2012 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 autonomous 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.
- Conversion of graduated sensor readings (sub-symbolic) into symbolic stimuli.
- Transfer of short term memory traces into long term memory.
- Learnt action habits integrated into an associated hierarchical behavior network.
- Parallel execution of subconscious action habits.
242 - What technological obstacles/uncertainties did you have to overcome to achieve the advancements described in line 240? (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. they are not 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 in a hierarchy for each new object or sequence recognized or for each new action habit learnt.
244 – What work did you perform in the tax year to overcome the technological obstacles/uncertainties described in Line 242? (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. More details about the research are available at www.adaptroninc.com
Areas of research performed this year - Two pieces of software are being crafted;
A) In the area of object and sequence recognition from multi-sensor senses producing graduated and discrete (symbolic) stimulus readings using a hierarchy of binons. Each new version of this software is then integrated into B.
B) In the area of short term and long term memory, learning, thinking and a hierarchical action habit structure.
In area A:
- Modified the recognition of graduated readings based on the independence of contrast, reflections and negatives.
- Introduced a new shape recognition algorithm that avoids the need to recognize gaps.
- Tested a new principle for pattern recognition based on the rule that neurons that “fire together, wire together”.
- Separated out the recognition of combinations of independent object properties from combinations of objects.
5/ Added a new bitmap structure to represent the “where” (source) of an object.
In area B:
- Twice integrated the pattern recognition algorithms from the A software into the B software.
- Twice rethought, redesigned, implemented and tested an improved action habit representation and execution hierarchy, with and without orienting responses.
- Tested the model with and without automatic kinesthetic feedback stimuli.
- Made three modifications to the Short Term Memory (STM) algorithm to detect repeated sequences.
- Added then tried to get working and disabled a conscious STM.
- Modified the attention attraction criteria.
- Added a practice mode for action habits with directed attention.
- Implemented generalization and discrimination for multi-sense stimuli
- Separated goal driven action from practice driven action.
- Revised the approach to handle fully explored (permanent) stimuli.