United States

As one of the pillars of readiness, maintenance manning plays a critical role in the production of mission capable aircraft; the quantity, skills, and experience of maintainers onboard directly impacts the ability of a squadron to meet its readiness goals. Current distribution of maintainers is performed manually according to a set of heuristics and expert knowledge. Prior work performed under the Digital Aviation Readiness Technology Engine (DARTE) effort focused on automating this process via a statistical approach to identifying targeted, data-driven personnel moves expected to increase the readiness of the enterprise. Improving upon this work, the Resource Optimization with Agent Reinforcement (ROAR) model is built using reinforcement learning to train an agent which directs maintainer transfers within the fleet. The agent learns within a simulated environment which incorporates predictive models of important features into the transition model. This approach allows the agent to consider additional elements of the state of the enterprise (e.g. expected change in mission capable aircraft). In this way, the agent can select targeted personnel transfers which maximize readiness across the enterprise.

NAML 2022

Resource Optimization with Agent Reinforcement

maintenance manning

readiness

reinforcement 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>

NAML 2021

poster

##### For full functionality of Underline, please SHUT OFF your VPN, or use a personal device.


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


<figure class="video_container">
  <iframe src="https://s3.amazonaws.com/pf-user-files-01/u-59356/uploads/2022-03-22/hk13mxo/NAML_ReceptionWithtitle.mp4" width=826  height=526  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

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



Assuming the common aphorism that “all models are wrong, but some are useful”, the natural question to ask is, how do we know a model is useful, and in particular, how useful is it? Uncertainty Quantification (UQ) is the scientific framework typically employed in search of answers to these types of questions. UQ is a multi-disciplinary field, borrowing tools from probability, statistics and numerical analysis; it has been around for a long time and has been applied, in one form or another, in various physics and engineering contexts to identify, quantify, and reduce uncertainties associated with models, algorithms and experimental outcomes. 

With the advent of Deep Learning (DL), substantial progress has been made in research areas dealing with the modeling and understanding of complex systems that had been otherwise challenging to achieve with conventional methods. Despite DL’s successes in many of these areas, the deployment of robust and reliable DL systems in safety-critical, high-risk, real world applications remains limited, in part due to the inherent fragility of basic DL models, as well as their tendency to deliver over- or under-confident prediction estimates, i.e. lack of proper calibration. To overcome this, in recent years there has been an increased interest in understanding and quantifying uncertainty in DL network models, and a variety of approaches have been proposed. The goal of this tutorial is to provide a gentle introduction and overview of Uncertainty Quantification in Deep Learning, focusing on some of the main techniques, applications and challenges. In the first half, George will provide a brief overview of UQ in Deep Learning, and will discuss some intrinsic UQ methods for DL, which treat uncertainty organically within a DL model. In the second half Ben will discuss extrinsic/post-hoc UQ methods for DL, which allow for the estimation of uncertainty and the calibration of existing non-probabilistic DL models, using conventional methods (e.g. temperature scaling), as well as techniques based on novel metrics (e.g. the recently introduced angular margin).


Uncertainty Quantification in Deep Learning

In this session, attendees will participate in a live tutorial of Juneberry, an experimental machine learning framework designed to manage the training and evaluation of machine learning models. Each participant will be able to download a fully configured Docker container and follow along with a live exercise. The exercise is based on the tutorial “Replicating a Classic Machine Learning Result with Juneberry”, which guides users through the steps required to replicate a ResNet from the He et al. 2015 paper.

Juneberry aims to reduce the costs associated with having to deal with multiple sets of machine learning models. The framework facilitates experimentation and model comparison through a JSON-based config file system, which manages input data files, models, and the underlying calls of machine learning platforms such as PyTorch, TensorFlow, Detectron2, and MMDetection. By relying on this config pipeline, a machine learning researcher can focus more on the design of their model, while spending less time implementing and iterating upon their design.

Juneberry also offers an “experiment outline” feature, which allows users to vary aspects of their base model and compare how the model’s performance reacts to those changes. Experiments also allow users to compare the performance of multiple models, enabling researchers to choose the model that is the best match for their design goals.

IMPORTANT:

Before the tutorial the users will need to have docker installed on their platform (note, we do NOT support Apple Silicon) and download a specific docker image. The directions can be found here:
https://github.com/cmu-sei/juneberry/blob/main/docs/vignettes/vignette1/Replicating_a_Classic_Machine_Learning_Result_with_Juneberry.md#working-with-juneberry-docker-containers

For more information about Juneberry, see the following links:
https://github.com/cmu-sei/juneberry
https://github.com/cmu-sei/juneberry/blob/main/juneberry/documentation/vignettes/Replicating_a_Classic_Machine_Learning_Result_with_Juneberry.md

Juneberry, a machine learning experiment framework tutorial

Challenges and Opportunities in the Navy AI Space: An Operational Perspective from the AI Task Forces

This talk describes the principle of ``General Cyclical Training'' in machine learning, where training starts and ends with "easy training" and the "hard training" happens during the middle epochs. We propose several manifestations for training neural networks, including algorithmic examples (via hyper-parameters and loss functions), data-based examples, and model-based examples. Specifically, we introduce several novel techniques: cyclical weight decay, cyclical batch size, cyclical focal loss, cyclical softmax temperature, cyclical data augmentation, cyclical gradient clipping, and cyclical semi-supervised learning. In addition, we demonstrate that cyclical weight decay, cyclical softmax temperature, and cyclical gradient clipping (as three examples of this principle) are beneficial in the test accuracy performance of a trained model. Furthermore, we discuss model-based examples (such as pretraining and knowledge distillation) from the perspective of general cyclical training and recommend some changes to the typical training methodology. In summary, this paper defines the general cyclical training concept and discusses several specific ways in which this concept can be applied to training neural networks.


On General Cyclical Training of Neural Networks

Derivations are given of various versions of equilibrium propagation using adjoint methods. The learning rules are studied using simulations with the MNIST data set.

Variational Perspective on Learning Rules for Networks with an Energy Function

Increasingly, operational systems within the defence space are leveraging AI/ML models. These models introduce unique vulnerabilities that cannot be addressed by traditional cybersecurity methods because their inputs during both training and deployment hang outside of traditional security firewalls. Consequently, AI/ML models are susceptible to a variety of adversarial attacks, both naturally occurring and those of malicious intent used to influence model behaviour or defeat AI/ML systems entirely. This poster provides a high-level overview of some of these vulnerabilities and outlines current work aimed at securing these AI/ML systems within an operational context.

Robustness and Security for AI and the Dangerous Dismissal of Edge Cases

Modulation recognition on Intel’s Loihi through ANN/SNN conversion

Monitoring of maritime objects, particularly dark vessels, at a global scale is a challenging task. Synthetic aperture radar (SAR) is a valuable data source because it offers day/night and all-weather situational awareness unlike passive sources such as electro-optical imagery or data sources requiring vessel cooperation such as automatic identification system (AIS) or vessel monitoring system (VMS) data. Deep learning-based computer vision approaches to analyzing SAR imagery have historically been limited by a scarcity of high-quality labeled imagery. To address this problem and to stimulate academic and commercial development of SAR-focused object detectors, the xView3 dataset and challenge was recently introduced to provide annotated imagery for training and evaluation drawn from the ongoing Sentinel-1 satellite SAR mission operated by the European Space Agency. While the xView3 dataset is an important contribution to SAR computer vision research, this is a temporary and limited solution. As novel examples are seen in the wild and as new SAR sensors become available, existing object detection models will need to be retrained with relevant new examples. Given a pool of unlabeled images, the task of selecting new images to label is traditionally assigned to human experts or chosen randomly. As labeling resources are limited, particularly with SAR which requires specialized expertise and ancillary data, it is important to select the most informative images to label so that the model steadily improves as new examples are encountered. Active learning (AL) seeks to automate and optimize this data selection process. Active learners provide an acquisition function which selects a subset of examples for labeling from the set of unlabeled data according to some criteria such as uncertainty, disagreement, diversity, expected error reduction, etc. In this work, we propose to evaluate state-of-the-art AL algorithms for the task of maritime object detection in SAR imagery using the xView3 dataset. To the best of our knowledge, no publicly available work has compared different AL approaches for SAR-based computer vision. We compare their learning curves for different dataset slices (e.g., near-shore, open-ocean, island, etc.) as well as for different object detection models to assess the transferability of AL algorithms to new data and model architectures. Given the high resolution and volume of satellite SAR imagery, we additionally report processing time for each algorithm. We identify gaps in current AL solutions for SAR computer vision and propose solutions to address these shortcomings to improve their utility in practical settings.

Active learning for maritime object detection in synthetic aperture radar imagery

Apply Reinforcement Learning (RL) techniques to extend the holdover time of an inertial system in the absence of aiding from a Global Navigation Satellite System (GNSS).

Drift Improvement through Reinforcement Learning - INS (DIRT-I)

Modern radar simulation development primarily uses raw data collects from blue forces placed in intelligence databases that have not yet been thoroughly vetted and distilled into a usable data product.  These resources often have redundant, ambiguous, or missing information describing modes and operation of the system that must be preprocessed by those local to the organization developing the simulations rather than the Intelligence Communities (ICs) themselves.  The ICs’ process to generate a Tier I or II product takes considerable time and doesn’t always meet the timeline requirement to support the Warfighter in a dynamically changing Electronic Warfare (EW) threat environment.  Hence, it is required for personnel to utilize data-driven tools leveraging Artificial Intelligence (AI) and Machine Learning (ML) to down-select redundant or ambiguous information and impute missing information to construct quick-reaction models at a relatively high frequency.  This effort employs clustering algorithms to find redundant or ambiguous modes for a particular emitter and then constructs the radar simulation based on the consolidation of modes.  The quality is comparable to the traditional manual construction of simulations in many cases and drastically increases the speed and quantity at which simulations are processed.  Missing parameter data is addressed by utilizing a decision-tree based regressor that imputes the missing parameters based on training data taken from other sources that could provide inference (i.e. other radars).  Lowering the variance of these estimates requires execution on data at fairly low levels describing the radar system, but has potential to initially bridge parameter gaps not yet filled. 

Premium content

Resource Optimization with Agent Reinforcement

Next from NAML 2022

Uncertainty Quantification in Deep Learning

Similar lecture

Computational Modeling Of Trust Factors in Recognition of Warfighting Ships

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES