Unifying AI Algorithms with Probabilistic Programming using Implicitly Defined Representations

Pfeffer, A., Harradon, M., Campolongo, J., and Cvijic, S. arXiv:2110.02325 (October 2021) We introduce Scruff, a new framework for developing AI systems using probabilistic programming. Scruff enables a variety of representations to be included, such as code with stochastic choices, neural networks, differential equations, and constraint systems. These representations are defined implicitly using a set […]

Towards Incorporating Artificial Intelligence in the Mission Planning Process

Kane, S., Moody, V, and Harradon, M. HCI International, Washington, DC (June 2021) While there are numerous powerful tools to support Navy mission planning, the mission planning process still remains a hybrid planning activity across human operators and advanced tools. Advances in artificial intelligence (AI) have seen an increase in interest and use in the mission planning environment.  Yet traditional […]

Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program

Druce, J.1, Niehaus, J.2, Moody, V.1, Jensen, D.2, Littman, M.3 arXiv:2106.05506v1 (June 2021) The advances in artificial intelligence enabled by deep learning architectures are undeniable. In several cases, deep neural network driven models have surpassed human level performance in benchmark autonomy tasks. The underlying policies for these agents, however, are not easily interpretable. In fact, […]

The Sociospatial Factors of Death: Analyzing Effects of Geospatially-distributed Variables in a Bayesian Mortality Model for Hong Kong

Alshaabi, T.1,2,4, Dewhurst, D.1,2,3, Bagrow, J.1,5, Dodds, P.1,2,4, Danforth, C.1,2,5 PLoS ONE 16(3): e0247795 (March 2021) Human mortality is in part a function of multiple socioeconomic factors that differ both spatially and temporally. Adjusting for other covariates, the human lifespan is positively associated with household wealth. However, the extent to which mortality in a geographical […]

SPICEs: Survey Papers as Interactive Cheat-sheet Embeddings

Prabhu, V.1, McAteer, M.2, Teehan, R.3 Rethinking ML Papers – ICLR 2021 Workshop Papers are hard to write. Survey papers are just that much harder. From the authors’ perspective, challenges include the responsibility to not erase out important work being done by (sometimes) adversarially aligned research groups, finding the right semantic clustering to sub-categorize individual contributions, […]

Development of Human-Out-of-the-Loop Participant Recruitment, Data Collection, Data Handling, and Participant Management System

Bracken, B.1, Potoczny-Jones, I.2, Wolcott, J.2, Raffaele, E.2, Woodward, L.2, Gogoel, C.3, Kiourtis, N.3, Schulte, B.3, Arean, P.4, and Farry, M.1 Proceedings of the Human Factors and Ergonomics Society Annual Meeting (February 2021) Most human subjects research requires data collection by contacting local participants who visit a research site. This is costly, time-consuming, and decreases subject retention with each required visit. Additionally, studies require increasingly […]

How the World’s Collective Attention is Being Paid to a Pandemic: COVID-19 Related n-gram Time Series for 24 Languages on Twitter

Alshaabi, T., Arnold, M., Minot, J., Adams, J., Dewhurst, D., Reagan, A., Muhamad, R., Danforth, C., and Dodds, D. PLoS ONE 16(1): e0244476 (January 2021) In confronting the global spread of the coronavirus disease COVID-19 pandemic we must have coordinated medical, operational, and political responses. In all efforts, data is crucial. Fundamentally, and in the possible absence of a vaccine for 12 […]

Structural time series grammar over variable blocks

Dewhurst, D. arXiv:2009.06865v1 (September 2020) A structural time series model additively decomposes into generative, semantically-meaningful components, each of which depends on a vector of parameters. We demonstrate that considering each generative component together with its vector of parameters as a single latent structural time series node can simplify reasoning about collections of structural time series […]

Storywrangler: A massive exploratorium for sociolinguistic, cultural, socioeconomic, and political timelines using Twitter

Alshaabi, T.1,2,3, Adams, J.1,2, Arnold, M.1,2, Minot, J.1,2, Dewhurst, D.1,2,4, Reagan, A.5, Danforth, C.1,2,3, and Sheridan Dodds, P.1,2,3 Science Advances (July 2021) In real time, Twitter strongly imprints world events, popular culture, and the day-to-day, recording an ever-growing compendium of language change. Vitally, and absent from many standard corpora such as books and news archives, […]

Continuous Cognitive Workload Assessment and Combined Metrics of Performance in the Multi-Attribute Task Battery

News Article Icon

Bracken, B.1, Endsley, M.2, Tobyne, S.1, Leather, C.1, and Farry, M.1 Presented at the 11th International Conference on Applied Human Factors and Ergonomics Conference (AHFE), San Diego, CA (July 2020) Neurophysiological correlates of cognitive workload (e.g., changes in brain blood oxygenation) are detectable with minimally-invasive wearable sensors including functional near infrared spectroscopy (fNIRS). When cognitive […]

Explainable Artificial Intelligence (XAI) for Increasing User Trust in Deep Reinforcement Learning Driven Autonomous Systems

Druce, J., Harradon, M., Tittle, J. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada We consider the problem of providing users of deep Reinforcement Learning (RL) based systems with a better understanding of when their output can be trusted. We offer an explainable artificial intelligence (XAI) framework that provides a three-fold explanation: […]

A Toolkit to Help Integrate Humans with Virtual Environments, Intelligent Simulations (FSMs), and Artificial Cognitive Systems (NPCs)

News Article Icon

Kingsley, C. and Jenkins, M. Proceedings of the 2019 Intelligent Human Systems Integration (IHSI) International Conference, San Diego, CA (February 2019) Charles River Analytics is developing an open-source, Unity-based Extended Reality (XR) SDK for development of immersive simulations, currently focused on medical simulations. Our work-to-date has focused on integrating humans into virtual environments through enhanced […]

Bot Detection: Will Focusing on Recall Cause Overall Performance Deterioration?

News Article Icon

Nazer, T.1, Davis, M.1, Karami, M.1, Akoglu, L.2, Koelle, D.3, and Liu, H.1 International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS), Washington, DC (July 2019)  Social bots are an effective tool in the arsenal of malicious actors who manipulate discussions on social media. Bots help spread misinformation, promote political […]

Bot Detection: Will Focusing on Recall Cause Overall Performance Deterioration?

News Article Icon

Nazer,T.H.1, Davis, M.1, Karami, M1, Akoglu, L.2, Koelle, D.3, and Liu, H.1 Presented at the 2019 International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS), Washington, DC (July 2019) Social bots are an effective tool in the arsenal of malicious actors who manipulate discussions on social media. Bots […]

Probabilistic Programming: Past, Present, and Future

News Article Icon

Pfeffer, A. Invited keynote at the 22nd International Conference on Information Fusion (Fusion 2019), Ottawa, Canada (July 2019)  Overview: What is Probabilistic Programming? Probabilistic Programming in Action Probabilistic Programming Inference Algorithms Probabilistic Programming for Long-Lived AI Systems Download Slides For More Information To learn more, contact Avi Pfeffer. (Please include your name, address, organization, and the […]

Software Adaptation for an Unmanned Undersea Vehicle

News Article Icon

Pfeffer, A.1, Wu, C.1, Fry, G.1, Lu, K.1, Marotta, S.1, Reposa, M.1, Shi, Y.2, Satish Kumar, T.2, Knoblock, C.2, Parker, D.3, Muhammad, I.3, and Novakovic, C.3 IEEE Software, Vol. 36, No. 2 (March/April 2019) Unmanned undersea vehicles (UUVs) are designed to carry out challenging missions in changing environments. To maximize their effectiveness, these vehicles should adapt to system failures […]

Combining Data‐Driven and Theory‐Driven Models for Causality Analysis in Sociocultural Systems

News Article Icon

Sliva, A.1, Neal Reilly, S.1, Blumstein, D.1, and Pierce, G.2 In Social-Behavioral Modeling for Complex Systems, Paul K. Davis, Angela O’Mahony, and Jonathan Pfautz (Eds) To better understand and describe sociocultural systems, it is critical that we can create, analyze, and validate social, political, and economic models that capture causal and predictive dynamics. Causality is, however, notoriously difficult […]

Privacy Preserving Neural Network Inference on Encrypted Data with GPUs

News Article Icon

Takabi, H.1, Podschwadt, R.2, Druce, J.3, Wu, C.3, and Procopio, K3. Presented at Privacy in Machine Learning, NeurIPS 2019 Workshop, Vancover, BC (December 2019) Machine Learning as a Service (MLaaS) has become a growing trend in recent years and several such services are currently offered. MLaaS is essentially a set of services that provides machine […]

Physiological Indices of Challenge and Threat: A Data-Driven Investigation of Autonomic Nervous System Reactivity During an Active Coping Stressor Task

News Article Icon

Wormwood, J.1, Khan, Z.2, Siegel, E.3,  Lynn, S.4, Dy, J.2, Barrett, K.2, and Quigley, K2. Psychophysiology (August 2019) We utilized a data‐driven, unsupervised machine learning approach to examine patterns of peripheral physiological responses during a motivated performance context across two large, independent data sets, each with multiple peripheral physiological measures. Results revealed that patterns of […]

Application of the DeepSense Deep Learning Framework to Determination of Activity Context from Smartphone Data

News Article Icon

Bracken, B., Manjunath, S., German, S., Monnier, C., and Farry, M. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Volume 63, Issue 1, Pages 792-796 (November 2019) Current methods of assessing health are infrequent, costly, and require advanced medical equipment. 92% of US adults carry mobile phones, and 77% carry smartphones with advanced sensors (Smith, 2017). […]

Spatial Degradation of Color Discrimination in Augmented Reality

News Article Icon

Flowers, B. A., Wollocko, A., Kingsley, C., Thiry, E., and Jenkins, M. 10th International Conference on Applied Human Factors and Ergonomics (AHFE 2019), Washington D.C. (July 2019) Stereoscopic Augmented Reality displays are known to degrade the color perception of users. Using a spatially-aware color matching task, we performed a repeated trial study in which participants […]

Using Sociocultural Data from Online Gaming and Game Communities

News Article Icon

Guarino, S., Eusebi, L., Bracken, B., and Jenkins, M. In Social-Behavioral Modeling for Complex Systems, Paul K. Davis, Angela O’Mahony, and Jonathan Pfautz (Eds) (April 2019) This volume describes frontiers in social-behavioral modeling for contexts as diverse as national security, health, and on-line social gaming. Recent scientific and technological advances have created exciting opportunities for such improvements. However, […]

Characterizing the Limits of Visual Field Augmentation in Augmented Reality: Psychophysical Foundations for Design and Mode Transition Acclimation Strategies

News Article Icon

Jenkins, M., Kingsley, C., and Flowers, B.A. Panel Presentation at the 22nd Annual Applied Ergonomics Conference, New Orleans, LA (March 2019) The impact of augmented reality displays on the human perceptual system will vary across headsets. Because of this, the display used for any solution should be selected with an awareness of the interaction between the […]

Automation Support using non-Invasive Measures of Operator Vocalization (ASIMOV)

Elkin-Frankston, S.1, Leather, C.1, Bracken, B.1, and van Mersbergen, M.2 To be presented at the 11th International Conference on Voice Physiology and Biomechanics (ICVPB 2018), East Lansing, MI (July 2018). Heightened states of arousal can be investigated using electroglottography (EGG) contact quotient, as well as other measures of vocalization, such as surface laryngeal electromyography (sEMG), […]

A Predicative Processing Model of Categorical Perception

Lynn, S. Presented at the 2018 International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS), Washington DC, USA (July 2018) Prior knowledge influences perception, as evidenced by categorical perception phenomena, in which expectations create psychometric distortions of perceptual space. These distortions are nonetheless associated with categorization accuracy. […]

Structured Factored Inference for Probabilistic Programming

Pfeffer, A., Ruttenberg, B., Kretschmer, W., and O’Connor, A. Presented at the 21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018), Lanzarote, Canary Islands (April 2018) Probabilistic reasoning on complex real-world models is computationally challenging. Inference algorithms have been developed that work well on specific models or on parts of general models, but they […]

Scruff: A Deep Probabilistic Cognitive Architecture

Pfeffer, A. Invited talk at the Association for the Advancement of Artificial Intelligence’s Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), New Orleans, LA (February 2018). Probabilistic programming is able to build rich models of systems that combine prior knowledge with the ability to learn from data. One of the reasons for the success of deep […]

The Support Method of Computing Expectations

Pfeffer, A. Extended abstract for the Probabilistic Program Semantics Workshop associated with the Principles of Programming Languages (POPL) conference, Los Angeles, CA (January 2018). A standard method for computing the expectation of a function on a probabilistic program is to sample values from the generative model and approximate the integral. An alternative approach is to […]

Using Reinforcement Learning for Probabilistic Program Inference

Pfeffer, A. Extended abstract for the Probabilistic Program Semantics Workshop associated with the Principles of Programming Languages (POPL) conference, Los Angeles, CA (January 2018). Inference in probabilistic programming often involves choosing between different methods. For example, one could use different algorithms to compute a conditional probability, or one could sample variables in different orders. Researchers […]

Predict and Analyze Novel and Emerging Diseases Enabled by Models of Infection Conditions

Prue, B.1, Voge, J.1, Mara, J.1, Wollocko, A.1, and Mekaru, S.2 Poster presentation at the International Conference of Human-Computer Interaction (HCII 2018), Las Vegas, NV (July 2018) Incidents of infectious disease pose serious threats to armed forces worldwide, risking the success of critical operations and the deaths of Warfighters. Force medical personnel require support to […]

Contamination and Lasting Effects Analysis for Negative Substances and Elements

Voge, J., Jacobs, P., Negri, A., and Farry, M. Poster presented at the International Conference on Applied Human Factors and Ergonomics (AHFE), Orlando, FL (July 2018). Military training facility managers are tasked with understanding and responding to the long-term effects of contaminant releases. To mitigate disastrous environmental damage to ecosystems, military training facility managers must […]

Leveraging Systemic Functional Grammars for Script Analysis and Understanding Human Behavior

Sliva, A., Call, C., and Patten, T. Presented at the 45th International Systemic Functional Congress (ISFC 2018), Boston, MA (July 2018). In sociolinguistics, it is desirable to understand not only social-functional aspects of language, but also the broader social and behavioral landscape. In psychology, script theory posits that human behavior follows discernable patterns, or “scripts,” […]

Predict and Analyze Novel and Emerging Diseases Enabled by Models of Infection Conditions

Prue, B.1, Voge, J.1, Mara, J.1, Wollocko, A.1, and Mekaru, S.2 Poster presentation at the International Conference of Human-Computer Interaction (HCII 2018), Las Vegas, NV (July 2018) Incidents of infectious disease pose serious threats to armed forces worldwide, risking the success of critical operations and the deaths of Warfighters. Force medical personnel require support to […]

Interfacing Systemic Functional Grammars with Frame Semantics

Dohmann, J.1 2, Patten, T2., Campolongo, J.2 Presented at the 45th International Systemic Functional Congress (ISFC 2018), Boston, MA (July 2018). As computational applications play a greater role in society, Systemic Functional Linguistics can play an important role in producing effective interactions between those applications and the people who use them. Significant progress has been […]

Scruff: A Deep Probabilistic Cognitive Architecture for Predictive Processing

Pfeffer, A. and Lynn, S. Biologically Inspired Cognitive Architectures 2018 The theory of predictive processing encompasses several elements that make it attractive as the underlying computational approach for a cognitive architecture. We introduce a new cognitive architecture, Scruff, capable of implementing predictive processing models by incorporating key properties of neural networks into the Bayesian probabilistic […]

Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations

Harradon, M., Druce, J., and Ruttenberg, B. arXiv:1802.00541v1 (February 2018) Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained […]

Complex Causality: Computational Formalisms, Mental Models, and Objective Truth

Dalal, M., Sliva, A., and Blumstein, D. Presented at the 7th International Conference on Cross-Cultural Decision Making at the International Conference on Applied Human Factors and Ergonomics, Los Angeles, CA (July 2017). There is a broad consensus that understanding causality is important for comprehending the world and making decisions. However, causality is notoriously difficult to understand […]

Testing the Usability of a Decision-Support System for Increasing Environmental Awareness

Danczyk, J., Jacobs, P., Montgomery, O., Jenkins, M., and Farry, M. Presented at the 2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA), Savannah, GA (March 2017) Military facility managers must track repeated contaminant release that occurs from scheduled training exercises to mitigate the effects of those releases before negative effects occur. Training […]

Automatic Differentiation Equipped Variable Elimination for Sensitivity Analysis on Probabilistic Inference Queries

Druce, J.1, Ruttenberg, B.1, Blumstein, D.1, and Scofield, D.2 Presented at the Conference on Neural Information Processing Systems (NIPS), Long Beach, CA (December 2017) Probabilistic Models are a natural framework for describing the stochastic relationships between variables in a system to perform inference tasks, such as estimating the probability of a specific set of conditions or […]

Designing a Pragmatic Graphical Grammar

Eusebi, L., and Guarino, S. Presented at the 2017 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA), Savannah, GA (March 2017) Modern adversaries have become more proficient in conducting cyberattacks against our military’s command and control (C2) infrastructure. To maintain security against these threats, operators perform a range of high-fidelity security assessments of […]

Probabilistic Model-Based Programming Techniques for Prediction, Analysis, and Control (PROMPT)

Harrison, S., Takata, G., Wu, C., and Pfeffer, A. Presented at the 15th Annual Conference on Systems Engineering Research Disciplinary Convergence: Implications for Systems Engineering Research, Redondo Beach, CA (March 2017) Model-based systems engineering (MBSE) frameworks such as SysML provide declarative descriptions of the structure, processes, functions, and context of a system. However, these frameworks do not […]

Scratchpad: Lightweight Data Capture Tools to Support Mission Planning

Kane, S., von Kelsch, E., Muller, C., and Hogan, C. Presented at the 19th International Conference on Human-Computer Interaction (HCII 2017), Vancouver, Canada (July 2017) Powerful tools are available to support the mission planning process. Although these tools provide support to multiple components, they do not support the dynamic nature of the process over time. Pilots […]

A Mission Library for Mission Plan Management

Kane, S., and von Kelsch, E. Presented at the 8th International Conference on Applied Human Factors and Ergonomics (AHFE 2017), Los Angeles, CA (July 2017) When Navy pilots create a new mission plan, they frequently build off of prior missions. Specifically, they duplicate a “master” mission plan that contains official settings, operational specifications, and other information […]

Long-Range Forecasting Using COMPASS Machine Learning

O’Connor, A.1, Bell, R.2, Kirtman, B.2, and Gorman, J.1 Presented at the 7th International Workshop of Climate Informatics hosted by the National Center for Atmospheric Research, Boulder, CO (September 2017) The Climatological Observations for Maritime Prediction and Analysis Support Service (COMPASS) uses machine learning to create long-range forecasts of the probability that future conditions will differ from […]

Probabilistic Modeling of Insider Threat Detection Systems

Ruttenberg, B.1, Blumstein, D.1, Druce, J.1, Howard, M.1, Reed, F.1, Wilfong, L.2, Lister, C.2, Gaskin, S.3, Foley, M.4, and Scofield, D.4 Presented at The Fourth International Workshop on Graphical Models for Security (GraMSec 2017), Santa Barbara, CA (August 2017) Due to the high consequences of poorly performing automated insider threat detection systems (ITDSs), it is advantageous […]

Combining Data-Driven and Theory-Driven Models for Causality Analysis in Sociocultural Systems

Sliva, A. Presented at the Current Challenges in Computing (CCubed) Conference, Napa, CA (September 2017) To better understand and describe sociocultural systems, it is critical that we can create, analyze, and validate social, political, and economic models that capture causal and predictive dynamics. Causality is, however, notoriously difficult to analyze, a challenge amplified by the complexity of […]

Techniques for Managing Stale Mission Information through Card-Based Interfaces

von Kelsch, E., Kane, S., and Muller, C. Presented at the 8th International Conference on Applied Human Factors and Ergonomics (AHFE 2017), Los Angeles, CA (July 2017) Powerful tools exist to support mission planning with complex decision making demands. However, these tools are unable to update missions with updated data or provide support for data […]

Are Behavioral Measures Useful for Detecting Cognitive Workload During Human-Computer Interaction?

Elkin-Frankston, S., Bracken, B., Irvin, S., and Jenkins, M. Presented at the 4th International Conference on Human Side of Service Engineering, taking place at the 7th International Conference on Applied Human Factors and Ergonomics (AHFE 2016),  Orlando, FL (July 2016) Commonly used techniques for measuring cognitive workload during human-computer interaction are cumbersome or intrusive to task performance. Physiological […]

SPIDER: New Technology for Constructing Sociometric Networks from Personal Network Data

Hopkins, C.1, Young, A.2,and Borgatti, S.2 Presented at the XXXVI Sunbelt Conference of the International Network for Social Network Analysis (INSNA), Newport Beach, CA (April 2016) During the past two decades, there has been a surge in the number of studies applying social network analysis (SNA) to the study of infectious disease transmission. The mapping of […]

Decision-making and Opinion Formation in Simple Networks

Leibovich1, M., Zuckerman2, I., Pfeffer3, A., and Gal4, Y. Knowledge and Information Systems, an International Journal (September 2016) In many networked decision-making settings, information about the world is distributed across multiple agents and agents’ success depends on their ability to aggregate and reason about their local information over time. This paper presents a computational model of […]

Modular Analytics Management Architecture for Interoperability and Decision Support

Marotta, S., Metzger, M., Gorman, J., and Sliva, A. Presented at SPIE Defense + Commercial Sensing, Baltimore Convention Center, Baltimore, MD (April 2016) The Dual Node Decision Wheels (DNDW) architecture is a new approach to information fusion and decision-support systems. By combining cognitive systems engineering organizational analysis tools, such as decision trees, with the Dual Node […]

Practical Probabilistic Programming

Pfeffer, A. Practical Probabilistic Programming, Manning Publications, Cherry Hill, NJ (2016) Practical Probabilistic Programming introduces the working programmer to probabilistic programming. In it, you’ll learn how to use the PP paradigm to model application domains and then express those probabilistic models in code. Although PP can seem abstract, in this book you’ll immediately work on practical examples, […]

Modeling Causality in Sociocultural Systems using Ensemble Methods

Sliva, A., Neal Reilly, S., Blumstein, D., Hookway, S., and Chamberlain, J. Presented at the 7th International Conference on Applied Human Factors and Ergonomics (AHFE 2016), Orlando, FL (July 2016) Awarded Best Paper at AHFE’s Cross-Cultural Decision-Making Conference When planning operations or designing policy interventions, military decision-makers and policy experts must have an understanding of the world […]

CAML: Machine Learning-based Predictable, System-Level Anomaly Detection

Song1, J., Fry2, G., Wu2, C., and Parmer1, G. 1st Workshop on Security and Dependability of Critical Embedded Real-Time Systems, in conjunction with IEEE Real-Time Systems Symposium, Porto, Portugal  (November 2016). Security challenges are increasing in distributed cyber-physical systems (CPSs), which integrate computation and physical processes. System security is complicated by both the temporal and safety […]

Laser Vibrometry Target Recognition Enhancement Using an Analytical Researcher’s Workbench

Stouch, D.     In Proceedings of the 2017 Military Sensing Symposium (MSS) Active Electro-Optical Systems Symposium, Gaithersberg, MD (September 2016). For More Information To learn more or request a copy of a paper (if available), contact Daniel Stouch. (Please include your name, address, organization, and the paper reference. Requests without this information will not be […]