Library

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
    Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit (2000)
    [s.l.] : Macmillian Magazines Ltd.
    Nature 405 (2000), S. 947-951 
    Details
    ISSN: 1476-4687
    Source: Nature Archives 1869 - 2009
    Topics: Biology , Chemistry and Pharmacology , Medicine , Natural Sciences in General , Physics
    Notes: [Auszug] Digital circuits such as the flip-flop use feedback to achieve multi-stability and nonlinearity to restore signals to logical levels, for example 0 and 1. Analogue feedback circuits are generally designed to operate linearly, so that signals are over a range, and the response is unique. By ...
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1038/35016072
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 2
    Electronic Resource
    Electronic Resource
    Learning from a population of hypotheses (1995)
    Springer
    Machine learning 18 (1995), S. 255-276 
    Details
    ISSN: 0885-6125
    Keywords: machine learning ; computational learning theory ; PAC learning ; learning agents
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approximate an unknown target function arbitrarily well. Our motivation includes the question of how to make optimal use of multiple independent runs of a mediocre learning algorithm, as well as settings in which the many hypotheses are obtained by a distributed population of identical learning agents.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00993412
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 3
    Electronic Resource
    Electronic Resource
    Learning the parts of objects by non-negative matrix factorization (1999)
    [s.l.] : Macmillian Magazines Ltd.
    Nature 401 (1999), S. 788-791 
    Details
    ISSN: 1476-4687
    Source: Nature Archives 1869 - 2009
    Topics: Biology , Chemistry and Pharmacology , Medicine , Natural Sciences in General , Physics
    Notes: [Auszug] Is perception of the whole based on perception of its parts? There is psychological and physiological evidence for parts-based representations in the brain, and certain computational theories of object recognition rely on such representations. But little is known about how brains or ...
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1038/44565
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 4
    Electronic Resource
    Electronic Resource
    Rigorous Learning Curve Bounds from Statistical Mechanics (1996)
    Springer
    Machine learning 25 (1996), S. 195-236 
    Details
    ISSN: 0885-6125
    Keywords: learning curves ; statistical mechanics ; phase transitions ; VC dimension
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this paper we introduce and investigate a mathematically rigorous theory of learning curves that is based on ideas from statistical mechanics. The advantage of our theory over the well-established Vapnik-Chervonenkis theory is that our bounds can be considerably tighter in many cases, and are also more reflective of the true behavior of learning curves. This behavior can often exhibit dramatic properties such as phase transitions, as well as power law asymptotics not explained by the VC theory. The disadvantages of our theory are that its application requires knowledge of the input distribution, and it is limited so far to finite cardinality function classes. We illustrate our results with many concrete examples of learning curve bounds derived from our theory.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1026499208981
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 5
    Electronic Resource
    Electronic Resource
    Selective Sampling Using the Query by Committee Algorithm (1997)
    Springer
    Machine learning 28 (1997), S. 133-168 
    Details
    ISSN: 0885-6125
    Keywords: selective sampling ; query learning ; Bayesian Learning ; experimental design
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We analyze the “query by committee” algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of perceptrons.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007330508534
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 6
    Electronic Resource
    Electronic Resource
    Rigorous learning curve bounds from statistical mechanics (1996)
    Springer
    Machine learning 25 (1996), S. 195-236 
    Details
    ISSN: 0885-6125
    Keywords: learning curves ; statistical mechanics ; phase transitions ; VC dimension
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract In this paper we introduce and investigate a mathematically rigorous theory of learning curves that is based on ideas from statistical mechanics. The advantage of our theory over the well-established Vapnik-Chervonenkis theory is that our bounds can be considerably tighter in many cases, and are also more reflective of the true behavior of learning curves. This behavior can often exhibit dramatic properties such as phase transitions, as well as power law asymptotics not explained by the VC theory. The disadvantages of our theory are that its application requires knowledge of the input distribution, and it is limited so far to finite cardinality function classes. We illustrate our results with many concrete examples of learning curve bounds derived from our theory.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00114010
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 7
    Electronic Resource
    Electronic Resource
    The Autapse: A Simple Illustration of Short-Term Analog Memory Storage by Tuned Synaptic Feedback (2000)
    Springer
    Journal of computational neuroscience 9 (2000), S. 171-185 
    Details
    ISSN: 1573-6873
    Keywords: short-term memory ; persistent neural activity ; synaptic feedback ; reverberating circuit
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science , Medicine , Physics
    Notes: Abstract According to a popular hypothesis, short-term memories are stored as persistent neural activity maintained by synaptic feedback loops. This hypothesis has been formulated mathematically in a number of recurrent network models. Here we study an abstraction of these models, a single neuron with a synapse onto itself, or autapse. This abstraction cannot simulate the way in which persistent activity patterns are distributed over neural populations in the brain. However, with proper tuning of parameters, it does reproduce the continuously graded, or analog, nature of many examples of persistent activity. The conditions for tuning are derived for the dynamics of a conductance-based model neuron with a slow excitatory autapse. The derivation uses the method of averaging to approximate the spiking model with a nonspiking, reduced model. Short-term analog memory storage is possible if the reduced model is approximately linear and if its feedforward bias and autapse strength are precisely tuned.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1008971908649
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...