2009 Scientific Research and Experimental Development tax credit claim
T661 - Part 2 – Project Information
Section B – Experimental development
240 - What technological advancements were you trying to achieve? (Maximum 350 words)
General purpose learning and thinking software for control of robots based on artificial neural networks (ANN). Advancements in the architecture of a hierarchical structure for ANN nodes, the use of binary neurons (binons) with reinforcement learning, network growth from the addition of nodes for parallel and sequential pattern recognition and learnt action habits integrated into an associated hierarchical behavior network.
242 - What technological obstacles did you have to overcome to achieve those advancements? (Maximum 350 words)
Current robot control software is not general purpose. It is specifically developed to function in a predefined environment with predefined tasks to be performed. Learning capability, if present, is limited to this environment. General purpose artificial intelligence architectures exist but are not designed for robot control i.e. grounded on sensory input and device activation. Examples include ACT-R, SOAR, and HTM. DRAMA, MAXSON and Brook’s COG are experimental architectures designed for robot control but have not been applied with any success. This research is developing a new architecture to solve the problem. However there are no hierarchical ANNs based on binons that are feed-forward and use reinforcement learning. There are also no ANNs that grow nodes for each new object or sequence recognized or new action habit learnt.
244 - Summarize the work performed in the tax year, and explain how that work contributed to the advancement of scientific knowledge. (Summarize the systematic investigation) (Maximum 700 words)
Approach: Increase the complexity of the ANN structure and algorithms to process the requirements at greater complexity while still handling the lower complexity features. Run regression tests on already working lower complexity features. Determine its success at learning and thinking based on the observation of its actions in artificial test environments simulated in software and by inspection of its internal memory traces and processes.
Areas of research performed this year - Two pieces of software are being crafted;
A) In the area of object and sequence recognition from a multi-sensor sense producing graduated and discrete stimulus readings using a hierarchy of binons.
B) In the area of learning, thinking and action habits.
In area A:
- Tried various schemes for combining edges and stimulus readings to identify objects, with and without gaps, independent of position, size and intensity.
- Developed a procedure for recognizing reflections and negatives of objects.
- Designed an algorithm to determine the most likely object to have moved, which objects are new and which have disappeared in a sequence of stimulus readings.
In area B:
- Developed a strategy in which all possible responses are done once before successful ones are retried. Strategy failed and reverted back to repeating successful responses and trying new responses when results become boring.
- Modified the use of interest levels as reinforcement and in the determination of what are unexpected and thus what attracts attention.
- Reworked the subconscious background habits and improved conscious habit processing.
- Changed the tree of sequential habits for overlapping stimuli and the recognition of stimulus sequences with actions in between.
- Integrated the software from area A into B,
- Fixed the current thinking algorithm (low complexity – one step ahead)
- Added multimodal (2 and 3 senses) stimulus recognition using binons.