Creating a Culture of Continuous Learning: Solutions for Patient Safety
Explore the source record for details and available documents.
Safety; learning; resilience; safety culture↗
SEARCH · Engineering Papers
Results for “Continual Learning”
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.
NASA’s System-Wide Safety Project: System-Wide Predictive Analytics and Continuous Learning for In-time Aviation Safety Management Systems (IASMS)
Explore the source record for details and available documents.
Michael James Vincent↗
Multiclass Continuous Correspondence Learning
We extend the Structural Correspondence Learning (SCL) domain adaptation algorithm of Blitzer er al. to the realm of continuous signals. Given a set of labeled examples belonging to a 'source' domain, we select a set of unlabeled examples in a related 'target' domain that play similar roles in both domains. Using these 'pivot samples, we map both domains into a common feature space, allowing us to adapt a classifier trained on source examples to classify target examples. We show that when between-class distances are relatively preserved across domains, we can automatically select target pivots to bring the domains into correspondence.
correspondence learning↗
Neuromorphic learning of continuous-valued mappings from noise-corrupted data. Application to real-time adaptive control
The ability of feed-forward neural network architectures to learn continuous valued mappings in the presence of noise was demonstrated in relation to parameter identification and real-time adaptive control applications. An error function was introduced to help optimize parameter values such as number of training iterations, observation time, sampling rate, and scaling of the control signal. The learning performance depended essentially on the degree of embodiment of the control law in the training data set and on the degree of uniformity of the probability distribution function of the data that are presented to the net during sequence. When a control law was corrupted by noise, the fluctuations of the training data biased the probability distribution function of the training data sequence. Only if the noise contamination is minimized and the degree of embodiment of the control law is maximized, can a neural net develop a good representation of the mapping and be used as a neurocontroller. A multilayer net was trained with back-error-propagation to control a cart-pole system for linear and nonlinear control laws in the presence of data processing noise and measurement noise. The neurocontroller exhibited noise-filtering properties and was found to operate more smoothly than the teacher in the presence of measurement noise.
Troudet, Terry↗
Cascade Back-Propagation Learning in Neural Networks
The cascade back-propagation (CBP) algorithm is the basis of a conceptual design for accelerating learning in artificial neural networks. The neural networks would be implemented as analog very-large-scale integrated (VLSI) circuits, and circuits to implement the CBP algorithm would be fabricated on the same VLSI circuit chips with the neural networks. Heretofore, artificial neural networks have learned slowly because it has been necessary to train them via software, for lack of a good on-chip learning technique. The CBP algorithm is an on-chip technique that provides for continuous learning in real time. Artificial neural networks are trained by example: A network is presented with training inputs for which the correct outputs are known, and the algorithm strives to adjust the weights of synaptic connections in the network to make the actual outputs approach the correct outputs. The input data are generally divided into three parts. Two of the parts, called the "training" and "cross-validation" sets, respectively, must be such that the corresponding input/output pairs are known. During training, the cross-validation set enables verification of the status of the input-to-output transformation learned by the network to avoid over-learning. The third part of the data, termed the "test" set, consists of the inputs that are required to be transformed into outputs; this set may or may not include the training set and/or the cross-validation set. Proposed neural-network circuitry for on-chip learning would be divided into two distinct networks; one for training and one for validation. Both networks would share the same synaptic weights.
Duong, Tuan A.↗
A neuro-fuzzy architecture for real-time applications
Neural networks and fuzzy expert systems perform the same task of functional mapping using entirely different approaches. Each approach has certain unique features. The ability to learn specific input-output mappings from large input/output data possibly corrupted by noise and the ability to adapt or continue learning are some important features of neural networks. Fuzzy expert systems are known for their ability to deal with fuzzy information and incomplete/imprecise data in a structured, logical way. Since both of these techniques implement the same task (that of functional mapping--we regard 'inferencing' as one specific category under this class), a fusion of the two concepts that retains their unique features while overcoming their individual drawbacks will have excellent applications in the real world. In this paper, we arrive at a new architecture by fusing the two concepts. The architecture has the trainability/adaptibility (based on input/output observations) property of the neural networks and the architectural features that are unique to fuzzy expert systems. It also does not require specific information such as fuzzy rules, defuzzification procedure used, etc., though any such information can be integrated into the architecture. We show that this architecture can provide better performance than is possible from a single two or three layer feedforward neural network. Further, we show that this new architecture can be used as an efficient vehicle for hardware implementation of complex fuzzy expert systems for real-time applications. A numerical example is provided to show the potential of this approach.
Ramamoorthy, P. A.↗
Post University On-the-Job Training for Engineers
Our national need for qualified scientists and engineers is greater now than at any other time in our history. Fortunately, we can point with pride to this need as a measure of the impact of science and technology on our way of life. In effect, we have made such rapid strides In advancing established sciences and in opening new technological fields that we have proved the value of the scientist and engineer to society, and, as a-result, have created an expanding demand for their services which we must now attempt to satisfy. This demand we face is also due to the changing skills and high degree of specialization required to perform in these new technological fields. The colleges and universities are doing their part to provide current graduates with a modern technical foundation, but we cannot afford to ignore the thousands of experienced engineers and scientists already employed by private industry and government. As employers, we have an obligation to these men and women to see that they are provided with an understanding of the latest advances that modern technology has to offer; that we develop them in particular specialty areas characteristic of a given field of work; and, equally important, that we assist them in the transition from one field to another as the technological emphasis shifts. Practically all technological industries have experienced and continue to experience rapid changes in their activities. The aerospace business, in particular, has been characterized by extremely rapid, in fact revolutionary, changes during the relatively short period of its existence0 At the National Aeronautics and Space Administration, successor to the National Advisory Committee for Aeronautics, for example, we have encountered the fun impact of a changing science and technology. Indeed, as a research organization, we have undoubtedly contributed, in some measure, to this change. Within the NASAs Lewis Research Center, we have approximately 800 research scientists and engineers who have matured professionally in an environment which is essentially one of continuous learning - an experience which comes close to being a form of post graduate training in itself. This environment, in addition to providing continuous evolutionary changes, has also provided two major revolutions which have made this development picture more complex. We will describe these environmental changes which have occurred at the Lewis Research Center and discuss the various techniques and programs we have employed to provide for the professional development of our staff. The Lewis Research Center has had an Interesting and exciting l8-year history of aerospace propulsion research and development. It began during the early years of World War II as an expansion of the Power Plant Division of the NCA Langley Center with the mission of conducting research required for the development of improved reciprocating engines and to study the associated problems of subsonic propulsion aerodynamics, It was only a few years later, however, that turbojet and ramjet propulsion and supersonic flight research became our main concern. This transition to jet type engines and higher speeds was our first major technological change. The aerodynamics of propellers became the aerodynamics of high speed turbine and compressor blades; the fuel ignition and carbon deposition problems were transferred from a cyclical or Intermittent high compression combustion chamber to a continuous combustion zone within a thin-walled metal shell; aerodynamics problems were thrust into the supersonic range; and high temperature materials began to play an increasingly critical role. Although this transition still required the same basic knowledge and principles as before, the new engine types did involve a different emphasis and variety of consideration not generally familiar to our scientists and engineers.
Manganiello, Eugene J.↗
The new organization: Rethinking work in the age of virtuality
Like two enormous steam engines, throttles wide-open, bells clanging and whistles screeching, careening toward each other down the same track, two powerful forces are about to collide and the point of collision will be smack in the middle of the white-collar workplace. Moreover, once the dust has settled, it is quite likely that we will never be able to think about the white-collar workplace in quite the same way again. The forces couldn't be more different. One force, the theory of complex adaptive systems, has its roots in the radical new sciences of chaos and complexity. The other force, the notion of organizations being learning systems, more like living organisms than 'information factories,' is an outgrowth of the new management thinking of leading organizational theorists like the Claremont Graduate School's Peter Drucker, MIT's Peter Senge, and Hitotsubashi University's Ikujiro Nonaka. Nevertheless, both the new science and the new management thinking seem to point to a similar and perhaps even startling conclusion: the business organization of the 21st century will look nothing like the bureaucratic organizational model that prevails in most companies today, a model that has remained largely unchanged since the manufacturing heydays of 1950s. While the details of the new organization remain sketchy, its rough outline is already beginning to take shape. Rather than simply being flatter through the elimination of layer upon layer of 'middle management,' the new organization is likely to be made up of networks of specialists who will be, for all practical purposes, self-managing. Rather than focusing on issues like re-engineering business processes, a holdover from Taylorism, the focus will be on supporting the continuous learning of an organization's specialists, the sharing of this learning with other specialists, and the embedding of this learning in the organization's physical structure. Finally, rather than viewing themselves as going through relatively long periods of stability punctuated by shorts bursts of 'reorganization,' business enterprises will come to realize that their very survival depends upon their being in a state of continuous organization. The implications of the new organization with respect to how companies approach the planning, design, and management of the technology infrastructure that enables individual learning, self-management, and continuous orgsnization, are both numerous and far-reaching. As part of this technology infrastructure, the white-collar workplace exists in the form it does today as a direct result of management's beliefs about how time, space, and tools ought to be organized and managed in order to accomplish useful intellectual work. Obviously, if these beliefs change radically, as both the new science and the new management thinking suggest is about to happen, then it is almost inevitable that the form and function of the white-collar workplace will change radically, as well. Will there even be a white-collar workplace in the 21st century, in the sense of purpose-built facilities designed to support the co-location of large numbers of white-collar workers? Only time will tell. However, the leading indicators seem to suggest that, as the old saying goes, 'We ain't seen nothin' yet!'
Sutherland, Duncan B., Jr.↗
Neuromorphic learning of continuous-valued mappings in the presence of noise: Application to real-time adaptive control
The ability of feed-forward neural net architectures to learn continuous-valued mappings in the presence of noise is demonstrated in relation to parameter identification and real-time adaptive control applications. Factors and parameters influencing the learning performance of such nets in the presence of noise are identified. Their effects are discussed through a computer simulation of the Back-Error-Propagation algorithm by taking the example of the cart-pole system controlled by a nonlinear control law. Adequate sampling of the state space is found to be essential for canceling the effect of the statistical fluctuations and allowing learning to take place.
Troudet, Terry↗
A preliminary empirical evaluation of virtual reality as an instructional medium for visual-spatial tasks
We explored the training potential of Virtual Reality (VR) technology. Thirty-one adults were trained and tested on spatial skills in a VR. They learned a sequence of button and knob responses on a VR console and performed flawlessly on the same console. Half were trained with a rote strategy; the rest used a meaningful strategy. Response times were equivalent for both groups and decreased significantly over five test trials indicating that learning continued on VR tests. The same subjects practiced navigating through a VR building, which had three floors with four rooms on each floor. The dependent measure was the number of rooms traversed on routes that differed from training routes. Many subjects completed tests in the fewest rooms possible. All subjects learned configurational knowledge according to the criterion of taking paths that were significantly shorter than those predicted by a random walk as determined by a Monte Carlo analysis. The results were discussed as a departure point for empirically testing the training potential of VR technology.
Regian, J. Wesley↗
Space Shuttle GN and C Development History and Evolution
Completion of the final Space Shuttle flight marks the end of a significant era in Human Spaceflight. Developed in the 1970 s, first launched in 1981, the Space Shuttle embodies many significant engineering achievements. One of these is the development and operation of the first extensive fly-by-wire human space transportation Guidance, Navigation and Control (GN&C) System. Development of the Space Shuttle GN&C represented first time inclusions of modern techniques for electronics, software, algorithms, systems and management in a complex system. Numerous technical design trades and lessons learned continue to drive current vehicle development. For example, the Space Shuttle GN&C system incorporated redundant systems, complex algorithms and flight software rigorously verified through integrated vehicle simulations and avionics integration testing techniques. Over the past thirty years, the Shuttle GN&C continued to go through a series of upgrades to improve safety, performance and to enable the complex flight operations required for assembly of the international space station. Upgrades to the GN&C ranged from the addition of nose wheel steering to modifications that extend capabilities to control of the large flexible configurations while being docked to the Space Station. This paper provides a history of the development and evolution of the Space Shuttle GN&C system. Emphasis is placed on key architecture decisions, design trades and the lessons learned for future complex space transportation system developments. Finally, some of the interesting flight operations experience is provided to inform future developers of flight experiences.
Zimpfer, Douglas↗
System Identification for Nonlinear Control Using Neural Networks
An approach to incorporating artificial neural networks in nonlinear, adaptive control systems is described. The controller contains three principal elements: a nonlinear inverse dynamic control law whose coefficients depend on a comprehensive model of the plant, a neural network that models system dynamics, and a state estimator whose outputs drive the control law and train the neural network. Attention is focused on the system identification task, which combines an extended Kalman filter with generalized spline function approximation. Continual learning is possible during normal operation, without taking the system off line for specialized training. Nonlinear inverse dynamic control requires smooth derivatives as well as function estimates, imposing stringent goals on the approximating technique.
Stengel, Robert F.↗
A neural network prototyping package within IRAF
We outline our plans for incorporating a Neural Network Prototyping Package into the IRAF environment. The package we are developing will allow the user to choose between different types of networks and to specify the details of the particular architecture chosen. Neural networks consist of a highly interconnected set of simple processing units. The strengths of the connections between units are determined by weights which are adaptively set as the network 'learns'. In some cases, learning can be a separate phase of the user cycle of the network while in other cases the network learns continuously. Neural networks have been found to be very useful in pattern recognition and image processing applications. They can form very general 'decision boundaries' to differentiate between objects in pattern space and they can be used for associative recall of patterns based on partial cures and for adaptive filtering. We discuss the different architectures we plan to use and give examples of what they can do.
Bazell, D.↗
Graphical User Interface Development for Representing Air Flow Patterns
In the Turbine Branch, scientists carry out experimental and computational work to advance the efficiency and diminish the noise production of jet engine turbines. One way to do this is by decreasing the heat that the turbine blades receive. Most of the experimental work is carried out by taking a single turbine blade and analyzing the air flow patterns around it, because this data indicates the sections of the turbine blade that are getting too hot. Since the cost of doing turbine blade air flow experiments is very high, researchers try to do computational work that fits the experimental data. The goal of computational fluid dynamics is for scientists to find a numerical way to predict the complex flow patterns around different turbine blades without physically having to perform tests or costly experiments. When visualizing flow patterns, scientists need a way to represent the flow conditions around a turbine blade. A researcher will assign specific zones that surround the turbine blade. In a two-dimensional view, the zones are usually quadrilaterals. The next step is to assign boundary conditions which define how the flow enters or exits one side of a zone. way of setting up computational zones and grids, visualizing flow patterns, and storing all the flow conditions in a file on the computer for future computation. Such a program is necessary because the only method for creating flow pattern graphs is by hand, which is tedious and time-consuming. By using a computer program to create the zones and grids, the graph would be faster to make and easier to edit. Basically, the user would run a program that is an editable graph. The user could click and drag with the mouse to form various zones and grids, then edit the locations of these grids, add flow and boundary conditions, and finally save the graph for future use and analysis. My goal this summer is to create a graphical user interface (GUI) that incorporates all of these elements. I am writing the program in Java, a language that is portable among platforms, because it can run on different operating systems such as Windows and Unix without having to be rewritten. I had no prior experience of programming in Java at the start of my internship; I am continuously learning as I create the program. I have written the part of the program that enables a user to draw several zones, edit them, and store their locations. The next phase of my project is to allow the user to click on the side of a zone and create a boundary condition for it. A previous intern wrote a program that allows the user to input boundary conditions. I can integrate the two programs to create a larger, more usable program. After that, I will develop a way for the user to save the graph for future reference. Another eventual goal is to make the GUI capable of creating three-dimensional zones as well. Researchers such as my mentor, Dr. David Ashpis, need a quick, user-friendly
Chaudhary, Nilika↗
Neuromorphic learning of continuous-valued mappings from noise-corrupted data
The effect of noise on the learning performance of the backpropagation algorithm is analyzed. A selective sampling of the training set is proposed to maximize the learning of control laws by backpropagation, when the data have been corrupted by noise. The training scheme is applied to the nonlinear control of a cart-pole system in the presence of noise. The neural computation provides the neurocontroller with good noise-filtering properties. In the presence of plant noise, the neurocontroller is found to be more stable than the teacher. A novel perspective on the application of neural network technology to control engineering is presented.
Troudet, T.↗
Cooperation and Coordination Between Fuzzy Reinforcement Learning Agents in Continuous State Partially Observable Markov Decision Processes
Successful operations of future multi-agent intelligent systems require efficient cooperation schemes between agents sharing learning experiences. We consider a pseudo-realistic world in which one or more opportunities appear and disappear in random locations. Agents use fuzzy reinforcement learning to learn which opportunities are most worthy of pursuing based on their promise rewards, expected lifetimes, path lengths and expected path costs. We show that this world is partially observable because the history of an agent influences the distribution of its future states. We consider a cooperation mechanism in which agents share experience by using and-updating one joint behavior policy. We also implement a coordination mechanism for allocating opportunities to different agents in the same world. Our results demonstrate that K cooperative agents each learning in a separate world over N time steps outperform K independent agents each learning in a separate world over K*N time steps, with this result becoming more pronounced as the degree of partial observability in the environment increases. We also show that cooperation between agents learning in the same world decreases performance with respect to independent agents. Since cooperation reduces diversity between agents, we conclude that diversity is a key parameter in the trade off between maximizing utility from cooperation when diversity is low and maximizing utility from competitive coordination when diversity is high.
Berenji, Hamid R.↗
Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning
Since most real-world applications of classification learning involve continuous-valued attributes, properly addressing the discretization process is an important problem. This paper addresses the use of the entropy minimization heuristic for discretizing the range of a continuous-valued attribute into multiple intervals.
discretization continuous-valued attributes classi↗
Towards Autonomous Lunar Resource Excavation via Reinforcement Learning
To continue on a sustainable and flexible path, NASA needs to address the challenge of collecting and moving large amounts of regolith at the destination. NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU) processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from a reduced sensor payload. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We created reduced-order simulation environments to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. The goal of reinforcement learning is for an agent to learn a policy (task strategy) through interactions with an environment. When the agent performs an action, a change occurs in environment state and a numerical reward is received which informs the agent whether the action performed was good or not. Since reinforcement learning algorithms learn through trial-and-error, a simulation is a desirable first environment for development and learning. We developed two simulations, the first is a 2D excavation simulation developed to facilitate parameter selection, and a 3D simulation developed using a game physics engine, to simulate simplified soil interactions and increase the fidelity of the dynamic models of the robotic agents. The development of this 3D simulation has enabled the training of additional sensing capabilities and research both at the granular mechanics and operations levels. We experimented with various virtual sensor payloads to identify a combination that enabled efficient excavation operation and learning. Our reward function is based on how much material is excavated per step. A penalty is also received for leaving the dig site and to smooth the acceleration of the drum arms. We implemented pseudo time-of-flight sensors to report distance from each drum to ground and the height above ground which was found to be more efficient than existing solutions. Our findings suggest that reinforcement learning for autonomous operations has learned viable trenching strategies within 3000 training episodes in our simplified 2D environment and helped identify desirable sensing capabilities, arrangements, and considerations such as the positioning of time-of-flight sensors. Future work includes expanding our simulation to more complex environments and scenarios, and transfer learning from simulation to RASSOR 2.0 hardware for deployment in the Regolith Test Bin at NASA's Kennedy Space Center.
rassor↗