SEARCH · Search NASA

Results for “learnability”

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.

SourceResearch connectionFrom yearThrough year

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

13 records

All sources NASA NTRS DOE OSTI

NASA NTRS1997

Learnability of Red-Green Opponency

Lennie, Haake, and Williams found that in the lateral geniculate nucleus (LGN), parvocellular unit responses are consistent with the hypothesis that their input connectivity is blind to the difference between middle-wavelength-sensitive (MWS) and long-wavelength-sensitive (LWS) cones. Most of their cells have a total MWS input weight opposite in sign and similar in magnitude to their total LWS input weight. If these weights are exactly balanced, the construction of a red-green opponent system from such units is simple: such units need only be aligned so the signs of their outputs agree. Ahumada and Mulligan described an associative learning process which can accomplish this alignment. If the units are not balanced (carry some luminance information), the strong overlap between the MWS and LWS spectral responses can cause units to agree more on the basis of luminance, and the associative process fails to produce red-green opponency. The learning theory requires that the LGN units be nearly balanced (more strongly encode chromaticity than luminance) and quantitatively expresses the requirement: the principal component of the LGN outputs must be in the red-green rather than the luminance direction. We show that the cone weights of the monkey LGN cells measured by Derrington, Krauskopf, and Lennie can satisfy this learnability criterion even if the MWS spectral response is close to the LWS spectral response, simulating anomalous trichromacy. The learnability theory provides a source of visual system variation for explaining why different anomalous trichromats may make the same average anomaloscope match (same pigments), but have either narrow (good opponent learning) or wide (poor learning) ranges of acceptable matches.

Ahumada, Albert J., Jr.↗

NASA NTRS2004

Time-Extended Policies in Mult-Agent Reinforcement Learning

Reinforcement learning methods perform well in many domains where a single agent needs to take a sequence of actions to perform a task. These methods use sequences of single-time-step rewards to create a policy that tries to maximize a time-extended utility, which is a (possibly discounted) sum of these rewards. In this paper we build on our previous work showing how these methods can be extended to a multi-agent environment where each agent creates its own policy that works towards maximizing a time-extended global utility over all agents actions. We show improved methods for creating time-extended utilities for the agents that are both "aligned" with the global utility and "learnable." We then show how to crate single-time-step rewards while avoiding the pi fall of having rewards aligned with the global reward leading to utilities not aligned with the global utility. Finally, we apply these reward functions to the multi-agent Gridworld problem. We explicitly quantify a utility's learnability and alignment, and show that reinforcement learning agents using the prescribed reward functions successfully tradeoff learnability and alignment. As a result they outperform both global (e.g., team games ) and local (e.g., "perfectly learnable" ) reinforcement learning solutions by as much as an order of magnitude.

Tumer, Kagan↗

NASA NTRS1992

Software design as a problem in learning theory (a research overview)

Our interest in automating software design has come out of our research in automated reasoning, inductive inference, learnability, and algebraic machine theory. We have investigated these areas extensively, in connection with specific problems of language representation, acquisition, processing, and design. In the case of formal context-free (CF) languages we established existence of finite learnable models ('behavioral realizations') and procedures for constructing them effectively. We also determined techniques for automatic construction of the models, inductively inferring them from finite examples of how they should 'behave'. These results were obtainable due to appropriate representation of domain knowledge, and constraints on the domain that the representation defined. It was when we sought to generalize our results, and adapt or apply them, that we began investigating the possibility of determining similar procedures for constructing correct software. Discussions with other researchers led us to examine testing and verification processes, as they are related to inference, and due to their considerable importance in correct software design. Motivating papers by other researchers, led us to examine these processes in some depth. Here we present our approach to those software design issues raised by other researchers, within our own theoretical context. We describe our results, relative to those of the other researchers, and conclude that they do not compare unfavorably.

Fass, Leona F.↗

NASA NTRSDate not supplied

QuantifyML: How good is my machine learning model?

This paper presents an approach, QuantifyML, which employs model counting to assess the learnability and robustness of machine learning models. Typically the efficacy of machine learning models is determined by computing their accuracy statistically on test data sets. However, this may be misleading, if the test data is not representative of the problem that is being studied. Further, two different models may have the same accuracy on a given data set, measured statistically, but may be very different in their behavior on unseen data. Also, models with high accuracy could have poor adversarial robustness. In QuantifyML, our goal is to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into a C program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise counts w.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, expressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the robustness of trained models around given inputs. Our evaluation demonstrates these applications of QuantifyML on decision trees and neural networks trained to learn relational properties of graphs, for which we know the ground truth, and to perform image classification, for which we do not have the ground truth, but we can quantify local robustness.

Deep Neural Networks↗

NASA NTRS1980

Simplicity in command and control systems - A human factors consideration

The importance of simplicity in the man computer interface (MCI) is stressed because of the effect it has on the system containing the MCI. Results are used from an MCI study at the Jet Propulsion Laboratory to find an area where the system MCIs can be simplified. The circumstances under which these simplifications are appropriate are listed. The concepts of cognitive simplicity and process simplicity are presented as design alternatives for the MCI. In addition, the concepts of understandability, operation, learnability, level of learning, and usability are presented as tools for the system designer. The use of these concepts in developing a systematic MCI design is discussed.

Chafin, R. L.↗

NASA NTRS1987

Attention theory and training research

This study used elements of attention theory as a methodological basis to decompose a complex training task in order to improve training efficiency. The complex task was a microcomputer flight simulation where subjects were required to control the stability of their own helicopter while acquiring and engaging enemy helicopers in a threat enviroment. Subjects were divided into whole-task, part-task, and part/open loop adaptive task groups in a transfer of training paradigm. The effect of reducing mental workload at the early stages of learning was examined with respect to the degree that subordinate elements of the complex task could be automated through practice of consistent, learnable stimulus-response relationships. Results revealed trends suggesting the benefit of isolating consistently mapped sub-tasks for part-task training and the presence of a time-sharing skill over and above the skill required for the separate subtasks.

Connelly, James G., Jr.↗

NASA NTRS1991

Neural network representation and learning of mappings and their derivatives

Discussed here are recent theorems proving that artificial neural networks are capable of approximating an arbitrary mapping and its derivatives as accurately as desired. This fact forms the basis for further results establishing the learnability of the desired approximations, using results from non-parametric statistics. These results have potential applications in robotics, chaotic dynamics, control, and sensitivity analysis. An example involving learning the transfer function and its derivatives for a chaotic map is discussed.

White, Halbert↗

NASA NTRS2001

Learning Sequences of Actions in Collectives of Autonomous Agents

In this paper we focus on the problem of designing a collective of autonomous agents that individually learn sequences of actions such that the resultant sequence of joint actions achieves a predetermined global objective. We are particularly interested in instances of this problem where centralized control is either impossible or impractical. For single agent systems in similar domains, machine learning methods (e.g., reinforcement learners) have been successfully used. However, applying such solutions directly to multi-agent systems often proves problematic, as agents may work at cross-purposes, or have difficulty in evaluating their contribution to achievement of the global objective, or both. Accordingly, the crucial design step in multiagent systems centers on determining the private objectives of each agent so that as the agents strive for those objectives, the system reaches a good global solution. In this work we consider a version of this problem involving multiple autonomous agents in a grid world. We use concepts from collective intelligence to design goals for the agents that are 'aligned' with the global goal, and are 'learnable' in that agents can readily see how their behavior affects their utility. We show that reinforcement learning agents using those goals outperform both 'natural' extensions of single agent algorithms and global reinforcement, learning solutions based on 'team games'.

Turner, Kagan↗

NASA NTRS2002

Time-Extended Payoffs for Collectives of Autonomous Agents

A collective is a set of self-interested agents which try to maximize their own utilities, along with a a well-defined, time-extended world utility function which rates the performance of the entire system. In this paper, we use theory of collectives to design time-extended payoff utilities for agents that are both aligned with the world utility, and are "learnable", i.e., the agents can readily see how their behavior affects their utility. We show that in systems where each agent aims to optimize such payoff functions, coordination arises as a byproduct of the agents selfishly pursuing their own goals. A game theoretic analysis shows that such payoff functions have the net effect of aligning the Nash equilibrium, Pareto optimal solution and world utility optimum, thus eliminating undesirable behavior such as agents working at cross-purposes. We then apply collective-based payoff functions to the token collection in a gridworld problem where agents need to optimize the aggregate value of tokens collected across an episode of finite duration (i.e., an abstracted version of rovers on Mars collecting scientifically interesting rock samples, subject to power limitations). We show that, regardless of the initial token distribution, reinforcement learning agents using collective-based payoff functions significantly outperform both natural extensions of single agent algorithms and global reinforcement learning solutions based on "team games".

Tumer, Kagan↗

NASA NTRS2004

Efficient Evaluation Functions for Multi-Rover Systems

Evolutionary computation can be a powerful tool in cresting a control policy for a single agent receiving local continuous input. This paper extends single-agent evolutionary computation to multi-agent systems, where a collection of agents strives to maximize a global fitness evaluation function that rates the performance of the entire system. This problem is solved in a distributed manner, where each agent evolves its own population of neural networks that are used as the control policies for the agent. Each agent evolves its population using its own agent-specific fitness evaluation function. We propose to create these agent-specific evaluation functions using the theory of collectives to avoid the coordination problem where each agent evolves a population that maximizes its own fitness function, yet the system has a whole achieves low values of the global fitness function. Instead we will ensure that each fitness evaluation function is both "aligned" with the global evaluation function and is "learnable," i.e., the agents can readily see how their behavior affects their evaluation function. We then show how these agent-specific evaluation functions outperform global evaluation methods by up to 600% in a domain where a set of rovers attempt to maximize the amount of information observed while navigating through a simulated environment.

Agogino, Adrian↗

NASA NTRS2018

Next Gen One Portal Usability Evaluation

Each exercise device on the International Space Station (ISS) has a unique, customized software system interface with unique layouts / hierarchy, and operational principles that require significant crew training. Furthermore, the software programs are not adaptable and provide no real-time feedback or motivation to enhance the exercise experience and/or prevent injuries. Additionally, the graphical user interfaces (GUI) of these systems present information through multiple layers resulting in difficulty navigating to the desired screens and functions. These limitations of current exercise device GUI's lead to increased crew time spent on initiating, loading, performing exercises, logging data and exiting the system. To address these limitations a Next Generation One Portal (NextGen One Portal) Crew Countermeasure System (CMS) was developed, which utilizes the latest industry guidelines in GUI designs to provide an intuitive ease of use approach (i.e., 80% of the functionality gained within 5-10 minutes of initial use without/limited formal training required). This is accomplished by providing a consistent interface using common software to reduce crew training, increase efficiency & user satisfaction while also reducing development & maintenance costs. Results from the usability evaluations showed the NextGen One Portal UI having greater efficiency, learnability, memorability, usability and overall user experience than the current Advanced Resistive Exercise Device (ARED) UI used by astronauts on ISS. Specifically, the design of the One-Portal UI as an app interface similar to those found on the Apple and Google's App Store, assisted many of the participants in grasping the concepts of the interface with minimum training. Although the NextGen One-Portal UI was shown to be an overall better interface, observations by the test facilitators noted specific exercise tasks appeared to have a significant impact on the NextGen One-Portal UI efficiency. Future updates to the NextGen One Portal UI will address these inefficiencies.

Cross, E. V., III↗

NASA NTRSDate not supplied

QuantifyML: How Good is My Machine Learning Model?

We present QuantifyML, which applies model counting to assess the learn ability, safety, and robustness of machine learning models. Typically, the efficacy of machine learning models is determined by computing their accuracy statistically on test datasets. However, this may be misleading, if the test data is not representative of the problem that is being studied. With QuantifyML we aim to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into aC program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise countsw.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, ex-pressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the safety and robustness of trained models.

Deep Neural Networks↗

NASA NTRSDate not supplied

What is the Role of Usability and Trust in Autonomy?

Usability encompasses learnability, efficiency, memorability, effectiveness, and satisfaction. NASA’s standards for usability acceptance criteria focus on interfaces that help operators achieve their tasks efficiently, effectively, and with satisfaction. However, discussions on usability, especially regarding future highly automated and autonomous systems, rarely include trust. As NASA plans for long-duration exploration missions, it envisions astronauts operating more independently from Mission Control on Earth. This independence will drive the development of these highly automated and autonomous systems that astronauts will use daily. To prepare for this future, our team has developed a scheduling and execution software tool that facilitates self-scheduling, allowing astronauts to independently manage their own schedule without Mission Control’s involvement. Over many years, we have developed, matured, and evaluated our software tool in extreme environments, prioritizing user-centered design and high usability. These evaluations have included multiple campaigns in NASA analogs, including NEEMO, BASALT, and HERA, as well as technology demonstrations onboard the International Space Station. Our recent research on software interfaces for future astronaut autonomy revealed a strong correlation between usability and trust measures. In a controlled lab experiment, we asked novice users to perform a complex scheduling task, during which the software immediately validated the schedule’s constraints and checked for violations. We collected usability (User Experience Questionnaire, UEQ) and trust (Trust in Automated Systems scale, TAS) measures; significant, strong, and moderate correlations emerged between several of the UEQ metrics and TAS. These results support the argument for investing in usability early to enable and sustain trust in highly automated and autonomous systems.

usability↗