Implementation of Associative Memory with Online Learning into a Spiking Neural Network on Neuromorphic Hardware

reportActive / Technical Report | Accession Number: AD1108514 | Open PDF

Abstract:

Implementing cognitive algorithms on robots is one potential direction to realize autonomous artificial agents. There is an effort to push robotics and artificial intelligence into many aspects of daily life. An important step in this process is leveraging concepts known to work from human cognitive features on computer systems to improve the performance of robotic systems. Spiking Neural Networks SNNs allow these computational models to be instantiated in a low size, weight, and power SWaP form factor due to the biological efficiencies they approximate.

Author(s):
Hampo, Michael J
Author Organization(s):
University of Dayton Dayton United States
Descriptive Note:
Technical Report
Pagination:
0057

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release;

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
AFRL-RY-WP-TR-2020-0280
Contract/Grant Number(s):
FA8650-18-C-1607
Monitor Series:
AFRL-RY-WP-TR-2020-0280
 Subject Terms
Joint Capability Areas:
JCA_1.2.1_Training; JCA_5_Command and Control; JCA_1.2.6_Concepts; JCA_4.6_Engineering; JCA_1.2.5_Lessons Learned; JCA_1.2.3_Educating; JCA_5.4_Decide
Modernization Areas:
AI and Machine Learning
Communities of Interest:
Energy and Power Technologies
Descriptor(s):
autonomy, artificial neural networks, artificial intelligence, simulators, robotics, machine learning, content addressable memory, algorithms, artificial intelligence software, energy efficiency
Field(s)/Group(s):
Cybernetics
Keyword(s):
low SWaP, machine learning, neuromorphic, spiking neural network
Report Date:
2020 Sep 01
Creation Date:
2020 Sep 14