Search NASA⌕ Search

SEARCH · Search NASA

Results for “Explanability”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

Reevaluation of spin-dependent WIMP-proton interactions as an explanation of the DAMA data

We reexamine the interpretation of the annual modulation signal observed by the DAMA experiment as due to WIMPs with a spin-dependent coupling mostly to protons. We consider both axial-vector and pseudo-scalar couplings, and elastic as well as endothermic and exothermic inelastic scattering. We conclude that the DAMA signal is in strong tension with null results of other direct detection experiments, particularly PICASSO and KIMS.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

HELIUM SHELL DETONATIONS ON LOW-MASS WHITE DWARFS AS A POSSIBLE EXPLANATION FOR SN 2005E

Recently, several Type Ib supernovae (SNe; with the prototypical SN 2005E) have been shown to have atypical properties. These SNe are faint (absolute peak magnitude of {approx} - 15) and fast SNe that show unique composition. They are inferred to have low ejecta mass (a few tenths of a solar mass) and to be highly enriched in calcium, but poor in silicon elements and nickel. These SNe were therefore suggested to belong to a new class of calcium-rich faint SNe explosions. Their properties were proposed to be the result of helium detonations that may occur on helium accreting white dwarfs. In this paper, we theoretically study the scenario of helium detonations and focus on the results of detonations in accreted helium layers on low-mass carbon-oxygen (CO) cores. We present new results from one-dimensional simulations of such explosions, including their light curves and spectra. We find that when the density of the helium layer is low enough the helium detonation produces large amounts of intermediate elements, such as calcium and titanium, together with a large amount of unburnt helium. Alternatively, enough carbon enrichment of the accreted helium as a result of convective undershoot at the early stages of the runaway can avoid the production of iron group elements as the alpha particles are consumed avoiding iron production. Our results suggest that the properties of calcium-rich faint SNe could indeed be consistent with the helium-detonation scenario on small CO cores. Above a certain density (larger CO cores) the detonation leaves mainly {sup 56}Ni and unburnt helium, and the predicted spectrum will unlikely fit the unique features of this class of SNe. Finally, none of our studied models reproduces the bright, fast-evolving light curves of another type of peculiar SNe suggested to originate in helium detonations (SNe 1885A, 1939B, and 2002bj).

79 ASTRONOMY AND ASTROPHYSICS↗

A possible explanation of low energy γ-ray excess from galactic centre and Fermi bubble by a Dark Matter model with two real scalars

We promote the idea of multi-component Dark Matter (DM) to explain results from both direct and indirect detection experiments. In these models as contribution of each DM candidate to relic abundance is summed up to meet WMAP/Planck measurements of Ω{sub DM}, these candidates have larger annihilation cross-sections compared to the single-component DM models. We illustrate this fact by introducing an extra scalar to the popular single real scalar DM model. We also present detailed calculations for the vacuum stability bounds, perturbative unitarity and triviality constraints on this model. As direct detection experimental results still show some conflict, we kept our options open, discussing different scenarios with different DM mass zones. In the framework of our model we make an interesting observation: the existing direct detection experiments like CDMS II, CoGeNT, CRESST II, XENON 100 or LUX together with the observation of excess low energy γ-ray from galactic centre and Fermi bubble by Fermi Gamma-ray Space Telescope (FGST) already have the capability to distinguish between different DM halo profiles.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Explanation of Dijet Asymmetry in Pb-Pb Collisions at the Large Hadron Collider

We investigate the medium modification of a partonic jet shower traversing in a hot quark-gluon plasma. We derive and solve a differential equation that governs the evolution of the radiated gluon distribution as the jet propagates through the medium. Energy contained inside the jet cone is lost by dissipation through elastic collisions with the medium and by scattering of shower partons to larger angles. We find that the jet energy loss at early times is dominated by medium effects on the vacuum radiation, and by medium-induced radiation effects at late times. We compare our numerical results for the nuclear modification of the dijet asymmetry with that recently reported by the ATLAS Collaboration.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Technicolor Explanation for the CDF Wjj Excess

We propose that the 3.2{sigma} excess at {approx}150 GeV in the dijet mass spectrum of W+jets reported by CDF is the technipion {pi}{sub T} of low-scale technicolor. Its relatively large cross section is due to production of a narrow Wjj resonance, the technirho, which decays to W{pi}{sub T}. We discuss ways to enhance and strengthen the technicolor hypothesis and suggest companion searches at the Tevatron and LHC.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Simple explanations and reasoning: From philosophy of science to expert systems

A preliminary prototype of a simple explanation system was constructed. Although the system, based on the idea of storytelling, did not incorporate all of the principles of simple explanation, it did demonstrate the potential of the approach. The system incorporated a hypertext system, an inference engine, and facilities for constructing contrast type explanations. The continued development of such a system should prove to be valuable. By extending the resources of the expert system paradigm, the knowledge engineer is not forced to learn a new set of skills, and the domain knowledge already acquired by him is not lost. Further, both the beginning user and the more advanced user can be accommodated. For the beginning user, corrective explanations and ES explanations provide facilities for more clearly understanding the way in which the system is functioning. For the more advanced user, the instance and state explanations allow him to focus on the issues at hand. The simple model of explanation attempts to exploit and show how the why and how facilities of the expert system paradigm can be extended by attending to the pragmatics of explanation and adding texture to the ordinary pattern of reasoning in a rule based system.

Rochowiak, Daniel↗

How Do Visual Explanations Foster End Users' Appropriate Trust in Machine Learning?

We investigated the effects of different visual explanations on users' trust in machine learning classification. We proposed three forms of visual explanations of a classification based on identifying relevant training instances. We conducted a user study to evaluate these visual explanations as well as a no explanation condition. We measured users' trust of a classifier, quantified the effects of these three forms of explanations, and assessed the changes in users' trust. We found that participants trust a classifier appropriately when an explanation is available. The combination of human, classification algorithm and understandable explanation makes better decisions than the classifier and human alone.This work advances the state-of-the-art closer to building trust-able machine learning models and informs the design and appropriate use of automated systems.

Yang, Fumeng↗

Development of the Delphi display concept for alternative explanations decision making support - 120

Human operators of advanced technology systems, such as nuclear power, command and control, and deepwater oil drilling, must be able to evaluate and respond to a wide array of operational anomalies. Unfortunately, these circumstances are often complex and ambiguous, complicating decision making tasks. One common decision making error, called confirmation bias, occurs when decision makers prematurely focus on one explanation instead of systematically considering all plausible alternative explanations that could equally well account for an operational anomaly (Nickerson, 1998). The Delphi display is designed to counteract decision makers' tendencies towards confirmation bias and to encourage them to consider all plausible explanations, including high risk explanations, they might otherwise overlook. An initial Delphi display prototype was designed to help identify the underlying cause of operational anomalies in the complex, high-consequence technology of deepwater drilling. This prototype decision aid incorporates major indicators related to operational anomalies and presents corresponding plausible explanations for each indicator, ranging from high-risk system-critical explanations to lower-risk but still significant events. The Delphi display incorporates several innovative features to help decision makers detect and monitor operational anomalies and view the relationships among indicators and their associated plausible explanations. Preliminary evaluations of an early prototype Delphi display for detecting kicks in deepwater oil drilling operations have been promising. Moreover, the methodology used to design and develop the Delphi display can be readily generalized to numerous other operational contexts that require humans to make system-critical decisions. To illustrate, an initial Delphi display design for nuclear power plant control is described. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Explanation production by expert planners

Although the explanation capability of expert systems is usually listed as one of the distinguishing characteristics of these systems, the explanation facilities of most existing systems are quite primitive. Computer generated explanations are typically produced from canned text or by direct translation of the knowledge structures. Explanations produced in this manner bear little resemblance to those produced by humans for similar tasks. The focus of our research in explanation is the production of justifications for decisions by expert planning systems. An analysis of justifications written by people for planning tasks has been taken as the starting point. The purpose of this analysis is two-fold. First, analysis of the information content of the justifications will provide a basis for deciding what knowledge must be represented if human-like justifications are to be produced. Second, an analysis of the textual organization of the justifications will be used in the development of a mechanism for selecting and organizing the knowledge to be included in a computer-produced explanation. This paper describes a preliminary analysis done of justifications written by people for a planning task. It is clear that these justifications differ significantly from those that would be produced by an expert system by tracing the firing of production rules. The results from the text analysis have been used to develop an augmented phrase structured grammar (APSG) describing the organization of the justifications. The grammar was designed to provide a computationally feasible method for determining textual organization that will allow the necessary information to be communicated in a cohesive manner.

Bridges, Susan↗

Improving the explanation capabilities of advisory systems

A major limitation of current advisory systems (e.g., intelligent tutoring systems and expert systems) is their restricted ability to give explanations. The goal of our research is to develop and evaluate a flexible explanation facility, one that can dynamically generate responses to questions not anticipated by the system's designers and that can tailor these responses to individual users. To achieve this flexibility, we are developing a large knowledge base, a viewpoint construction facility, and a modeling facility. In the long term we plan to build and evaluate advisory systems with flexible explanation facilities for scientists in numerous domains. In the short term, we are focusing on a single complex domain in biological science, and we are working toward two important milestones: (1) building and evaluating an advisory system with a flexible explanation facility for freshman-level students studying biology, and (2) developing general methods and tools for building similar explanation facilities in other domains.

Porter, Bruce↗

Improving the explanation capabilities of advisory systems

A major limitation of current advisory systems (e.g., intelligent tutoring systems and expert systems) is their restricted ability to give explanations. The goal of our research is to develop and evaluate a flexible explanation facility, one that can dynamically generate responses to questions not anticipated by the system's designers and that can tailor these responses to individual users. To achieve this flexibility, we are developing a large knowledge base, a viewpoint construction facility, and a modeling facility. In the long term we plan to build and evaluate advisory systems with flexible explanation facilities for scientists in numerous domains. In the short term, we are focusing on a single complex domain in biological science, and we are working toward two important milestones: (1) building and evaluating an advisory system with a flexible explanation facility for freshman-level students studying biology; and (2) developing general methods and tools for building similar explanation facilities in other domains.

Porter, Bruce↗

A human-in-the-loop explanation framework for morphologically transparent AI predictions from whole-slide images

Deep learning models enable the prediction of clinical endpoints from whole-slide images (WSIs), but many such models function as “black boxes”, lacking transparency about whether and which histomorphological patterns drive their predictions, hindering interpretability and clinical adoption. Here we propose a human-in-the-loop explanation framework, MorphoXAI, which provides both local and global interpretability for deep learning models by incorporating human-expert interpretations. At the global level, it reveals the histomorphological patterns on which the model consistently relies to distinguish between classes of WSIs, as well as the patterns associated with confusion between classes. At the local level, it indicates which of these patterns are used in the prediction of an individual WSI and which regions within the slide correspond to such patterns. We validated our method across multiple deep learning–based WSI analysis tasks spanning different tissue types. The results show that our framework generates explanations that accurately reflect the histomorphology underlying the model’s predictions at both global and local levels. For interpretability and clinical utility in diagnostic contexts, human evaluation results showed that our explanations were easy to interpret, rich in diagnostic features, and directly helpful for diagnostic decision-making, thereby enhancing pathologist-AI collaboration. Our work highlights that unifying global and local explanations and grounding them in expert-interpreted morphology enhances the interpretability and verifiability of deep learning models, thereby facilitating the transparent deployment of such models in clinical practice.

Lou, Peiliang↗

An architecture for rule based system explanation

A system architecture is presented which incorporate both graphics and text into explanations provided by rule based expert systems. This architecture facilitates explanation of the knowledge base content, the control strategies employed by the system, and the conclusions made by the system. The suggested approach combines hypermedia and inference engine capabilities. Advantages include: closer integration of user interface, explanation system, and knowledge base; the ability to embed links to deeper knowledge underlying the compiled knowledge used in the knowledge base; and allowing for more direct control of explanation depth and duration by the user. User models are suggested to control the type, amount, and order of information presented.

Fennel, T. R.↗