Difference between revisions of "AMatterRequirements"

From aHuman Wiki
Jump to: navigation, search
(Automated page entry using MWPush.pl)
 
(One intermediate revision by the same user not shown)
Line 1: Line 1:
−
 
 
<pre style="color: green">aMatter Requirements</pre>
 
<pre style="color: green">aMatter Requirements</pre>
 
@@[[Home]] -> [[ProjectPlanning]] -> [[aMatterRequirements]]
 
@@[[Home]] -> [[ProjectPlanning]] -> [[aMatterRequirements]]
Line 6: Line 5:
 
__TOC__
 
__TOC__
 
----
 
----
−
 
−
= 2016 book of work =
 
−
 
−
* target research - split specific and non-specific mind - '''done'''
 
−
* split mind into target, core, lifecycle, specific and integration modules - '''done'''
 
−
* copy aHuman core model to aWee - '''done'''
 
−
* create aWee target model - '''done'''
 
−
* implement filewatcher - primary sensor analogous to human eye (with focus point, focus depth, projection to neuromatrix - to be able to feel file system) - in progress
 
−
* design lifecycle set for software alive creature (aSoftLife, state control and autonomic control modules) - in progress
 
−
* reduce aWee core model to functionally transparent, improve external circuit coverage
 
−
* define aWee specific and integration models
 
−
* biological research - define set of neural tissue types
 
−
* biological research - describe logic of neural tissue types
 
−
* create aWee dynamical model
 
−
* setup running aWee model, define runtime metrics to measure proof of the concept
 
  
 
= Overall Features =
 
= Overall Features =
−
 
−
* to be refined later
 
  
 
== Mocked Functions ==
 
== Mocked Functions ==
Line 48: Line 30:
 
= Goals Achievement =
 
= Goals Achievement =
  
−
== Perception/Self-Learning features ==
+
== Perception/Self-Learning features ==  
  
−
=== Perception ===
+
=== Perception ===  
  
 
* Effective Signal Processing
 
* Effective Signal Processing
Line 63: Line 45:
 
** implement subsampling
 
** implement subsampling
  
−
=== Self-Learning ===
+
=== Self-Learning ===  
  
 
* Mock cortex implementation - to allow development of other components
 
* Mock cortex implementation - to allow development of other components
Line 97: Line 79:
 
** NeuroPool - time-based dissolving of membrane potential - '''done'''
 
** NeuroPool - time-based dissolving of membrane potential - '''done'''
 
** NeuroPool - postpone firing to minimum time interval after last firing - '''done'''
 
** NeuroPool - postpone firing to minimum time interval after last firing - '''done'''
−
** SparseMatrix - create intermediate activation representation for non-persistent components - like Dorsal Root Ganglion
 
 
* Signal Processing
 
* Signal Processing
 
** ExcitatoryLink - project excitatory signal to NeuroPool - '''done'''
 
** ExcitatoryLink - project excitatory signal to NeuroPool - '''done'''
 
** ExcitatoryLink - generate excited signal from projection - '''done'''
 
** ExcitatoryLink - generate excited signal from projection - '''done'''
 
** NeuroSignal - store only activated source items - '''done'''
 
** NeuroSignal - store only activated source items - '''done'''

Latest revision as of 18:51, 28 November 2018

aMatter Requirements

@@Home -> ProjectPlanning -> aMatterRequirements

Contents:

Overall Features

Mocked Functions

  • M-01. aMatter has primitive predefined set of effectors producing representation in external world based on predefined set of low-level commands provided by hardcoded motor strategies
  • M-02. aMatter limits effectors actions to ones explaining internal representations by means of hardcoded symbolical language
  • M-03. aMatter has primitive predefined hierarchy of behavioural strategies, on leaf level directly connected with effectors commands

Cognition

  • C-01. aMatter receives information using predefined set of sensors
  • C-02. aMatter recognises received information in real-time mode and calculates recognition metric R reflecting percentage of successfully recognised sensors inputs in given environment
  • C-03. aMatter generalises unrecognised inputs so that R monotonously increases for the same static environment
  • C-04. aMatter forms growing set of internal entities, so that specific subset of internal entities, when being in active state, can be treated as a representation of specific external data from sensors, disregarding whether previously perceived or internally inspired
  • C-05. aMatter is able to forget internal entities, if not activated for a long time, so that the same input triggers another set of internal entities after a while
  • C-06. aMatter forms growing set of associations between internal entities activated about the same time

Feeling

  • F-01. aMatter collects information from predefined set of embodiment signals equivalent in purpose with human being, with body treated as related operating system process with all its inherent features and properties
  • F-02. aMatter collects predefined set of uncertainty metrics from expectation flow of behavioural strategies

Goals Achievement

Perception/Self-Learning features

Perception

  • Effective Signal Processing
    • MindSensorArea - receptive field averaging and inhibition
    • ThalamusArea - create relay sensory nuclei - done
    • ThalamusArea - create inhibitory NeuroPool - done
    • Connect PerceptionArea feedback and inhibitory NeuroPool - done
    • Connect internal InhibitoryLink from relay NeuroPool and inhibitory NeuroPool - done
    • Implement realistic inhibitory properties (150ms inhibition vs 20 ms excitatory non-firing interval)
  • Functional value
    • implement sampling
    • implement subsampling

Self-Learning

  • Mock cortex implementation - to allow development of other components
    • create feed-forward NeuroPool - done
    • create spatial pooler - process feed-forward signal from ThalamusArea - done
    • create temporal pooler - process fixed-size sequences and derive predicted spatial pooler item - done
    • create feedback NeuroPool - done
    • apply temporal pooler prediction to feedback NeuroPool and generate cortex feedback signal - done
  • Cortex implementation
    • Columnar processing
    • Hierarchical Processing
    • Infinite Temporal Prediciton
    • Focus Processing
    • Attention Processing
    • Event Driven Implementation
  • Functional value
    • implement high-probability predictive sampling and subsampling

Cognition as Meaningful Sensor Control

  • saccadic scene scanning, spacial into temporal-spatial approach
  • novelty, motavation, attention
  • virtuality

Demonstrate Feeling Feature

  • TBD

Real-Time Neural Networks

  • Neural Structures
    • NeuroPool - accumulate arriving action potentials in membrane potential - done
    • NeuroPool - time-based dissolving of membrane potential - done
    • NeuroPool - postpone firing to minimum time interval after last firing - done
  • Signal Processing
    • ExcitatoryLink - project excitatory signal to NeuroPool - done
    • ExcitatoryLink - generate excited signal from projection - done
    • NeuroSignal - store only activated source items - done
Retrieved from "http://wiki.ahuman.org/index.php?title=AMatterRequirements&oldid=11738"