ALBERT

All Library Books, journals and Electronic Records Telegrafenberg

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
    Springer
    Machine learning 23 (1996), S. 221-249 
    ISSN: 0885-6125
    Keywords: Robotics ; Neural Networks ; Fuzzy Controllers ; Multistrategy Learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract One of the most significant cost factors in robotics applications is the design and development of real-time robot control software. Control theory helps when linear controllers have to be developed, but it doesn't sufficiently support the generation of non-linear controllers, although in many cases (such as in compliance control), nonlinear control is essential for achieving high performance. This paper discusses how Machine Learning has been applied to the design of (non-)linear controllers. Several alternative function approximators, including Multilayer Perceptrons (MLP), Radial Basis Function Networks (RBFNs), and Fuzzy Controllers are analyzed and compared, leading to the definition of two major families: Open Field Function Approximators and Locally Receptive Field Function Approximators. It is shown that RBFNs and Fuzzy Controllers bear strong similarities, and that both have a symbolic interpretation. This characteristic allows for applying both symbolic and statistic learning algorithms to synthesize the network layout from a set of examples and, possibly, some background knowledge. Three integrated learning algorithms, two of which are original, are described and evaluated on experimental test cases. The first test case is provided by a robot KUKA IR-361 engaged into the peg-into-hole task, whereas the second is represented by a classical prediction task on the Mackey-Glass time series. From the experimental comparison, it appears that both Fuzzy Controllers and RBFNs synthesised from examples are excellent approximators, and that, in practice, they can be even more accurate than MLPs.
    Type of Medium: Electronic Resource
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 2
    Electronic Resource
    Electronic Resource
    Springer
    Machine learning 23 (1996), S. 221-249 
    ISSN: 0885-6125
    Keywords: Robotics ; Neural Networks ; Fuzzy Controllers ; Multistrategy Learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract One of the most significant cost factors in robotics applications is the design and development of real-time robot control software. Control theory helps when linear controllers have to be developed, but it doesn't sufficiently support the generation of non-linear controllers, although in many cases (such as in compliance control), nonlinear control is essential for achieving high performance. This paper discusses how Machine Learning has been applied to the design of (non-)linear controllers. Several alternative function approximators, including Multilayer Perceptrons (MLP), Radial Basis Function Networks (RBFNs), and Fuzzy Controllers are analyzed and compared, leading to the definition of two major families: Open Field Function Approximators and Locally Receptive Field Function Approximators. It is shown that RBFNs and Fuzzy Controllers bear strong similarities, and that both have a symbolic interpretation. This characteristic allows for applying both symbolic and statistic learning algorithms to synthesize the network layout from a set of examples and, possibly, some background knowledge. Three integrated learning algorithms, two of which are original, are described and evaluated on experimental test cases. The first test case is provided by a robot KUKA IR-361 engaged into the “peg-into-hole” task, whereas the second is represented by a classical prediction task on the Mackey-Glass time series. From the experimental comparison, it appears that both Fuzzy Controllers and RBFNs synthesised from examples are excellent approximators, and that, in practice, they can be even more accurate than MLPs.
    Type of Medium: Electronic Resource
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 3
    facet.materialart.
    Unknown
    Instituto Nacional de Investigación y Desarrollo Pesquero (INIDEP): Mar del Plata
    Publication Date: 2021-05-19
    Description: In this chapter the main features of the currents on the Argentine continental shelf are described. Due to the scarcity of direct current observations, adequate to resolve the mean flow, the circulation of the continental shelf is studied based on property distributions and models. These analyses indicate that the mean flowover the continental shelf varies between 1 and 2 Sverdrups (1Sverdrup = 1x106 m3 s-1)towards the NNE. A synthesis of results of studies of higher frequency motions is also presented. The most relevant results derived from long term direct current observations on the continental shelf near 43°S are discussed. The mean current velocities in the inner and mid-shelf regions vary between 0,05 and 0,10 m/s towards the NNE, in agreement with the direction inferred from property distributions and models.
    Description: Bibliographic reference/Referencia bibliográfica: Piola, A.R.; Rivas, A.; 1997. Corrientes en la plataforma continental. En: Boschi, E.E.; ed. Antecedentes históricos de las exploraciones en el mar y las características ambientales. Mar del Plata: Instituto Nacional de Investigación y Desarrollo Pesquero INIDEP, (El Mar Argentino y sus Recursos Pesqueros; 1) p.119-132
    Description: Published
    Description: corrientes oceánicas, circulación oceánica, oceanografía física, plataforma continental
    Keywords: Ocean currents ; Physical oceanography ; Continental shelves ; Continental shelves ; Ocean currents ; Ocean circulation ; Physical oceanography
    Repository Name: AquaDocs
    Type: Book Section
    Format: 1125466 bytes
    Format: application/pdf
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 4
    facet.materialart.
    Unknown
    Instituto Nacional de Investigación y Desarrollo Pesquero (INIDEP): Mar del Plata | Instituto Nacional de Investigación y Desarrollo Pesquero (INIDEP): Mar del Plata
    Publication Date: 2021-05-19
    Description: The current knowledge on the argentine continental shelf water masses is summarized in this paper. These water masses are characterized as a function of water types fed by the boundary currents and the modifications due to continental runoff, and water energy exchange with the atmosphere. Based on sea surface salinity distributions and the temperature-salinity characteristics, three masses are described: coastal waters, mid-shelf waters and slope waters. The main freshwater sources found along the coast are identified, as well as high salinity formation areas. The vertical stratification, mainly controlled by temperature, is analyzed along the annual cycle. The stratification cycle is mainly driven by the heat exchange between the atmosphere and the ocean. Finally the oceanic fronts in the Argentine Sea are cited.
    Description: Bibligraphic reference/Referencia bibliográfica: Guerrero, R.A.; Piola, A.R. 1997. Masas de agua en la plataforma continental. En: Boschi, E.E.; ed. Antecedentes históricos de las exploraciones en el mar y las características ambientales. Mar del Plata: Instituto Nacional de Investigación y Desarrollo Pesquero INIDEP. (El Mar Argentino y sus Recursos Pesqueros, 1) p.107-118
    Description: Published
    Description: hidrografía, plataforma continental, circulación de agua, estratificación, frentes oceánicos, masas de agua
    Keywords: Water circulation ; Stratification ; Hydrography ; Continental shelves ; Continental shelves ; Water masses ; Hydrography ; Water circulation ; Oceanic fronts ; Stratification
    Repository Name: AquaDocs
    Type: Book Section
    Format: 1881430 bytes
    Format: application/pdf
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...