United States

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).

NAML 2022

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

rlzoo

inertial navigation systems

openai gym

kalman filter

reinforcement learning

**BRACIS** originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence – **SBIA** (22 editions), and the Brazilian Symposium on Neural Networks – **SBRN** (13 editions). <br>**ENIAC** is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. <br>**STIL** is the bi-annual Language Technology event.
All events are supported by the Brazilian Computer Society – Special Interest Groups: **CE-IA**, **CE-IC** and **CE-PLN**.<br><br><br>

To access the 10th Brazilian Conference on Intelligent Systems (**BRACIS**), you need to register for the conference.  Please visit the Conference official site to register

[Register now](http://c4ai.inova.usp.br/bracis2021/)

Register now

BRACIS 2021

BRACIS originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence – SBIA (22 editions), and the Brazilian Symposium on Neural Networks – SBRN (13 editions). 
ENIAC is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. 
STIL is the bi-annual Language Technology event.
All events are supported by the Brazilian Computer Society – Special Interest Groups: CE-IA, CE-IC and CE-PLN

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

Automatic Modulation Classification (AMC) is an important front-end step in a number of applications such as Signals Intelligence, spectrum interference monitoring, link adaptation, dynamic spectrum access, radio fault detection, cognitive radio and 4G/5G cellular standards. We present results of Quantization-Aware Training (QAT) and Pruning of a Deep Convolutional Neural Network (DCNN) for Hardware-Efficient RF modulation classification. An 8-bit quantized MobileNeXt DCNN consisting of sandglass blocks of Depthwise and Pointwise convolution layers was trained on the DeepSig RadioML 2018.01A dataset as part of the 2021 ITU AI/ML in 5G Lightning-Fast Modulation Classification challenge organized by the International Telecommunication Union. The training was done using the Xilinx Brevitas QAT library and the PyTorch pruning library. We introduce the notion of Inference Cost whose key determinants are the number of multiply accumulate (MAC) operations, the number of weights and the bit precision of the weights and activations as compared to a reference 8-bit quantized VGG10 DCNN. We will discuss the next steps for deploying the model with hardware specific optimizations on the Zynq UltraScale+ RFSoC using the Xilinx FINN (Fast Scalable Quantized Neural Network Inference) library. Work was supported by FY21 NISE 219 funding.

Quantization-Aware Training and Pruning for Hardware-Efficient Neural Network Modulation Classification

Understanding data prior to using machine learning algorithms can help make machine learning (ML) results less opaque and inform ML design decisions. Characterizing the geometry (topology) of data can help identify (i) missing data and (ii) the complexity of the decision boundary between different classes of data. This can lead to the more efficient deployment of ML tools. In this poster we present new results on our use of topological data analysis for analyzing machine learning tools and show how to scale these methods to manage larger data sets. We illustrate this approach with a large data set from the particle physics community and compare topological results with deep learning results.

Extracting Properties of Separators from Larger Scale Data using Topological Data Analysis Methods

Can reproduction alone in the context of survival produce intelligence in our machines? In this work, self-replication is explored as a mechanism for the emergence of intelligent behavior in modern learning environments. By focusing purely on survival, while undergoing natural selection, evolved organisms are shown to produce meaningful, complex, and intelligent behavior, demonstrating
creative solutions to challenging problems without any notion of reward or objectives. Atari and robotic learning environments are re-defined in terms of natural selection, and the behavior which emerged in self-replicating organisms during these experiments is described in detail.


Evolutionary Self-Replication as a Mechanism for Producing Artificial Intelligence

Over the years, there has been a rising application of artificial intelligence (AI) in computing devices, and studies have been done to develop a cost-effective and energy-efficient approach to machine learning. Advancements in computing and communication technologies have led to the creation of more advanced processors, neuromorphic computers, quantum computing technologies, as well as the increasing usage of 5G networks in the industry. Together, these not only increase the amount of processing that can be done but also the amount of data that can be transmitted at a given time.
The field of AI is becoming very broad, and several studies so far have been able to achieve very high prediction accuracy using convolutional neural networks (CNNs), which is a very popular class of deep neural networks. Neurons in CNNs constantly perform a lot of computation as data is fed into the network. The size of the network (the number of neurons) determines the amount of computation that must be performed. This uses up a lot of energy due to the high number of computations when dealing with large networks.
Spiking neural networks (SNNs) are event-based networks that make use of spikes in learning. Neurons in SNNs are designed to operate like actual biological neurons. The signals in an SNN are propagated in the form of spike trains which are a timed representation of input signals. Neurons within the network only forward propagate signals/action potentials when the neuron potential of a given neuron crosses a predefined threshold value. This implies that the number computation becomes mainly dependent on the amount of dynamic data rather than the size of the network.
Several studies have investigated different forms of collaborative learning such as federated learning, but not many have been done with Spiking Neural Networks, given that SNN learning algorithms have been a bit challenging to develop and haven’t been able to achieve very high accuracy like CNNs.
A study on spiking neural networks has investigated what could happen when weight parameters gotten by training a ReLU Multilayer Perceptron Network (ReLU MLP) model, are shared with a model gotten by training a less-performant Spiking Neural Network model of the same size. The results were an improved performance of the spiking neural network.
The purpose of this project is to investigate the improvement in the machine learning model that can be achieved by employing/simulating a swarm of client marine robots functioning on a distinct image dataset. This can be done by training different instances of a given algorithm on separate groups of datasets representing each client robot, and only updating the parameters across the group whenever any one of the clients have been able to achieve a higher prediction accuracy. This is inspired by the fact that hyperparameters learned during the training process can easily be shared with clients.
The idea behind our design is to use a more powerful computing unit on the backend to perform training while using a less powerful device on the client-side for inference. Each client in our design also has the additional responsibility of supplying data to the backend computing unit where training is done, with each client having a different repository for its dataset to ensure that the data remains distinct.


Initial work in this research has involved employing a time-based backpropagation algorithm to train our spiking neural network and fractional stochastic gradient descent for weight update. We trained our algorithm on the MNIST dataset. Results show a maximum prediction accuracy of 97.03%, on a single client.
This is ongoing research and, in the future, we intend to study the changes or improvements in prediction accuracy that can be gotten by running the training algorithm on distinct MNIST datasets and finally applying the algorithm to a real collection of marine datasets.


Non-critical Marine Application of Collaborative Learning with Spiking Neural Networks

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.

Premium content

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

Next from NAML 2022

Uncertainty Quantification in Deep Learning

Similar lecture

On the impact of MDP design for Reinforcement Learning agents in Resource Management

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES