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
Filter
  • Articles  (7)
  • computational learning theory  (5)
  • Child  (2)
  • 2015-2019  (1)
  • 1995-1999  (6)
  • 1830-1839
  • Computer Science  (7)
  • Technology
  • 1
    Electronic Resource
    Electronic Resource
    On-line learning of linear functions (1995)
    Springer
    Computational complexity 5 (1995), S. 1-23 
    Details
    ISSN: 1420-8954
    Keywords: Machine learning ; computational learning theory ; on-line learning ; linear functions ; worst-case loss bounds ; adaptive filter theory ; 68T05
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We present an algorithm for the on-line learning of linear functions which is optimal to within a constant factor with respect to bounds on the sum of squared errors for a worst case sequence of trials. The bounds are logarithmic in the number of variables. Furthermore, the algorithm is shown to be optimally robust with respect to noise in the data (again to within a constant factor).
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF01277953
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 2
    Electronic Resource
    Electronic Resource
    On the complexity of function learning (1995)
    Springer
    Machine learning 18 (1995), S. 187-230 
    Details
    ISSN: 0885-6125
    Keywords: computational learning theory ; on-line learning ; mistake-bounded learning ; function learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The majority of results in computational learning theory are concerned with concept learning, i.e. with the special case of function learning for classes of functions with range {0, 1}. Much less is known about the theory of learning functions with a larger range such as ℕ or ℝ. In particular relatively few results exist about the general structure of common models for function learning, and there are only very few nontrivial function classes for which positive learning results have been exhibited in any of these models. We introduce in this paper the notion of a binary branching adversary tree for function learning, which allows us to give a somewhat surprising equivalent characterization of the optimal learning cost for learning a class of real-valued functions (in terms of a max-min definition which does not involve any “learning” model). Another general structural result of this paper relates the cost for learning a union of function classes to the learning costs for the individual function classes. Furthermore, we exhibit an efficient learning algorithm for learning convex piecewise linear functions from ℝ d into ℝ. Previously, the class of linear functions from ℝ d into ℝ was the only class of functions with multidimensional domain that was known to be learnable within the rigorous framework of a formal model for online learning. Finally we give a sufficient condition for an arbitrary class $$\mathcal{F}$$ of functions from ℝ into ℝ that allows us to learn the class of all functions that can be written as the pointwise maximum ofk functions from $$\mathcal{F}$$ . This allows us to exhibit a number of further nontrivial classes of functions from ℝ into ℝ for which there exist efficient learning algorithms.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1007/BF00993410
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 3
    Electronic Resource
    Electronic Resource
    Structural Results About On-line Learning Models With and Without Queries (1999)
    Springer
    Machine learning 36 (1999), S. 147-181 
    Details
    ISSN: 0885-6125
    Keywords: computational learning theory ; learning with queries ; mistake bounds ; function learning ; learning with noise
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We solve an open problem of Maass and Turán, showing that the optimal mistake-bound when learning a given concept class without membership queries is within a constant factor of the optimal number of mistakes plus membership queries required by an algorithm that can ask membership queries. Previously known results imply that the constant factor in our bound is best possible. We then show that, in a natural generalization of the mistake-bound model, the usefulness to the learner of arbitrary “yes-no” questions between trials is very limited. We show that several natural structural questions about relatives of the mistake-bound model can be answered through the application of this general result. Most of these results can be interpreted as saying that learning in apparently less powerful (and more realistic) models is not much more difficult than learning in more powerful models.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007614417594
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 4
    Electronic Resource
    Electronic Resource
    The Complexity of Learning According to Two Models of a Drifting Environment (1999)
    Springer
    Machine learning 37 (1999), S. 337-354 
    Details
    ISSN: 0885-6125
    Keywords: computational learning theory ; concept drift ; context-sensitive learning ; prediction ; PAC learning ; agnostic learning ; uniform convergence ; VC theory
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We show that a $$\frac{{c \in ^3 }}{{{\text{VCdim(}}\mathcal{F}{\text{)}}}}$$ bound on the rate of drift of the distribution generating the examples is sufficient for agnostic learning to relative accuracy ∈, where c 〉 0 is a constant; this matches a known necessary condition to within a constant factor. We establish a $$\frac{{c \in ^2 }}{{{\text{VCdim(}}\mathcal{F}{\text{)}}}}$$ sufficient condition for the realizable case, also matching a known necessary condition to within a constant factor. We provide a relatively simple proof of a bound of $$O(\frac{1}{{_ \in 2}}({\text{VCdim(}}\mathcal{F}{\text{)}}$$ + $$\log \frac{1}{\delta }))$$ on the sample complexity of agnostic learning in a fixed environment.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1007666507971
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 5
    Electronic Resource
    Electronic Resource
    On the Complexity of Function Learning (1995)
    Springer
    Machine learning 18 (1995), S. 187-230 
    Details
    ISSN: 0885-6125
    Keywords: computational learning theory ; on-line learning ; mistake-bounded learning ; function learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract The majority of results in computational learning theory are concerned with concept learning, i.e. with the special case of function learning for classes of functions with range {0, 1}. Much less is known about the theory of learning functions with a larger range such as $$\mathbb{N}$$ or $$\mathbb{R}$$ . In particular relatively few results exist about the general structure of common models for function learning, and there are only very few nontrivial function classes for which positive learning results have been exhibited in any of these models. We introduce in this paper the notion of a binary branching adversary tree for function learning, which allows us to give a somewhat surprising equivalent characterization of the optimal learning cost for learning a class of real-valued functions (in terms of a max-min definition which does not involve any “learning” model). Another general structural result of this paper relates the cost for learning a union of function classes to the learning costs for the individual function classes. Furthermore, we exhibit an efficient learning algorithm for learning convex piecewise linear functions from $$\mathbb{R}^d $$ into $$\mathbb{R}$$ . Previously, the class of linear functions from $$\mathbb{R}^d $$ into $$\mathbb{R}$$ was the only class of functions with multidimensional domain that was known to be learnable within the rigorous framework of a formal model for online learning. Finally we give a sufficient condition for an arbitrary class $$\mathcal{F}$$ of functions from $$\mathbb{R}$$ into $$\mathbb{R}$$ that allows us to learn the class of all functions that can be written as the pointwise maximum of k functions from $$\mathcal{F}$$ . This allows us to exhibit a number of further nontrivial classes of functions from $$\mathbb{R}$$ into $$\mathbb{R}$$ for which there exist efficient learning algorithms.
    Type of Medium: Electronic Resource
    URL: http://dx.doi.org/10.1023/A:1022851430087
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    Paper (German National Licenses)
    Fulltext
  • 6
    facet.materialart.
    Unknown
    Search for cross-species transmission of porcine endogenous retrovirus in patients treated with living pig tissue. The XEN 111 Study Group (1999)
    American Association for the Advancement of Science (AAAS)
    Details
    Publication Date: 1999-08-24
    Description: Pig organs may offer a solution to the shortage of human donor organs for transplantation, but concerns remain about possible cross-species transmission of porcine endogenous retrovirus (PERV). Samples were collected from 160 patients who had been treated with various living pig tissues up to 12 years earlier. Reverse transcription-polymerase chain reaction (RT-PCR) and protein immunoblot analyses were performed on serum from all 160 patients. No viremia was detected in any patient. Peripheral blood mononuclear cells from 159 of the patients were analyzed by PCR using PERV-specific primers. No PERV infection was detected in any of the patients from whom sufficient DNA was extracted to allow complete PCR analysis (97 percent of the patients). Persistent microchimerism (presence of donor cells in the recipient) was observed in 23 patients for up to 8.5 years.〈br /〉〈span class="detail_caption"〉Notes: 〈/span〉Paradis, K -- Langford, G -- Long, Z -- Heneine, W -- Sandstrom, P -- Switzer, W M -- Chapman, L E -- Lockey, C -- Onions, D -- Otto, E -- New York, N.Y. -- Science. 1999 Aug 20;285(5431):1236-41.〈br /〉〈span class="detail_caption"〉Author address: 〈/span〉Imutran Ltd. (a Novartis Pharma AG company), Post Office Box 399, Cambridge CB2 2YP, UK. khazal.paradis@pharma.novartis.com〈br /〉〈span class="detail_caption"〉Record origin:〈/span〉 〈a href="http://www.ncbi.nlm.nih.gov/pubmed/10455044" target="_blank"〉PubMed〈/a〉
    Keywords: Adolescent ; Adult ; Aged ; Animals ; Antibodies, Viral/blood ; Child ; Child, Preschool ; Chimera ; DNA, Viral/analysis ; Extracorporeal Circulation ; Female ; *Gammaretrovirus/genetics/immunology/isolation & purification ; Humans ; Immunoblotting ; Islets of Langerhans Transplantation ; Male ; Middle Aged ; RNA, Viral/analysis ; Retrospective Studies ; Retroviridae Infections/diagnosis/*transmission ; Reverse Transcriptase Polymerase Chain Reaction ; Skin Transplantation ; Swine ; *Transplantation, Heterologous/adverse effects ; Tumor Virus Infections/diagnosis/*transmission ; Viremia/diagnosis ; *Zoonoses
    Print ISSN: 0036-8075
    Electronic ISSN: 1095-9203
    Topics: Biology , Chemistry and Pharmacology , Computer Science , Medicine , Natural Sciences in General , Physics
    Published by American Association for the Advancement of Science (AAAS)
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
    PAPER CURRENT
  • 7
    facet.materialart.
    Unknown
    Structure and inhibition of EV-D68, a virus that causes respiratory illness in children (2015)
    American Association for the Advancement of Science (AAAS)
    Details
    Publication Date: 2015-01-03
    Description: Enterovirus D68 (EV-D68) is a member of Picornaviridae and is a causative agent of recent outbreaks of respiratory illness in children in the United States. We report here the crystal structures of EV-D68 and its complex with pleconaril, a capsid-binding compound that had been developed as an anti-rhinovirus drug. The hydrophobic drug-binding pocket in viral protein 1 contained density that is consistent with a fatty acid of about 10 carbon atoms. This density could be displaced by pleconaril. We also showed that pleconaril inhibits EV-D68 at a half-maximal effective concentration of 430 nanomolar and might, therefore, be a possible drug candidate to alleviate EV-D68 outbreaks.〈br /〉〈br /〉〈a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4307789/" target="_blank"〉〈img src="https://static.pubmed.gov/portal/portal3rc.fcgi/4089621/img/3977009" border="0"〉〈/a〉   〈a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4307789/" target="_blank"〉This paper as free author manuscript - peer-reviewed and accepted for publication〈/a〉〈br /〉〈br /〉〈span class="detail_caption"〉Notes: 〈/span〉Liu, Yue -- Sheng, Ju -- Fokine, Andrei -- Meng, Geng -- Shin, Woong-Hee -- Long, Feng -- Kuhn, Richard J -- Kihara, Daisuke -- Rossmann, Michael G -- AI11219/AI/NIAID NIH HHS/ -- R24 GM111072/GM/NIGMS NIH HHS/ -- R37 AI011219/AI/NIAID NIH HHS/ -- RR007707/RR/NCRR NIH HHS/ -- New York, N.Y. -- Science. 2015 Jan 2;347(6217):71-4. doi: 10.1126/science.1261962.〈br /〉〈span class="detail_caption"〉Author address: 〈/span〉Department of Biological Sciences, Hockmeyer Hall of Structural Biology, 240 South Martin Jischke Drive, Purdue University, West Lafayette, IN 47907, USA. ; Department of Biological Sciences, Hockmeyer Hall of Structural Biology, 240 South Martin Jischke Drive, Purdue University, West Lafayette, IN 47907, USA. Department of Computer Science, 305 North University Street, Purdue University, West Lafayette, IN 47907, USA. ; Department of Biological Sciences, Hockmeyer Hall of Structural Biology, 240 South Martin Jischke Drive, Purdue University, West Lafayette, IN 47907, USA. mr@purdue.edu.〈br /〉〈span class="detail_caption"〉Record origin:〈/span〉 〈a href="http://www.ncbi.nlm.nih.gov/pubmed/25554786" target="_blank"〉PubMed〈/a〉
    Keywords: Antiviral Agents/*chemistry/pharmacology/therapeutic use ; Capsid/*chemistry/drug effects/ultrastructure ; Child ; Crystallography, X-Ray ; Enterovirus D, Human/*chemistry/drug effects/ultrastructure ; Enterovirus Infections/drug therapy/epidemiology/*virology ; Humans ; Hydrophobic and Hydrophilic Interactions ; Oxadiazoles/*chemistry/pharmacology/therapeutic use ; Respiratory Tract Diseases/drug therapy/epidemiology/*virology ; United States/epidemiology ; Viral Proteins/chemistry/ultrastructure
    Print ISSN: 0036-8075
    Electronic ISSN: 1095-9203
    Topics: Biology , Chemistry and Pharmacology , Computer Science , Medicine , Natural Sciences in General , Physics
    Published by American Association for the Advancement of Science (AAAS)
    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...