2015 SR&ED Claim

2015 Scientific Research and Experimental Development tax credit claim

T661 - Part 2 – Project Information

Section B – Project Description

Line 242 -– What scientific or technological uncertainties did you attempt to overcome- uncertainties that could not be removed using standard practice? (Maximum 350 words)

The project is attempting to develop general purpose learning and thinking software for the autonomous control of robots. The approach is based on the development of a new artificial neural network (ANN).

Current robot control software is not general purpose. It is specifically developed to function in a predefined environment with predefined tasks to be performed. An example is Google’s self-driving car control software. 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, CLARION, LIDA, SIGMA and HTM.  DRAMA, MAXSON and Brook’s COG are experimental architectures designed for robot control but have not been applied with any general purpose success. When such architectures are grounded on real sensory input they also make heavy use of stochastic inference that becomes complex and is a heavy computational overhead. One of the reasons for the complexity of these architectures is that they do not use the same structures for pattern recognition and motor action control.

This research is developing a new architecture to solve these problems. However there are no simple hierarchical ANNs based on binary nodes that are feed-forward and use reinforcement learning. There are also no ANNs that grow nodes in a hierarchy for both recognizing objects / sequences and for learning new action habits. Even the deep learning pattern recognition ANNs do not add nodes dynamically as they learn.

More specifically the project is attempting to:

  • Develop a new hierarchical structure for ANN nodes.
  • Use binary neurons (binons) with reinforcement learning.
  • Grow the ANN by adding nodes for parallel (spatial) and sequential (temporal) pattern recognition.
  • Convert graduated sensor readings (sub-symbolic) into symbolic stimuli.
  • Transfer short term memory traces into long term memory.
  • Learn action habits and integrate them into the associated hierarchical behavior network.
  • Execute action habits subconsciously while thinking about other actions (simulation based on experience).

Line 244 – What work did you perform in the tax year to overcome the scientific or technological 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

Two pieces of software are being researched;

A) In the area of object and sequential pattern recognition from multi-sensor senses producing graduated (ratio scale) and discrete (symbolic / nominal) 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:

  1. Tried using the frequency of occurrence of associating patterns and labels to obtain a better recognition rate in supervised learning. No substantial improvement in recognition occurred.
  2. Added different size gaps between edges to form patterns in which the parts are widely separated. The recognition rate improved but the speed was very slow.
  3. Started using edges as the lowest level feature in the recognition of two dimensional spatial patterns. The edges were then combined to form corners and areas of different shapes.

In area B:

  1. Used Morse code as the source of sensor readings to refine the attention – action cycle. This began with multi-modal recognition combining the three properties of dit/dar, duration and the letter labels. However, this work was reduced to just one property to recognize repeated sequences.
  2. Worked with two different data structures to form the short term memory patterns of sequential stimuli and to detect when patterns repeat.
  3. Added a data structure to represent the active habits that are recognizing sequential patterns of stimuli. One habit is designated as the conscious one (the one being done) and the others are subconscious.

Line 246 – What scientific or technological advancements did you achieve as a result of the work described in line 244? (Maximum 350 words)

  1. Determined that the ratio of the count of repeating patterns could be used at all levels of complexity, not just the sensory level. Edges are found between any two repeating patterns.
  2. Realized that the algorithm that recognizes sequential patterns is sufficiently general purpose to recognition spatial / parallel patterns.
  3. There is a need to have subconscious recognition habits that habituate as a result of repeated sequences of patterns at all levels of complexity in the ANN hierarchy.