Library

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
  • 1995-1999  (8)
  • 1915-1919
  • 1890-1899
  • Analytical Chemistry and Spectroscopy  (3)
  • on-line learning  (3)
  • Cholecystokinin  (2)
  • 1
    Electronic Resource
    Electronic Resource
    Springer
    Machine learning 27 (1997), S. 51-68 
    ISSN: 0885-6125
    Keywords: decision trees ; pruning ; prediction ; on-line learning
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract Many algorithms for inferring a decision tree from data involve a two-phase process: First, a very large decision tree is grown which typically ends up “over-fitting” the data. To reduce over-fitting, in the second phase, the tree is pruned using one of a number of available methods. The final tree is then output and used for classification on test data. In this paper, we suggest an alternative approach to the pruning phase. Using a given unpruned decision tree, we present a new method of making predictions on test data, and we prove that our algorithm's performance will not be “much worse” (in a precise technical sense) than the predictions made by the best reasonably small pruning of the given decision tree. Thus, our procedure is guaranteed to be competitive (in terms of the quality of its predictions) with any pruning algorithm. We prove that our procedure is very efficient and highly robust. Our method can be viewed as a synthesis of two previously studied techniques. First, we apply Cesa-Bianchi et al.'s (1993) results on predicting using “expert advice” (where we view each pruning as an “expert”) to obtain an algorithm that has provably low prediction loss, but that is computationally infeasible. Next, we generalize and apply a method developed by Buntine (1990, 1992) and Willems, Shtarkov and Tjalkens (1993, 1995) to derive a very efficient implementation of this procedure.
    Type of Medium: Electronic Resource
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 2
    Electronic Resource
    Electronic Resource
    Springer
    Machine learning 22 (1996), S. 95-121 
    ISSN: 0885-6125
    Keywords: machine learning ; temporal-difference learning ; on-line learning ; worst-case analysis
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We study the behavior of a family of learning algorithms based on Sutton's method of temporal differences. In our on-line learning framework, learning takes place in a sequence of trials, and the goal of the learning algorithm is to estimate a discounted sum of all the reinforcements that will be received in the future. In this setting, we are able to prove general upper bounds on the performance of a slightly modified version of Sutton's so-called TD(λ) algorithm. These bounds are stated in terms of the performance of the best linear predictor on the given training sequence, and are proved without making any statistical assumptions of any kind about the process producing the learner's observed training sequence. We also prove lower bounds on the performance of any algorithm for this learning problem, and give a similar analysis of the closely related problem of learning to predict in a model in which the learner must produce predictions for a whole batch of observations before receiving reinforcement.
    Type of Medium: Electronic Resource
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 3
    Electronic Resource
    Electronic Resource
    Springer
    Machine learning 22 (1996), S. 95-121 
    ISSN: 0885-6125
    Keywords: machine learning ; temporal-difference learning ; on-line learning ; worst-case analysis
    Source: Springer Online Journal Archives 1860-2000
    Topics: Computer Science
    Notes: Abstract We study the behavior of a family of learning algorithms based on Sutton‘s method of temporal differences. In our on-line learning framework, learning takes place in a sequence of trials, and the goal of the learning algorithm is to estimate a discounted sum of all the reinforcements that will be received in the future. In this setting, we are able to prove general upper bounds on the performance of a slightly modified version of Sutton‘s so-called TD((gl) algorithm. These bounds are stated in terms of the performance of the best linear predictor on the given training sequence, and are proved without making any statistical assumptions of any kind about the process producing the learner‘s observed training sequence. We also prove lower bounds on the performance of any algorithm for this learning problem, and give a similar analysis of the closely related problem of learning to predict in a model in which the learner must produce predictions for a whole batch of observations before receiving reinforcement.
    Type of Medium: Electronic Resource
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 4
    Electronic Resource
    Electronic Resource
    Springer
    Naunyn-Schmiedeberg's archives of pharmacology 353 (1996), S. 693-697 
    ISSN: 1432-1912
    Keywords: Rat nodose ganglion ; Cholecystokinin ; Depolarisation ; Receptor subtypes ; Receptor antagonists
    Source: Springer Online Journal Archives 1860-2000
    Topics: Medicine
    Notes: Abstract With increased interest in the pharmacology of cholecystokininA (CCKA) receptors, including their trophic and mitogenic effects, the actions of two new non-peptide CCKA receptor antagonists, PD140548 and SR 2789713, were investigated in a convenient model system, the rat isolated nodose ganglion. CCK (1 nM-1 μM) caused concentration-dependent depolarisations when superfused over the nodose ganglion at 37° C as measured by a silicone grease gap technique, and both CCKA antagonists caused significant rightward shifts in the concentration response curve to CCK. SR 2789713 (3 and 10 nM) caused 7.9-and 17.9-fold shifts in the CCK concentration-response curve and the apparent — log KB values for each concentration of antagonist were calculated to be 9.36 and 9.23. Further experiments with PD140548 (30 and 100 nM) yielded shifts of 2.9- and 12.5-fold from which — log KB values were determined to be 7.80 and 8.06. Overall SR 2789713 was significantly more efficacious than PD140548. Thus, the isolated nodose ganglion preparation allows a functional assessment of CCKA-mediated responses, with the results indicating that both SR 27897B and PD 140548 are efficacious CCKA receptor antagonists.
    Type of Medium: Electronic Resource
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 5
    Electronic Resource
    Electronic Resource
    Springer
    Naunyn-Schmiedeberg's archives of pharmacology 353 (1996), S. 693-697 
    ISSN: 1432-1912
    Keywords: Key words Rat nodose ganglion ; Cholecystokinin ; Depolarisation ; Receptor subtypes ; Receptor antagonists
    Source: Springer Online Journal Archives 1860-2000
    Topics: Medicine
    Notes: Abstract  With increased interest in the pharmacology of cholecystokininA (CCKA) receptors, including their trophic and mitogenic effects, the actions of two new non-peptide CCKA receptor antagonists, PD140548 and SR 27897B, were investigated in a convenient model system, the rat isolated nodose ganglion. CCK (1 nM–1 μM) caused concentration-dependent depolarisations when superfused over the nodose ganglion at 37° C as measured by a silicone grease gap technique, and both CCKA antagonists caused significant rightward shifts in the concentration response curve to CCK. SR 27897B (3 and 10 nM) caused 7.9- and 17.9-fold shifts in the CCK concentration-response curve and the apparent −log KB values for each concentration of antagonist were calculated to be 9.36 and 9.23. Further experiments with PD140548 (30 and 100 nM) yielded shifts of 2.9- and 12.5-fold from which −log KB values were determined to be 7.80 and 8.06. Overall SR 27897B was significantly more efficacious than PD140548. Thus, the isolated nodose ganglion preparation allows a functional assessment of CCKA-mediated responses, with the results indicating that both SR 27897B and PD140548 are efficacious CCKA receptor antagonists.
    Type of Medium: Electronic Resource
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 6
    Electronic Resource
    Electronic Resource
    Weinheim : Wiley-Blackwell
    Journal of High Resolution Chromatography 20 (1997), S. 643-646 
    ISSN: 0935-6304
    Keywords: Capillary electrophoresis ; Electogenerated chemiluminescence ; Ru(bpy)32+ ; Tripropylamine ; Proline ; Chemistry ; Analytical Chemistry and Spectroscopy
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology
    Notes: A post- column chemiluminescent technique for thedetection of compounds that are poor chromoshores using electorogenerated chemiluminescence following separation by capillartgy electrophoresis is described. The luminrescent signal is generated followintg the reaction of anlyres (e.g. amines) with Ru(bpy)33+, which isx electrochemically generated post-columan from Ru(bpy)32+. Tripropylamine and proline are used as two model compounds to demostrate the feasibility of the method. Detection limits for the prototype system were in the micromolar rage, suggesting that this technnique offers an alternative to indirect detection of compounds that are poor chromophores with an added selectivity advangage. The system includes the use of a conductive joint to isolate the separation field from the potential necessary to drive the elctrogenerated chemiluminescent reactiion. Addition of the chemiluminescent reagent Ru(bpy)32+ post-column did not decrease the efficiency of the separation. The design and favrication of the novel cell is discussed.
    Additional Material: 2 Ill.
    Type of Medium: Electronic Resource
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 7
    Electronic Resource
    Electronic Resource
    Weinheim : Wiley-Blackwell
    Journal of High Resolution Chromatography 18 (1995), S. 495-499 
    ISSN: 0935-6304
    Keywords: SPME ; Capillary columns ; Volatile organic compounds ; Purge and trap ; Chlorinated pesticides ; Chemistry ; Analytical Chemistry and Spectroscopy
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology
    Notes: The application of SPME, a solventless extraction procedure, is demonstrated for two environmental applications. Extraction of VOCs by SPME is coupled with analysis on short narrow bore capillary gas chromatography columns. The technique is shown both as a fast screening tool and as part of an analytical procedure when combined with a mass spectrometer. Data show the linear range of the procedure. The extraction of chlorinated pesticides from hazardous wastewater and drinking water by SPME is also described in this paper. SPME is compared to traditional extraction procedures with respect to cost, time, ease of use, solvent usage, and sample usage.
    Additional Material: 5 Ill.
    Type of Medium: Electronic Resource
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 8
    ISSN: 0749-1581
    Keywords: 1H NMR ; 13C NMR ; substituted dihydronaphthalenes ; Chemistry ; Analytical Chemistry and Spectroscopy
    Source: Wiley InterScience Backfile Collection 1832-2000
    Topics: Chemistry and Pharmacology
    Notes: 1H and 13C NMR studies were carried out on the substituted dihydronaphthalene compounds 1,2-dihydro-8-isopropyl-6,7-dimethoxy-2-methylnaphthalene, 3-bromo-1, 2-dihydro-8-isopropyl-6, 7-dimethoxy-2-methylnaphthalene, 3, 4-dihydro-5-isopropyl-6, 7-dimethoxy-3-methyl-1(2H)-naphthalenone, 1, 2-dihydro-6, 7-dimethoxy-2, 8-dimethylnaphthalene, 3-bromo-1, 2-dihydro-6, 7-dimethoxy-2, 8-dimethylnaphthalene and 3, 4-dihydro-6, 7-dimethoxy-3, 5-dimethyl-1(2H)-naphthalenone. Complete assignments of the proton and carbon spectra were made using one- and two-dimensional NMR techniques including APT, COSY, NOESY and 1H-13C HETCOR spectroscopy.
    Additional Material: 4 Tab.
    Type of Medium: Electronic Resource
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...