Citation: Nugent MA, Molter TW (2014) AHaH Computing–From Metastable Switches to Attractors to Machine Learning. PLoS ONE 9(2): e85175. https://doi.org/10.1371/journal.pone.0085175
Get the official YouTube app for Android phones and tablets. See what the world is watching - from the hottest music videos to what’s trending in gaming, entertainment, news, and more. Subscribe to channels you love, share with friends, and watch on any device. With a new design, you can have fun exploring videos you love more easily and quickly than before. Sign in to like videos, comment, and subscribe. Watch Queue Queue.
Editor: Derek Abbott, University of Adelaide, Australia
Received: May 7, 2013; Accepted: November 23, 2013; Published: February 10, 2014
Copyright: © 2014 Nugent, Molter. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Funding: This work has been supported in part by the Air Force Research Labs (AFRL) and Navy Research Labs (NRL) under the SBIR/STTR programs AF10-BT31, AF121-049 and N12A-T013 (http://www.sbir.gov/about/about-sttr; http://www.sbir.gov/#). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Competing interests: The authors of this paper have a financial interest in the technology derived from the work presented in this paper. Patents include the following: US6889216, Physical neural network design incorporating nanotechnology; US6995649, Variable resistor apparatus formed utilizing nanotechnology; US7028017, Temporal summation device utilizing nanotechnology; US7107252, Pattern recognition utilizing a nanotechnology-based neural network; US7398259, Training of a physical neural network; US7392230, Physical neural network liquid state machine utilizing nanotechnology; US7409375, Plasticity-induced self organizing nanotechnology for the extraction of independent components from a data stream; US7412428, Application of hebbian and anti-hebbian learning to nanotechnology-based physical neural networks; US7420396, Universal logic gate utilizing nanotechnology; US7426501, Nanotechnology neural network methods and systems; US7502769, Fractal memory and computational methods and systems based on nanotechnology; US7599895, Methodology for the configuration and repair of unreliable switching elements; US7752151, Multilayer training in a physical neural network formed utilizing nanotechnology; US7827131, High density synapse chip using nanoparticles; US7930257, Hierarchical temporal memory utilizing nanotechnology; US8041653, Method and system for a hierarchical temporal memory utilizing a router hierarchy and hebbian and anti-hebbian learning; US8156057, Adaptive neural network utilizing nanotechnology-based components. Additional patents are pending. Authors of the paper are owners of the commercial companies performing this work. Companies include the following: Cover Letter; KnowmTech LLC, Intellectual Property Holding Company: Author Alex Nugent is a Co-owner; M. Alexander Nugent Consulting, Research and Development: Author Alex Nugent is owner and Tim Molter employee; Xeiam LLC, Technical Architecture: Authors Tim Molter and Alex Nugent are co-owners. Products resulting from the technology described in this paper are currently being developed. This does not alter the authors’ adherence to all the PLOS ONE policies on sharing data and materials. The authors agree to make freely available any materials and data described in this publication that may be reasonably requested for the purpose of academic, non-commercial research. As part of this, the authors have open-sourced all code and data used to generated the results of this paper under a “M. Alexander Nugent Consulting Research License”.
Contains Ads
Get the official YouTube app for Android phones and tablets. See what the world is watching -- from the hottest music videos to what’s trending in gaming, entertainment, news, and more. Subscribe to channels you love, share with friends, and watch on any device.
With a new design, you can have fun exploring videos you love more easily and quickly than before. Just tap an icon or swipe to switch between recommended videos, your subscriptions, or your account. You can also subscribe to your favorite channels, create playlists, edit and upload videos, express yourself with comments or shares, cast a video to your TV, and more – all from inside the app.
FIND VIDEOS YOU LOVE FAST
• Browse personal recommendations on the Home tab
• See the latest from your favorite channels on the Subscriptions tab
• Look up videos you’ve watched and liked on the Account tab
CONNECT AND SHARE
• Let people know how you feel with likes, comments, and shares
• Upload and edit your own videos with filters and music – all inside the app
With a new design, you can have fun exploring videos you love more easily and quickly than before. Just tap an icon or swipe to switch between recommended videos, your subscriptions, or your account. You can also subscribe to your favorite channels, create playlists, edit and upload videos, express yourself with comments or shares, cast a video to your TV, and more – all from inside the app.
FIND VIDEOS YOU LOVE FAST
• Browse personal recommendations on the Home tab
• See the latest from your favorite channels on the Subscriptions tab
• Look up videos you’ve watched and liked on the Account tab
CONNECT AND SHARE
• Let people know how you feel with likes, comments, and shares
• Upload and edit your own videos with filters and music – all inside the app
Collapse
55,881,184 total
4
2
Read more
Varies with device
5,000,000,000+
Varies with device
Varies with device
Parental Guidance Recommended
Users Interact, Digital Purchases
Google LLC
1600 Amphitheatre Parkway, Mountain View 94043