Skip to content

Audio (analog, digital) experiments using NuPIC HTM/CLA

License

Notifications You must be signed in to change notification settings

rcrowder/nupic.audio

 
 

Repository files navigation

nupic.audio

![Gitter](https://badges.gitter.im/Join Chat.svg) Gitter public chat channel

Auditory experiments using cortical learning algorithms (CLA) and hierarchical temporal memory (HTM).

Repositories of interest

Note: These repositories currently are all work-in-progress.

Online videos of interest

Taken from the collection gathered via Gitter channel https://gitter.im/rcrowder/EncodingSpecificityPrinciple -

Online books and references

Potential areas of investigation

  • Genre and style classification
  • Musical prediction and composition
  • Acoustic correlation using canonical correlation analysis (CCA)
  • Transient analysis (harmonic tracking)
  • Motion derivative encoding (similar to optical flow)
  • Echo location and spatial positioning (e.g. Anterior Ventral Cochlea Nucleus)
  • Stream segmentation and seperation (includes selective attention)
  • Cortical pathways and projections, 'What' and 'Where' pathways (belts?)
  • Auditory nerve spike firing (e.g. IHC to CN GBC integrators)
  • Dendritic micro-circuits and synaptic placement (temporal smoothing)
  • Spike-timing dependent plasticity
  • Acetylcholine inhibition enhancing discharge frequency but decreasing synaptic adaption
  • Acoustic related cell, and dendrite, membrane properties (cascading conductances, shunting)

An alternative for the encoding of audio signals is the modelling of spike firing of auditory-nerve fibers. A collection of models can be found in the EarLab @ Boston University (http://earlab.bu.edu/ See Modelling -> Downloadable Models). If you plan to use these models, beware of their history and limitations. For example, early models lack some necessary non-linearity in their responses.

About

Audio (analog, digital) experiments using NuPIC HTM/CLA

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • MATLAB 41.4%
  • Python 40.6%
  • C++ 8.6%
  • C 7.4%
  • Shell 1.6%
  • QMake 0.3%
  • CMake 0.1%