United States

Developing systems capable of learning at the edge post-deployment can greatly expand AI’s ability to adapt to changes in the environment and incorporate new information that may not be available prior to its deployment. Biological systems have become extremely adept at processing and learning complex signals with few computational resources in real time. In this work, we use the insect’s processing and internal representation of polarized light and auditory signals as inspiration to demonstrate archictectures capable of learning new RF signals post-deployment. Our architecture works with the complex envelope as input, and creates a robust internal representation that projects the in-phase and quadrature components into a higher dimensional space. It also relies on modulated synaptic plasticity rules to learn specific RF patterns in real time. In order to validate our architecture we have constructed a dataset of words consisting of specific sequences of multiple symbols, and subject our architectures to two types of online learning assays: in the online learning task the architecture is receiving a randomized stream of RF signals and needs to learn the vocabulary in a supervised fashion in a single experiment in real time. In the continual learning task, different patterns are shown sequentially, and the system needs to demonstrate the ability to incorporate this new information and build a larger vocabulary while minimizing catastrophic forgetting. For this presentation we will focus on vocabularies encoded using 8-PSK and 16-QAM modulation schemes. However, the proposed approach is general enough that could be applicable to any type of signal amenable to extract its complex envelope. This research has been partially funded through DARPA’s Lifelong Learning Machine program and Argonne’s Laboratory Directed Research and Development program.

NAML 2021

Online and Continual Learning of RF Data Using Brain-Inspired Architectures

edge ai

neuromorphic computing

online learning

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

* To spread awareness of current machine learning research relevant to Naval applications

* To connect machine learning researchers with experts in military requirements

* To build and strengthen collaborations within the defense research community

**Watch this video to hear about the AFCEA purpose.**

<iframe width=1280 height=706 frameborder="0" scrolling="no" src="https://screencast-o-matic.com/player/creleVVcvRh?v=6&ff=1&title=0&controls=1" allowfullscreen="true"></iframe>

technical paper

The Strategic and Technical Landscape in 2021

Leading Change and Transformation at Scale in an Era of AI and Exponential Technologies

Unlocking Power of Data for Space Exploration

Managing Emerging Technology Transitions

Keynote Q&A sessions

Autonomy and Edge Computing Q&A Session

Autonomous systems, both cyber and physical, operate in highly contested environmentsin which it must be assumed that adversaries are capable, agile and informed about state-of-the-arttechnology. In order to sustain performance in such environments, systems must be able to adaptautonomously through online machine learning - that is, improve their performance quickly, evenover the duration of a single engagement. In this presentation, we outline the challenges of adapting insuch environments and propose a solution approach that leverages a variety of recent innovations inreinforcement learning, distributed computing and trusted consensus algorithms such as Blockchain. We argue that multi-component systems operating in contested environments must leverage theirredundancy for learning while also remaining resilient with respect to component failures and com-promises. In particular, to enable and accelerate learning, such systems will have to allow somenumber of components to operate sub-optimally to achieve the right exploration-exploitation bal-ance needed for rapid and effective reinforcement learning. At the same time that some number ofcomponents are possibly being sacrificed due to sub-optimal performance, the underlying missionof the system must be maintained. This leads to challenges in distributed trusted computing suchas Byzantine agreement problems. We include a discussion of the role of current Blockchain tech-nology in supporting future multiagent adaptive adversarial autonomy with the desired associatedresilience.

Resilient Distributed Adaptive Cyber-Defense Using Blockchain

Data and analytics are strategic assets supporting the Department of the Navy’s DON Information Superiority Vision (ISV). Exploiting our data drives the critical insights and decision-making that inform the full range of DON missions and functions, from integrated joint operations to the care and feeding of the Naval enterprise. This session will discuss how Sailors, Marines, and Civilians are leveraging Jupiter, the Naval Enterprise Data & Analytics environment, to integrate, share, and exploit data at speed and scale across the Warfighting, Business, and Readiness pillars. Jupiter makes DON data widely discoverable, accessible, understandable, and usable across the Naval enterprise and arms our military and civilian decision-makers with decision support analytics and context-rich visualizations, while simultaneously providing our data workforce with access to advanced data tools. This session will focus on how four Naval organizations are leveraging Jupiter’s capabilities for data analysis, visualization, and advanced analytics to drive decision advantage.

Leveraging Jupiter for Decision Advantage Across the Department of the NavyDepartment of the Navy

Safety represents a primary consideration and formidable challenge for unmanned autonomous vehicles.   DoD Standard Practice for System Safety (MIL-STD-882E, 2012), and DoD Joint Software Systems Engineering Handbook (JSSSEH, 2012) provide standard practices and guidelines that can be applied to development, testing, and evaluation of software in unmanned autonomous systems.

This presentation highlights the process for software engineering and hazard analysis applicable to autonomous systems based on MIL-STD-882 and JSSSEH.  This process is broadly defined in terms of requirements, design, implementation, testing, verification, validation and lifecycle support tasking. 

Level of Rigor in Software Engineering for Unmanned Autonomous Systems

Reduced Precision Computation for Accurate and Robust Learning Systems

keynote

live discussion

poster

https://d3smihljt9218e.cloudfront.net/transcript/11033/subtitle/cf24e28b31ac0e6bea385cb4c8d56c54.vtt

English (automatic)

Premium content

Online and Continual Learning of RF Data Using Brain-Inspired Architectures

Downloads

Next from NAML 2021

The Strategic and Technical Landscape in 2021

Similar lecture

Energy Based Models for Analog Neural Networks