Publications

Refine Results

(Filters Applied) Clear All

Fast training of deep neural networks robust to adversarial perturbations

Summary

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their learned feature representations are often difficult to interpret, raising concerns about their true capability and trustworthiness. Recent work in adversarial training, a form of robust optimization in which the model is optimized against adversarial examples, demonstrates the ability to improve performance sensitivities to perturbations and yield feature representations that are more interpretable. Adversarial training, however, comes with an increased computational cost over that of standard (i.e., nonrobust) training, rendering it impractical for use in largescale problems. Recent work suggests that a fast approximation to adversarial training shows promise for reducing training time and maintaining robustness in the presence of perturbations bounded by the infinity norm. In this work, we demonstrate that this approach extends to the Euclidean norm and preserves the human-aligned feature representations that are common for robust models. Additionally, we show that using a distributed training scheme can further reduce the time to train robust deep networks. Fast adversarial training is a promising approach that will provide increased security and explainability in machine learning applications for which robust optimization was previously thought to be impractical.
READ LESS

Summary

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their learned feature representations are often difficult to interpret, raising concerns about their true capability and trustworthiness. Recent...

READ MORE

Safe predictors for enforcing input-output specifications [e-print]

Summary

We present an approach for designing correct-by-construction neural networks (and other machine learning models) that are guaranteed to be consistent with a collection of input-output specifications before, during, and after algorithm training. Our method involves designing a constrained predictor for each set of compatible constraints, and combining them safely via a convex combination of their predictions. We demonstrate our approach on synthetic datasets and an aircraft collision avoidance problem.
READ LESS

Summary

We present an approach for designing correct-by-construction neural networks (and other machine learning models) that are guaranteed to be consistent with a collection of input-output specifications before, during, and after algorithm training. Our method involves designing a constrained predictor for each set of compatible constraints, and combining them safely via...

READ MORE

AI enabling technologies: a survey

Summary

Artificial Intelligence (AI) has the opportunity to revolutionize the way the United States Department of Defense (DoD) and Intelligence Community (IC) address the challenges of evolving threats, data deluge, and rapid courses of action. Developing an end-to-end artificial intelligence system involves parallel development of different pieces that must work together in order to provide capabilities that can be used by decision makers, warfighters and analysts. These pieces include data collection, data conditioning, algorithms, computing, robust artificial intelligence, and human-machine teaming. While much of the popular press today surrounds advances in algorithms and computing, most modern AI systems leverage advances across numerous different fields. Further, while certain components may not be as visible to end-users as others, our experience has shown that each of these interrelated components play a major role in the success or failure of an AI system. This article is meant to highlight many of these technologies that are involved in an end-to-end AI system. The goal of this article is to provide readers with an overview of terminology, technical details and recent highlights from academia, industry and government. Where possible, we indicate relevant resources that can be used for further reading and understanding.
READ LESS

Summary

Artificial Intelligence (AI) has the opportunity to revolutionize the way the United States Department of Defense (DoD) and Intelligence Community (IC) address the challenges of evolving threats, data deluge, and rapid courses of action. Developing an end-to-end artificial intelligence system involves parallel development of different pieces that must work together...

READ MORE

Human-machine collaborative optimization via apprenticeship scheduling

Summary

Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years of apprenticeship. A process for manually codifying this domain knowledge within a computational framework is necessary to scale beyond the "single-expert, single-trainee" apprenticeship model. However, human domain experts often have difficulty describing their decision-making processes. We propose a new approach for capturing this decision-making process through counterfactual reasoning in pairwise comparisons. Our approach is model-free and does not require iterating through the state space. We demonstrate that this approach accurately learns multifaceted heuristics on a synthetic and real world data sets. We also demonstrate that policies learned from human scheduling demonstration via apprenticeship learning can substantially improve the efficiency of schedule optimization. We employ this human-machine collaborative optimization technique on a variant of the weapon-to-target assignment problem. We demonstrate that this technique generates optimal solutions up to 9.5 times faster than a state-of-the-art optimization algorithm.
READ LESS

Summary

Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years of apprenticeship. A process for manually codifying this domain knowledge within a computational framework is necessary to scale...

READ MORE

A cloud-based brain connectivity analysis tool

Summary

With advances in high throughput brain imaging at the cellular and sub-cellular level, there is growing demand for platforms that can support high performance, large-scale brain data processing and analysis. In this paper, we present a novel pipeline that combines Accumulo, D4M, geohashing, and parallel programming to manage large-scale neuron connectivity graphs in a cloud environment. Our brain connectivity graph is represented using vertices (fiber start/end nodes), edges (fiber tracks), and the 3D coordinates of the fiber tracks. For optimal performance, we take the hybrid approach of storing vertices and edges in Accumulo and saving the fiber track 3D coordinates in flat files. Accumulo database operations offer low latency on sparse queries while flat files offer high throughput for storing, querying, and analyzing bulk data. We evaluated our pipeline by using 250 gigabytes of mouse neuron connectivity data. Benchmarking experiments on retrieving vertices and edges from Accumulo demonstrate that we can achieve 1-2 orders of magnitude speedup in retrieval time when compared to the same operation from traditional flat files. The implementation of graph analytics such as Breadth First Search using Accumulo and D4M offers consistent good performance regardless of data size and density, thus is scalable to very large dataset. Indexing of neuron subvolumes is simple and logical with geohashing-based binary tree encoding. This hybrid data management backend is used to drive an interactive web-based 3D graphical user interface, where users can examine the 3D connectivity map in a Google Map-like viewer. Our pipeline is scalable and extensible to other data modalities.
READ LESS

Summary

With advances in high throughput brain imaging at the cellular and sub-cellular level, there is growing demand for platforms that can support high performance, large-scale brain data processing and analysis. In this paper, we present a novel pipeline that combines Accumulo, D4M, geohashing, and parallel programming to manage large-scale neuron...

READ MORE

Learning to tutor from expert demonstrators via apprenticeship scheduling

Published in:
AAAI-17 Workshop on Human-Machine Collaborative Learning, 4 February 2017.

Summary

We have conducted a study investigating the use of automated tutors for educating players in the context of serious gaming (i.e., game designed as a professional training tool). Historically, researchers and practitioners have developed automated tutors through a process of manually codifying domain knowledge and translating that into a human-interpretable format. This process is laborious and leaves much to be desired. Instead, we seek to apply novel machine learning techniques to, first, learn a model from domain experts' demonstrations how to solve such problems, and, second, use this model to teach novices how to think like experts. In this work, we present a study comparing the performance of an automated and a traditional, manually-constructed tutor. To our knowledge, this is the first investigation using learning from demonstration techniques to learn from experts and use that knowledge to teach novices.
READ LESS

Summary

We have conducted a study investigating the use of automated tutors for educating players in the context of serious gaming (i.e., game designed as a professional training tool). Historically, researchers and practitioners have developed automated tutors through a process of manually codifying domain knowledge and translating that into a human-interpretable...

READ MORE

Apprenticeship scheduling: learning to schedule from human experts

Published in:
Proc. of the Int. Joint Conf. Artificial Intelligence (IJCAI), 9-15 July 2016.

Summary

Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years of apprenticeship. A process for manually codifying this domain knowledge within a computational framework is necessary to scale beyond the "single expert, single-trainee" apprenticeship model. However, human domain experts often have difficulty describing their decision-making processes, causing the codification of this knowledge to become laborious. We propose a new approach for capturing domain-expert heuristics through a pairwise ranking formulation. Our approach is model-free and does not require enumerating or iterating through a large state-space. We empirically demonstrate that this approach accurately learns multifaceted heuristics on both a synthetic data set incorporating job-shop scheduling and vehicle routing problems and a real-world data set consisting of demonstrations of experts solving a weapon-to-target assignment problem.
READ LESS

Summary

Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years of apprenticeship. A process for manually codifying this domain knowledge within a computational framework is necessary to scale...

READ MORE

Comparisons between the extended Kalman filter and the state-dependent Riccati estimator

Summary

The state-dependent Riccati equation-based estimator is becoming a popular estimation tool for nonlinear systems since it does not use system linearization. In this paper, the state-dependent Riccati equation-based estimator is compared with the widely used extended Kalman filter for three simple examples that appear in the open literature. It is demonstrated that, by simulation, the state-dependent Riccati equation-based estimator at best has comparable results to the extended Kalman filter but is often worse than the extended Kalman filter. In some cases, the state-dependent Riccati equation-based estimator does not converge, even though the system considered satisfies all the mathematical constraints on controllability and observability. Sufficient detail is presented in the paper so that the interested reader cannot only duplicate the results but perhaps make suggestions on how to get the state-dependent Riccati equation-based estimator to perform better.
READ LESS

Summary

The state-dependent Riccati equation-based estimator is becoming a popular estimation tool for nonlinear systems since it does not use system linearization. In this paper, the state-dependent Riccati equation-based estimator is compared with the widely used extended Kalman filter for three simple examples that appear in the open literature. It is...

READ MORE

Geospatial analysis based on GIS integrated with LADAR

Summary

In this work, we describe multi-layered analyses of a high-resolution broad-area LADAR data set in support of expeditionary activities. High-level features are extracted from the LADAR data, such as the presence and location of buildings and cars, and then these features are used to populate a GIS (geographic information system) tool. We also apply line-of-sight (LOS) analysis to develop a path-planning module. Finally, visualization is addressed and enhanced with a gesture-based control system that allows the user to navigate through the enhanced data set in a virtual immersive experience. This work has operational applications including military, security, disaster relief, and task-based robotic path planning.
READ LESS

Summary

In this work, we describe multi-layered analyses of a high-resolution broad-area LADAR data set in support of expeditionary activities. High-level features are extracted from the LADAR data, such as the presence and location of buildings and cars, and then these features are used to populate a GIS (geographic information system)...

READ MORE

Distributed multi-modal sensor system for searching a foliage-covered region

Summary

We designed and constructed a system that includes aircraft, ground vehicles, and throwable sensors to search a semiforested region that was partially covered by foliage. The system contained 4 radio-controlled (RC) trucks, 2 aircraft, and 30 SensorMotes (throwable sensors). We also investigated communications links, search strategies, and system architecture. Our system is designed to be low-cost, contain a variety of sensors, and distributed so that the system is robust even if individual components are lost.
READ LESS

Summary

We designed and constructed a system that includes aircraft, ground vehicles, and throwable sensors to search a semiforested region that was partially covered by foliage. The system contained 4 radio-controlled (RC) trucks, 2 aircraft, and 30 SensorMotes (throwable sensors). We also investigated communications links, search strategies, and system architecture. Our...

READ MORE

Showing Results

1-10 of 13