Machines

The Cognitive Approach to Consciousn Machines book coverThe Cognitive Approach to Conscious Machines
by Pentti O. Haikonen
Principal Scientist, Cognitive Technology, Nokia Research
Imprint Academics. March 2003, 300 pp., ISBN 0907845428.

Review of the book ‘The Cognitive Approach to Conscious Machines’ by Pentti O. Haikonen, Principal Scientist, Cognitive Technology, Nokia Research.

The first thing to say about this book is that it is quite complete. For anyone interested in Machine Consciousness, this is an excellent resource as it covers virtually all open issues of this research field. The first part of the book is an introduction to computation, Artificial Intelligence and Neural Networks, so it is worth reading for those who don’t have a good background in Computer Science (even though if you are not particularly interested in Machine Consciousness).

The simple and direct writing style of the book makes it quite easy to read, even to the non-native English speaker (like me). It is actually amazing how the author manages to deal with lots of controversial and complicated issues with such a clarity and simplicity. After having read some other books on consciousness I have to say that this is the one that you can read and have the real feeling that you actually understand everything. But make no mistake; this apparent simplicity doesn’t imply that the author doesn’t approach the hard issues of Machine Consciousness. On the contrary, hard problems like the generation of speech are brilliantly tackled down and practical solutions are always explained.

Part II of the book is an introduction to consciousness and cognition, hard concepts that again are clearly introduced and explained. Part III of the book covers the author’s Machine Consciousness proposal, the cognitive architecture. I think that someone with a strong background in Computer Science (part I) and also in the scientific study of consciousness (part II) could skip parts I and II. However, I enjoyed reading them as they are presented from a particular straightforward point of view. Haikonen’s cognitive architecture described in part III of the book is something that anyone seriously interested in Machine Consciousness should read. I personally don’t know of any other framework that covers in such a broad range the problem of Machine Consciousness.

Finally the two last chapters are quite thought provoking and provide an insight of what the field of Machine Consciousness could lead us to in the future.