United States

The performance of CPU-based and GPU- based systems is often low for PDE codes, where large, sparse, and often structured systems of linear equations must be solved. Iterative solvers are limited by data movement, both between caches and memory and between nodes. Here we describe the solution of such systems of equations on the Cerebras Systems CS-1, a wafer-scale processor that has the memory bandwidth and communication latency to perform well. We achieve 0.86 PFLOPS on a single wafer-scale system for the solution by BiCGStab of a linear system arising from a 7-point finite difference stencil on a 600 × 595 × 1536 mesh, achieving about one third of the machine’s peak performance. We explain the system, its architecture and programming, and its performance on this problem and related problems. We discuss issues of memory capacity and floating point precision. We outline plans to extend this work towards full applications. 


NAML 2021

Fast Stencil-Code Computation on a Wafer-Scale Processor

linear solvers

biconjugate gradient method

machine 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>

poster

Radio Modulation classification (RMC) is an important front-end step in a number of applications such as Signals Intelligence, spectrum monitoring, link adaptation, dynamic spectrum access, cognitive radio and 4G/5G cellular standards. We report on an RMC method which uses a novel multi-channel Time-Series Imaging input to a hybrid Residual CNN-BiLSTM Deep Neural Network. Training and testing on the RadioML 2018.01A 24-class dataset shows a peak accuracy of 96% at the highest SNRs and improvement at lower SNRs using the hybrid architecture. A new amateur radio satellite downlink collection effort for a modulation classification dataset with naturally varying SNR, Doppler shift and various bit rates will also be discussed.

Deep Neural Network Modulation Classification

As tech giants are advancing for gaining quantum supremacy, quantum technologies are becoming more and more prominent in different parts of the world, with applications that include the military sector. Promising applications, such as quantum machine learning, are starting to establish as fields of their own. Much like classical machine learning, the goal is to be able to generalize a process into multiple applications, but a deeper question remains as to whether there is computational advantage against classical processes via quantum-inspired algorithms; common ways to find such advantages involves proving that there is no best known classical algorithm that performs more efficiently than a quantum algorithm, and processing wise that there exists a runtime exponential advantage over classical computing [1]. While proving quantum advantage and supremacy is controversial and non-trivial, an additional challenge lies in the processing limitation imposed by currently available quantum computers, often referred to as Noisy Intermediate Scale Quantum (NISQ) processors [2]. As a result, it is widely accepted in academia and industry that there is not much advantage over classical processors given the current technological readiness of available quantum processors due to noise and quantum bits qubit de-coherence limiting the number of qubits and gate operations. These are some avenues to continue advancing the paradigm of quantum machine learning applications acknowledging hardware limitations: 1) theoretical explorations are done to demonstrate, via computational complexity theory, implementations that could get attained in the future once a fault-tolerant quantum computer becomes available, 2) via hybrid instances where some machine learning tasks are managed by a quantum computer while a classical processor takes the rest, such that, quantum machine learning algorithms are used to classify quantum states that are produced by a quantum simulator, and 3) programming a NISQ computer and assessing its quantum algorithm performance against a classical processor counterpart [3]. 
In this talk, we will discuss the challenges for implementing machine learning on NISQ computers and provide insight into what can be achieved accounting for present day hardware limitations. 
REERENCES
[1] Nielsen, Micheal A., and Issac L Chuang. Quantum Computation and Quantum Information. Cambridge: Cambridge University Press, 2000.
[2] Preskill, J. Quantum computing in the NISQ era and beyond. Quantum 2, 79, 2018.
[3] Schuld, Maria, and F. Petruccione. Supervised Learning with Quantum Computers. 1st ed. 2018. Cham: Springer International Publishing, 2018.


Promises And Challenges For Implementing Machine Learning On Noisy Intermediate Scale (NISQ) Computers

Knowledge graphs, or node-edge graphs representing entities and relationships are fundamental to a wide variety of cutting-edge Natural Language Processing (NLP) tasks including search, question-answering, salience determination, slot-filling, and event schema induction. Such tasks enable advanced analytics that allow users to derive new, meaningful insights about their data and are particularly useful in the realm of Big Data. Google’s Knowledge Graph, for example, forms the backbone of its search engine, enabling Google to make more intelligent inferences about results relevant to user queries. Knowledge graphs and their associated NLP tasks are widely applicable to large Navy text corpora including Navy missile standards documents, instrument logs, and cybersecurity and safety policy documents. 

The goal of this project is to build a Natural Language Processing (NLP) pipeline capable of ingesting a corpus of documents and automatically creating a Knowledge Graph containing the entities and relationships in the corpus. We are constructing an end-to-end pipeline composed of six modules: Coreference Resolution, Open Information Extraction, Canonicalization, Entity Linking, a Neo4j Graph Database, and a Graphical User Interface (GUI). 

We first perform Coreference Resolution (AllenNLP) on the corpus to create a single term for all expressions that refer to the same entity. We then extract all subject-predicate-object triplets using Open Information Extraction models by Stanford, AllenNLP, and the University of Washington and IIT Delhi; currently the user can choose a single model or a combination of models. Next we map each name to a canonical form, by clustering entities via cosine similarity, Jaccard similarity, or inverse document frequency. We then link our entities to existing entities with the same names in a pre-constructed knowledge base (KB), in effect ingesting all knowledge contained in the KB. Finally, we load the processed subject-predicate-object triplets into a Neo4j graph database, accessible to users via our GUI. 
The GUI provides an interface through which users can input text data, either by uploading files or typing raw text, choose pipeline modules to include and models and thresholds to use, query the database, run advanced analytics, produce interactive graph visualizations, and save data and visualizations. 

Through the aforementioned six modules, our project is an end-to-end pipeline of state-of-the-art methods for converting unstructured text data into a structured Knowledge Graph. 


Automated Knowledge Graphs

There is a critical need within the military to be able to identify outbreaks of communicable diseases early in order to be able to contain, mitigate, or track their spread. This is especially true when soldiers and personnel have to be kept in close quarters on a ship or in barracks. Wearable health monitoring devices provide the capability to record a variety of real time physiological time series data including, but not limited to: respiratory rate, respiratory rate variability, heart rate, steps, calorie intake and state of mind (or mental activity level). We hypothesize that these physiological measures may be used to predict the health status of individuals over the course of an acute respiratory infection (ARI) from healthy, infected, pre-symptomatic, symptomatic, and recovered. To test this hypothesis, we are using data collected using Spire HealthTag devices that were deployed during a community cohort contact tracing study conducted by the University of Maryland during the 2018-2019 influenza season. The objective of this study is to use the wearable data to predict the onset of acute respiratory infections due to viruses such as parainfluenza, coronavirus, adenovirus, influenza, and rhinovirus. We are using methods in time series analysis, topological data analysis, machine learning, and anomaly detection to develop predictors that link physiological variables collected from the Spire HealthTag device to disease onset based on perceived symptom scores and confirmed infections. A model being developed and its performance in predicting the onset of ARIs will be presented.

Learning Objectives

1. Understand the potential of wearable health data to predict the onset of illness.
2. Describe the model and our analytic approach.
3. Discuss this potential health monitoring system’s use in the field.

Predicting of Health Status from Wearable Physiological Monitoring Data (PreMonData)

PMW/ISEA teams are dealing with thousands of trouble tickets on a daily basis – currently the process is reliant on sailors or help desk self-assessing issue severity​. CASREP Prediction Model was develop to predict which Trouble Tickets are most likely to escalate into a CASREP or will take longer to resolve. This allows immediate identification of high-risk issues as soon as the trouble ticket is submitted. Enables team to prioritize response actions and resources, and potentially reduce system downtime. CASREP Prediction Model uses NAVWAR Help Desk ITSM data and five different AI/ML algorithms to work together to boost accuracy. 

The Trouble Ticket Duration model builds upon the framework of the CASREP Prediction Model but with the focus on predicting how long until a trouble ticket will be resolved. The Fleet will be potentially able to forecast downtime and adjust operational plans to compensate effectively. The PMW/ISEA teams are potentially able to use the forecast to prioritize tasking in resolving these trouble tickets.



Using Machine Learning to Predict CASREP Occurrence and Trouble Ticket Duration

Create synchronized data to train a machine learning algorithm to esimate turbulence in image data.

Atmospheric Turbulence Estimation from Degraded Image Data

We present several algorithms for vehicle routing problems that involve coordinated operations with a ground vehicle and a collection of drones.

Algorithms for drone-assisted mission planning problems

Patent pending for this big data collection and cleaning process. The sample data includes engineered features through various Navy databases. The data is then modeled in several predictive analytics algorithms, to include error metrics, training, and test sets. This then produces a list of submarine equipment needed to deploy that are forecasted to go obsolete in the next five years. These visual analytics are used by system leads and analysts to procure or prevent any shortfall. In turn, this encourages proactive triggers and money-savings for the fleet.

Forecasting Obsolescence Model Optimization

Recognizing that “garbage in” leads to “garbage out,” many organizations that employ machine learning and other types of data analytics strive for a zero-defect data ingestion process. While these efforts are critical, they are not infallible. Therefore, programs should adopt a multi-layered approach to risk management that includes mitigation plans for addressing issues that occur after faulty data has corrupted data analytic efforts and potentially influenced program-level decisions.

The impetus for what would become the Quality Risk Management Framework was a planned change to an analytics environment’s data ingestion process. The authors realized that the upcoming changes would likely increase the risks relating to data management. The authors also realized that these risks might not be discovered until after that faulty data had been used in subsequent analysis and decision support efforts, including those that may impact the safety of personnel. With these potential issues in mind, the authors performed a literature review in the hopes of finding an existing framework that addressed their concerns. While the review did not uncover a suitable framework, it did uncover elements that the authors would later incorporate into their Quality Risk Management Framework.

The authors’ resulting framework takes the form of a matrix where the columns relate to six quality dimensions and the rows relate to the six phases of the intelligence lifecycle. Using this matrix, the authors were able to identify 36 unique areas where quality risks could arise. Then, the authors developed mitigation plans for each area of potential danger. With these mitigation plans established, the authors are confident their program will be able to rapidly respond to the discovery of a quality issue regardless of when the program discovers it.

What if we were wrong? – Creating and Applying a Quality Risk Management Framework

Over the years, the use of data throughout the V-22 Osprey program steadily grew. Initially, automated software analyzed flight data to inform maintenance decisions. A few years later, analysts mined maintenance data to inform program-level decisions. Then, a few years after that, analysts leveraged artificial intelligence and machine learning on dozens of different V-22 data sets to gain deep insights on aircraft readiness. While each of the three program areas described above was successful, their roadmaps and maturation plans were independent until now. This presentation describes how overlaying a decision framework on the “big picture” enabled system-level optimization of the formerly siloed initiatives.

In the 1950s, John Boyd, an instructor at the Air Force’s Fighter Weapons School, realized that the pilot who made decisions faster than his opponent would win the aerial dogfight. Studying this further, Boyd realized that decision-making was a continual progression through four activities: observe, orient, decide, and act. Boyd subsequently named this decision-making process the OODA Loop. When the authors of this presentation took a system-level view of the V-22 maintenance support infrastructure, they discovered those same four elements were also critical factors in their program's success. They also realized, as did Boyd, that their goal should be to get through the decision-making cycle as quickly as possible.

With this system-level view and a goal of optimizing the OODA Loop, the authors examined the existing technologies and capabilities supporting each of the four decision-making activities. Next, they identified what was necessary to accelerate the program’s progression through the OODA Loop. Then, they set out to fill those gaps. As these new capabilities are introduced, the program’s decision-making system will become increasingly optimized. As a result, the V-22 program will gain maximum benefit from its machine learning and other data analytic efforts.

Fast Stencil-Code Computation on a Wafer-Scale Processor

Next from NAML 2021

Deep Neural Network Modulation Classification

Similar lecture

Neural Arrays for Autonomous Electronic Support

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES