ALBERT

All Library Books, journals and Electronic Records Telegrafenberg

X
feed icon rss

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Electronic Resource
    Electronic Resource
    Direct and indirect model based control using artificial neural networks (1991)
    s.l. : American Chemical Society
    Industrial & engineering chemistry research 30 (1991), S. 2564-2573 
    Details
    ISSN: 1520-5045
    Source: ACS Legacy Archives
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1021/ie00060a009
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 2
    Electronic Resource
    Electronic Resource
    Expert multivariable control. 1. Structure and design methodology (1990)
    s.l. : American Chemical Society
    Industrial & engineering chemistry research 29 (1990), S. 382-389 
    Details
    ISSN: 1520-5045
    Source: ACS Legacy Archives
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1021/ie00099a014
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 3
    Electronic Resource
    Electronic Resource
    Expert multivariable control. 2. Application of EMC to two-product distillation columns (1990)
    s.l. : American Chemical Society
    Industrial & engineering chemistry research 29 (1990), S. 389-403 
    Details
    ISSN: 1520-5045
    Source: ACS Legacy Archives
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1021/ie00099a015
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 4
    Electronic Resource
    Electronic Resource
    Expert multivariable control. 3. Extension of EMC to three-product side-stream distillation columns (1990)
    s.l. : American Chemical Society
    Industrial & engineering chemistry research 29 (1990), S. 404-415 
    Details
    ISSN: 1520-5045
    Source: ACS Legacy Archives
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1021/ie00099a016
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 5
    Electronic Resource
    Electronic Resource
    Active Learning for Vision-Based Robot Grasping (1996)
    Springer
    Machine learning 23 (1996), S. 251-278 
    Details
    ISSN: 0885-6125
    Keywords: robots ; vision ; manipulation ; active learning ; grasping ; interval estimation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Reliable vision-based grasping has proved elusive outside of controlled environments. One approach towards building more flexible and domain-independent robot grasping systems is to employ learning to adapt the robot's perceptual and motor system to the task. However, one pitfall in robot perceptual and motor learning is that the cost of gathering the learning set may be unacceptably high. Active learning algorithms address this shortcoming by intelligently selecting actions so as to decrease the number of examples necessary to achieve good performance and also avoid separate training and execution phases, leading to higher autonomy. We describe the IE-ID3 algorithm, which extends the Interval Estimation (IE) active learning approach from discrete to real-valued learning domains by combining IE with a classification tree learning algorithm (ID-3). We present a robot system which rapidly learns to select the grasp approach directions using IE-ID3 given simplified superquadric shape approximations of objects. Initial results on a small set of objects show that a robot with a laser scanner system can rapidly learn to pick up new objects, and simulation studies show the superiority of the active learning approach for a simulated grasping task using larger sets of objects. Extensions of the approach and future areas of research incorporating more sophisticated perceptual and action representation are discussed
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1018280807006
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 6
    Electronic Resource
    Electronic Resource
    Active learning for vision-based robot grasping (1996)
    Springer
    Machine learning 23 (1996), S. 251-278 
    Details
    ISSN: 0885-6125
    Keywords: robots ; vision ; manipulation ; active learning ; grasping ; interval estimation
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Reliable vision-based grasping has proved elusive outside of controlled environments. One approach towards building more flexible and domain-independent robot grasping systems is to employ learning to adapt the robot's perceptual and motor system to the task. However, one pitfall in robot perceptual and motor learning is that the cost of gathering the learning set may be unacceptably high. Active learning algorithms address this shortcoming by intelligently selecting actions so as to decrease the number of examples necessary to achieve good performance and also avoid separate training and execution phases, leading to higher autonomy. We describe the IE-ID3 algorithm, which extends the Interval Estimation (IE) active learning approach from discrete to real-valued learning domains by combining IE with a classification tree learning algorithm (ID-3). We present a robot system which rapidly learns to select the grasp approach directions using IE-ID3 given simplified superquadric shape approximations of objects. Initial results on a small set of objects show that a robot with a laser scanner system can rapidly learn to pick up new objects, and simulation studies show the superiority of the active learning approach for a simulated grasping task using larger sets of objects. Extensions of the approach and future areas of research incorporating more sophisticated perceptual and action representation are discussed
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00117446
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 7
    Electronic Resource
    Electronic Resource
    Model-based approach to automated hazard identification of chemical plants (1995)
    Hoboken, NJ : Wiley-Blackwell
    AIChE Journal 41 (1995), S. 97-109 
    Details
    ISSN: 0001-1541
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: A prototype hazard identification system, qualitative hazard identifier (QHI), works by exhaustively positing possible faults, automatically building qualitative process models, simulating them, and checking for hazards. QHI matches a library of general faults such as leaks, broken filters, blocked pipes, and controller failures against the physical description of the plant to determine all specific instances of faults that can occur in the plant. Faults may perturb variables in the original design model or may require building a new model. Fault models are automatically generated using the qualitative process compiler and simulated using QSIM. Hazards including overpressure, overtemperature, controller saturation, and explosion are identified in the reactor section of a nitric acid plant using QHI.
    Additional Material: 7 Ill.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/aic.690410110
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 8
    Electronic Resource
    Electronic Resource
    A hybrid neural network-first principles approach to process modeling (1992)
    Hoboken, NJ : Wiley-Blackwell
    AIChE Journal 38 (1992), S. 1499-1511 
    Details
    ISSN: 0001-1541
    Keywords: Chemistry ; Chemical Engineering
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology , Process Engineering, Biotechnology, Nutrition Technology
    Notes: A hybrid neural network-first principles modeling scheme is developed and used to model a fedbatch bioreactor. The hybrid model combines a partial first principles model, which incorporates the available prior knowledge about the process being modeled, with a neural network which serves as an estimator of unmeasured process parameters that are difficult to model from first principles. This hybrid model has better properties than standard “black-box” neural network models in that it is able to interpolate and extrapolate much more accurately, is easier to analyze and interpret, and requires significantly fewer training examples. Two alternative state and parameter estimation strategies, extended Kalman filtering and NLP optimization, are also considered. When no a priori known model of the unobserved process parameters is available, the hybrid network model gives better estimates of the parameters, when compared to these methods. By providing a model of these unmeasured parameters, the hybrid network can also make predictions and hence can be used for process optimization. These results apply both when full and partial state measurements are available, but in the latter case a state reconstruction method must be used for the first principles component of the hybrid model.
    Additional Material: 18 Ill.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/aic.690381003
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 9
    Electronic Resource
    Electronic Resource
    Application of the boundary element method to dense dispersions (1988)
    Chichester [u.a.] : Wiley-Blackwell
    International Journal for Numerical Methods in Engineering 26 (1988), S. 2487-2501 
    Details
    ISSN: 0029-5981
    Keywords: Engineering ; Engineering General
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Mathematics , Technology
    Notes: The boundary element method (BEM) is used to find the effective conductivity of a random dispersion of disks in a second material. Small separations between inclusions give rise to difficulties not usually associated with the use of the BEM. We find that the integration point spacing on a given surface element has to be of the order of the shortest distance between disks. The spacing requirement becomes a limitation at high densities, even when the ratio of the conductivity of the disks to that of the host material is close to one. This limitation is overcome by increasing the order of the integration scheme used rather than by increasing the number of surface elements. A more conventional concern is that the surface mesh itself must be sufficiently fine to represent the temperature and flux profiles. As with all simulations of dense dispersions, periodic boundary conditions have to be used and further, because random dispersions are of interest, averages of calculations over many configurations are needed. Taking account of the above considerations we calculate the first exact results for the effective conductivity of a dispersion of cylinders at a high (0.6) density. The influence of vectorization on the performance of the code is briefly mentioned, as are other possible improvements.
    Additional Material: 9 Ill.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1002/nme.1620261108
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 10
    facet.materialart.
    Unknown
    Expert-augmented machine learning (2020)
    National Academy of Sciences
    Details
    Publication Date: 2020-02-18
    Description: Machine learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption is limited by the level of trust afforded by given models. Human vs. machine performance is commonly compared empirically to decide whether a certain task should be performed by a computer or an expert. In reality, the optimal learning strategy may involve combining the complementary strengths of humans and machines. Here, we present expert-augmented machine learning (EAML), an automated method that guides the extraction of expert knowledge and its integration into machine-learned models. We used a large dataset of intensive-care patient data to derive 126 decision rules that predict hospital mortality. Using an online platform, we asked 15 clinicians to assess the relative risk of the subpopulation defined by each rule compared to the total sample. We compared the clinician-assessed risk to the empirical risk and found that, while clinicians agreed with the data in most cases, there were notable exceptions where they overestimated or underestimated the true risk. Studying the rules with greatest disagreement, we identified problems with the training data, including one miscoded variable and one hidden confounder. Filtering the rules based on the extent of disagreement between clinician-assessed risk and empirical risk, we improved performance on out-of-sample data and were able to train with less data. EAML provides a platform for automated creation of problem-specific priors, which help build robust and dependable machine-learning models in critical applications.
    Print ISSN: 0027-8424
    Electronic ISSN: 1091-6490
    Topics: Biology , Medicine , Natural Sciences in General
    Published by National Academy of Sciences
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    PAPER CURRENT
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...