Neural nets and chaotic carriers /:
Neural Nets and Chaotic Carriers develops rational principles for the design of associative memories, with a view to applying these principles to models with irregularly oscillatory operation so evident in biological neural systems, and necessitated by the meaninglessness of absolute signal levels....
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Elektronisch E-Book |
| Sprache: | English |
| Veröffentlicht: |
London : Hackensack, NJ :
Imperial College Press ; Distributed by World Scientific Pub.,
©2010.
|
| Ausgabe: | 2nd ed. |
| Schriftenreihe: | Advances in computer science and engineering. Texts ;
v. 5. |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Zusammenfassung: | Neural Nets and Chaotic Carriers develops rational principles for the design of associative memories, with a view to applying these principles to models with irregularly oscillatory operation so evident in biological neural systems, and necessitated by the meaninglessness of absolute signal levels. Design is based on the criterion that an associative memory must be able to cope with "fading data", i.e., to form an inference from the data even as its memory of that data degrades. The resultant net shows striking biological parallels. When these principles are combined with the Freeman specification of a neural oscillator, some remarkable effects emerge. For example, the commonly-observed phenomenon of neuronal bursting appears, with gamma-range oscillation modulated by a low-frequency square-wave oscillation (the "escapement oscillation"). Bridging studies and new results of artificial and biological neural networks, the book has a strong research character. It is, on the other hand, accessible to non-specialists for its concise exposition on the basics |
| Beschreibung: | 1 online resource (xii, 230 pages) : illustrations |
| Bibliographie: | Includes bibliographical references and index. |
| ISBN: | 9781848165915 1848165919 |
Internformat
MARC
| LEADER | 00000cam a2200000 a 4500 | ||
|---|---|---|---|
| 001 | ZDB-4-EBA-ocn738439505 | ||
| 003 | OCoLC | ||
| 005 | 20241004212047.0 | ||
| 006 | m o d | ||
| 007 | cr cnu---unuuu | ||
| 008 | 110705s2010 enka ob 001 0 eng d | ||
| 040 | |a N$T |b eng |e pn |c N$T |d EBLCP |d E7B |d CDX |d STF |d OCLCQ |d UIU |d OCLCA |d OCLCQ |d DEBSZ |d OCLCQ |d OCLCF |d YDXCP |d OCLCQ |d AZK |d LOA |d JBG |d AGLDB |d MOR |d PIFAG |d ZCU |d MERUC |d OCLCQ |d U3W |d WRM |d OCLCQ |d VTS |d NRAMU |d ICG |d INT |d VT2 |d AU@ |d OCLCQ |d WYU |d OCLCQ |d DKC |d OCLCQ |d M8D |d UKAHL |d OCLCQ |d LEAUB |d UKCRE |d AJS |d OCLCQ |d OCLCO |d OCLCQ |d OCLCO |d OCLCL |d SXB |d OCLCQ | ||
| 015 | |a GBB079618 |2 bnb | ||
| 016 | 7 | |a 015590378 |2 Uk | |
| 019 | |a 754711935 |a 961690545 |a 962724739 |a 966210898 |a 988479329 |a 991927617 |a 1037735130 |a 1038619253 |a 1045447254 |a 1055324124 |a 1058513826 |a 1058780394 |a 1065845545 |a 1081291302 |a 1086423073 |a 1153519555 |a 1228558347 | ||
| 020 | |a 9781848165915 |q (electronic bk.) | ||
| 020 | |a 1848165919 |q (electronic bk.) | ||
| 020 | |z 9781848165908 | ||
| 020 | |z 1848165900 | ||
| 035 | |a (OCoLC)738439505 |z (OCoLC)754711935 |z (OCoLC)961690545 |z (OCoLC)962724739 |z (OCoLC)966210898 |z (OCoLC)988479329 |z (OCoLC)991927617 |z (OCoLC)1037735130 |z (OCoLC)1038619253 |z (OCoLC)1045447254 |z (OCoLC)1055324124 |z (OCoLC)1058513826 |z (OCoLC)1058780394 |z (OCoLC)1065845545 |z (OCoLC)1081291302 |z (OCoLC)1086423073 |z (OCoLC)1153519555 |z (OCoLC)1228558347 | ||
| 050 | 4 | |a QA76.87 |b .W46 2010eb | |
| 072 | 7 | |a COM |x 044000 |2 bisacsh | |
| 082 | 7 | |a 006.32 |2 22 | |
| 049 | |a MAIN | ||
| 100 | 1 | |a Whittle, Peter, |d 1927- |1 https://id.oclc.org/worldcat/entity/E39PBJcWpMGMGMcpxPXFDVmjmd |0 http://id.loc.gov/authorities/names/n81099090 | |
| 245 | 1 | 0 | |a Neural nets and chaotic carriers / |c Peter Whittle. |
| 250 | |a 2nd ed. | ||
| 260 | |a London : |b Imperial College Press ; |a Hackensack, NJ : |b Distributed by World Scientific Pub., |c ©2010. | ||
| 300 | |a 1 online resource (xii, 230 pages) : |b illustrations | ||
| 336 | |a text |b txt |2 rdacontent | ||
| 337 | |a computer |b c |2 rdamedia | ||
| 338 | |a online resource |b cr |2 rdacarrier | ||
| 490 | 1 | |a Advances in computer science and engineering: Texts ; |v v. 5 | |
| 504 | |a Includes bibliographical references and index. | ||
| 505 | 0 | |a 1. Introduction and aspirations -- 2. Optimal statistical procedures. 2.1. The optimisation of actions. 2.2. Effective estimation of state. 2.3. The quadratic/Gaussian case : estimation and certainty equivalence. 2.4 The linear model, in Bayesian and classic versions -- 3. Linear links and nonlinear knots : The basic neural net. 3.1. Neural calculations : The linear gate and the McCulloch-Pitts net. 3.2. Sigmoid and threshold functions. 3.3. Iteration. 3.4. Neural systems and feedback in continuous time. 3.5. Equilibrium excitation patterns. 3.6. Some special-purpose nets -- 4. Bifurcations and chaos. 4.1. The Hopf bifurcation. 4.2. Chaos -- 5. What is a memory? The Hamming and Hopfield nets. 5.1. Associative memories. 5.2. The Hamming net. 5.3. Autoassociation, feedback and storage. 5.4. The Hopfield net. 5.5. Alternative formulations of the Hopfield net -- 6. Compound and 'spurious' traces. 6.1. Performance and trace structure. 6.2. The recognition of simple traces. 6.3. Inference for compound traces. 6.4. Network realisation of the quantised regression. 6.5. Reliability constraints for the quantised regression. 6.6. Stability constraints for the quantised regression. 6.7. The Hopfield net -- 7. Preserving plasticity : A Bayesian approach. 7.1. A Bayesian view. 7.2. A robust estimation method. 7.3. Dynamic and neural versions of the algorithm -- 8. The key task : the fixing of fading data. Conclusions I. 8.1. Fading data, and the need for quantisation. 8.2. The probability-maximising algorithm (PMA). 8.3. Properties of the vector activation function F(z). 8.4. Some special cases. 8.5. The network realisation of the full PMA. 8.6. Neural implementation of the PMA. 8.7. The PMA and the exponential family. 8.8. Conclusions I -- 9. Performance of the probability-maximising algorithm. 9.1. A general formulation. 9.2. Considerations for reliable inference. 9.3. Performance of the PMA for simple stimuli. 9.4. Compound stimuli : The general pattern. 9. 5. Compound stimuli in the Gaussian case -- 10. Other memories -- other considerations. 10.1. The supervised learning of a linear relation. 10.2. Unsupervised learning : The criterion of economy. | |
| 520 | |a Neural Nets and Chaotic Carriers develops rational principles for the design of associative memories, with a view to applying these principles to models with irregularly oscillatory operation so evident in biological neural systems, and necessitated by the meaninglessness of absolute signal levels. Design is based on the criterion that an associative memory must be able to cope with "fading data", i.e., to form an inference from the data even as its memory of that data degrades. The resultant net shows striking biological parallels. When these principles are combined with the Freeman specification of a neural oscillator, some remarkable effects emerge. For example, the commonly-observed phenomenon of neuronal bursting appears, with gamma-range oscillation modulated by a low-frequency square-wave oscillation (the "escapement oscillation"). Bridging studies and new results of artificial and biological neural networks, the book has a strong research character. It is, on the other hand, accessible to non-specialists for its concise exposition on the basics | ||
| 588 | 0 | |a Print version record. | |
| 650 | 0 | |a Neural networks (Computer science) |0 http://id.loc.gov/authorities/subjects/sh90001937 | |
| 650 | 0 | |a Chaotic behavior in systems. |0 http://id.loc.gov/authorities/subjects/sh85022562 | |
| 650 | 2 | |a Neural Networks, Computer |0 https://id.nlm.nih.gov/mesh/D016571 | |
| 650 | 6 | |a Réseaux neuronaux (Informatique) | |
| 650 | 6 | |a Chaos. | |
| 650 | 7 | |a COMPUTERS |x Neural Networks. |2 bisacsh | |
| 650 | 7 | |a Chaotic behavior in systems |2 fast | |
| 650 | 7 | |a Neural networks (Computer science) |2 fast | |
| 776 | 0 | 8 | |i Print version: |a Whittle, Peter, 1927- |t Neural nets and chaotic carriers. |b 2nd ed. |d London : Imperial College Press ; Hackensack, NJ : Distributed by World Scientific Pub., ©2010 |z 9781848165908 |w (OCoLC)645707637 |
| 830 | 0 | |a Advances in computer science and engineering. |p Texts ; |v v. 5. |0 http://id.loc.gov/authorities/names/no2007041420 | |
| 856 | 4 | 0 | |l FWS01 |p ZDB-4-EBA |q FWS_PDA_EBA |u https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=374799 |3 Volltext |
| 938 | |a Askews and Holts Library Services |b ASKH |n AH24682659 | ||
| 938 | |a Coutts Information Services |b COUT |n 18078458 | ||
| 938 | |a EBL - Ebook Library |b EBLB |n EBL731354 | ||
| 938 | |a ebrary |b EBRY |n ebr10479953 | ||
| 938 | |a EBSCOhost |b EBSC |n 374799 | ||
| 938 | |a YBP Library Services |b YANK |n 6964868 | ||
| 994 | |a 92 |b GEBAY | ||
| 912 | |a ZDB-4-EBA | ||
| 049 | |a DE-863 | ||
Datensatz im Suchindex
| DE-BY-FWS_katkey | ZDB-4-EBA-ocn738439505 |
|---|---|
| _version_ | 1816881763900719104 |
| adam_text | |
| any_adam_object | |
| author | Whittle, Peter, 1927- |
| author_GND | http://id.loc.gov/authorities/names/n81099090 |
| author_facet | Whittle, Peter, 1927- |
| author_role | |
| author_sort | Whittle, Peter, 1927- |
| author_variant | p w pw |
| building | Verbundindex |
| bvnumber | localFWS |
| callnumber-first | Q - Science |
| callnumber-label | QA76 |
| callnumber-raw | QA76.87 .W46 2010eb |
| callnumber-search | QA76.87 .W46 2010eb |
| callnumber-sort | QA 276.87 W46 42010EB |
| callnumber-subject | QA - Mathematics |
| collection | ZDB-4-EBA |
| contents | 1. Introduction and aspirations -- 2. Optimal statistical procedures. 2.1. The optimisation of actions. 2.2. Effective estimation of state. 2.3. The quadratic/Gaussian case : estimation and certainty equivalence. 2.4 The linear model, in Bayesian and classic versions -- 3. Linear links and nonlinear knots : The basic neural net. 3.1. Neural calculations : The linear gate and the McCulloch-Pitts net. 3.2. Sigmoid and threshold functions. 3.3. Iteration. 3.4. Neural systems and feedback in continuous time. 3.5. Equilibrium excitation patterns. 3.6. Some special-purpose nets -- 4. Bifurcations and chaos. 4.1. The Hopf bifurcation. 4.2. Chaos -- 5. What is a memory? The Hamming and Hopfield nets. 5.1. Associative memories. 5.2. The Hamming net. 5.3. Autoassociation, feedback and storage. 5.4. The Hopfield net. 5.5. Alternative formulations of the Hopfield net -- 6. Compound and 'spurious' traces. 6.1. Performance and trace structure. 6.2. The recognition of simple traces. 6.3. Inference for compound traces. 6.4. Network realisation of the quantised regression. 6.5. Reliability constraints for the quantised regression. 6.6. Stability constraints for the quantised regression. 6.7. The Hopfield net -- 7. Preserving plasticity : A Bayesian approach. 7.1. A Bayesian view. 7.2. A robust estimation method. 7.3. Dynamic and neural versions of the algorithm -- 8. The key task : the fixing of fading data. Conclusions I. 8.1. Fading data, and the need for quantisation. 8.2. The probability-maximising algorithm (PMA). 8.3. Properties of the vector activation function F(z). 8.4. Some special cases. 8.5. The network realisation of the full PMA. 8.6. Neural implementation of the PMA. 8.7. The PMA and the exponential family. 8.8. Conclusions I -- 9. Performance of the probability-maximising algorithm. 9.1. A general formulation. 9.2. Considerations for reliable inference. 9.3. Performance of the PMA for simple stimuli. 9.4. Compound stimuli : The general pattern. 9. 5. Compound stimuli in the Gaussian case -- 10. Other memories -- other considerations. 10.1. The supervised learning of a linear relation. 10.2. Unsupervised learning : The criterion of economy. |
| ctrlnum | (OCoLC)738439505 |
| dewey-full | 006.32 |
| dewey-hundreds | 000 - Computer science, information, general works |
| dewey-ones | 006 - Special computer methods |
| dewey-raw | 006.32 |
| dewey-search | 006.32 |
| dewey-sort | 16.32 |
| dewey-tens | 000 - Computer science, information, general works |
| discipline | Informatik |
| edition | 2nd ed. |
| format | Electronic eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>06751cam a2200625 a 4500</leader><controlfield tag="001">ZDB-4-EBA-ocn738439505</controlfield><controlfield tag="003">OCoLC</controlfield><controlfield tag="005">20241004212047.0</controlfield><controlfield tag="006">m o d </controlfield><controlfield tag="007">cr cnu---unuuu</controlfield><controlfield tag="008">110705s2010 enka ob 001 0 eng d</controlfield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">N$T</subfield><subfield code="b">eng</subfield><subfield code="e">pn</subfield><subfield code="c">N$T</subfield><subfield code="d">EBLCP</subfield><subfield code="d">E7B</subfield><subfield code="d">CDX</subfield><subfield code="d">STF</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">UIU</subfield><subfield code="d">OCLCA</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">DEBSZ</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">OCLCF</subfield><subfield code="d">YDXCP</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">AZK</subfield><subfield code="d">LOA</subfield><subfield code="d">JBG</subfield><subfield code="d">AGLDB</subfield><subfield code="d">MOR</subfield><subfield code="d">PIFAG</subfield><subfield code="d">ZCU</subfield><subfield code="d">MERUC</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">U3W</subfield><subfield code="d">WRM</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">VTS</subfield><subfield code="d">NRAMU</subfield><subfield code="d">ICG</subfield><subfield code="d">INT</subfield><subfield code="d">VT2</subfield><subfield code="d">AU@</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">WYU</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">DKC</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">M8D</subfield><subfield code="d">UKAHL</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">LEAUB</subfield><subfield code="d">UKCRE</subfield><subfield code="d">AJS</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">OCLCO</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">OCLCO</subfield><subfield code="d">OCLCL</subfield><subfield code="d">SXB</subfield><subfield code="d">OCLCQ</subfield></datafield><datafield tag="015" ind1=" " ind2=" "><subfield code="a">GBB079618</subfield><subfield code="2">bnb</subfield></datafield><datafield tag="016" ind1="7" ind2=" "><subfield code="a">015590378</subfield><subfield code="2">Uk</subfield></datafield><datafield tag="019" ind1=" " ind2=" "><subfield code="a">754711935</subfield><subfield code="a">961690545</subfield><subfield code="a">962724739</subfield><subfield code="a">966210898</subfield><subfield code="a">988479329</subfield><subfield code="a">991927617</subfield><subfield code="a">1037735130</subfield><subfield code="a">1038619253</subfield><subfield code="a">1045447254</subfield><subfield code="a">1055324124</subfield><subfield code="a">1058513826</subfield><subfield code="a">1058780394</subfield><subfield code="a">1065845545</subfield><subfield code="a">1081291302</subfield><subfield code="a">1086423073</subfield><subfield code="a">1153519555</subfield><subfield code="a">1228558347</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781848165915</subfield><subfield code="q">(electronic bk.)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">1848165919</subfield><subfield code="q">(electronic bk.)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="z">9781848165908</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="z">1848165900</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)738439505</subfield><subfield code="z">(OCoLC)754711935</subfield><subfield code="z">(OCoLC)961690545</subfield><subfield code="z">(OCoLC)962724739</subfield><subfield code="z">(OCoLC)966210898</subfield><subfield code="z">(OCoLC)988479329</subfield><subfield code="z">(OCoLC)991927617</subfield><subfield code="z">(OCoLC)1037735130</subfield><subfield code="z">(OCoLC)1038619253</subfield><subfield code="z">(OCoLC)1045447254</subfield><subfield code="z">(OCoLC)1055324124</subfield><subfield code="z">(OCoLC)1058513826</subfield><subfield code="z">(OCoLC)1058780394</subfield><subfield code="z">(OCoLC)1065845545</subfield><subfield code="z">(OCoLC)1081291302</subfield><subfield code="z">(OCoLC)1086423073</subfield><subfield code="z">(OCoLC)1153519555</subfield><subfield code="z">(OCoLC)1228558347</subfield></datafield><datafield tag="050" ind1=" " ind2="4"><subfield code="a">QA76.87</subfield><subfield code="b">.W46 2010eb</subfield></datafield><datafield tag="072" ind1=" " ind2="7"><subfield code="a">COM</subfield><subfield code="x">044000</subfield><subfield code="2">bisacsh</subfield></datafield><datafield tag="082" ind1="7" ind2=" "><subfield code="a">006.32</subfield><subfield code="2">22</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">MAIN</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Whittle, Peter,</subfield><subfield code="d">1927-</subfield><subfield code="1">https://id.oclc.org/worldcat/entity/E39PBJcWpMGMGMcpxPXFDVmjmd</subfield><subfield code="0">http://id.loc.gov/authorities/names/n81099090</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Neural nets and chaotic carriers /</subfield><subfield code="c">Peter Whittle.</subfield></datafield><datafield tag="250" ind1=" " ind2=" "><subfield code="a">2nd ed.</subfield></datafield><datafield tag="260" ind1=" " ind2=" "><subfield code="a">London :</subfield><subfield code="b">Imperial College Press ;</subfield><subfield code="a">Hackensack, NJ :</subfield><subfield code="b">Distributed by World Scientific Pub.,</subfield><subfield code="c">©2010.</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 online resource (xii, 230 pages) :</subfield><subfield code="b">illustrations</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">computer</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">online resource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Advances in computer science and engineering: Texts ;</subfield><subfield code="v">v. 5</subfield></datafield><datafield tag="504" ind1=" " ind2=" "><subfield code="a">Includes bibliographical references and index.</subfield></datafield><datafield tag="505" ind1="0" ind2=" "><subfield code="a">1. Introduction and aspirations -- 2. Optimal statistical procedures. 2.1. The optimisation of actions. 2.2. Effective estimation of state. 2.3. The quadratic/Gaussian case : estimation and certainty equivalence. 2.4 The linear model, in Bayesian and classic versions -- 3. Linear links and nonlinear knots : The basic neural net. 3.1. Neural calculations : The linear gate and the McCulloch-Pitts net. 3.2. Sigmoid and threshold functions. 3.3. Iteration. 3.4. Neural systems and feedback in continuous time. 3.5. Equilibrium excitation patterns. 3.6. Some special-purpose nets -- 4. Bifurcations and chaos. 4.1. The Hopf bifurcation. 4.2. Chaos -- 5. What is a memory? The Hamming and Hopfield nets. 5.1. Associative memories. 5.2. The Hamming net. 5.3. Autoassociation, feedback and storage. 5.4. The Hopfield net. 5.5. Alternative formulations of the Hopfield net -- 6. Compound and 'spurious' traces. 6.1. Performance and trace structure. 6.2. The recognition of simple traces. 6.3. Inference for compound traces. 6.4. Network realisation of the quantised regression. 6.5. Reliability constraints for the quantised regression. 6.6. Stability constraints for the quantised regression. 6.7. The Hopfield net -- 7. Preserving plasticity : A Bayesian approach. 7.1. A Bayesian view. 7.2. A robust estimation method. 7.3. Dynamic and neural versions of the algorithm -- 8. The key task : the fixing of fading data. Conclusions I. 8.1. Fading data, and the need for quantisation. 8.2. The probability-maximising algorithm (PMA). 8.3. Properties of the vector activation function F(z). 8.4. Some special cases. 8.5. The network realisation of the full PMA. 8.6. Neural implementation of the PMA. 8.7. The PMA and the exponential family. 8.8. Conclusions I -- 9. Performance of the probability-maximising algorithm. 9.1. A general formulation. 9.2. Considerations for reliable inference. 9.3. Performance of the PMA for simple stimuli. 9.4. Compound stimuli : The general pattern. 9. 5. Compound stimuli in the Gaussian case -- 10. Other memories -- other considerations. 10.1. The supervised learning of a linear relation. 10.2. Unsupervised learning : The criterion of economy.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Neural Nets and Chaotic Carriers develops rational principles for the design of associative memories, with a view to applying these principles to models with irregularly oscillatory operation so evident in biological neural systems, and necessitated by the meaninglessness of absolute signal levels. Design is based on the criterion that an associative memory must be able to cope with "fading data", i.e., to form an inference from the data even as its memory of that data degrades. The resultant net shows striking biological parallels. When these principles are combined with the Freeman specification of a neural oscillator, some remarkable effects emerge. For example, the commonly-observed phenomenon of neuronal bursting appears, with gamma-range oscillation modulated by a low-frequency square-wave oscillation (the "escapement oscillation"). Bridging studies and new results of artificial and biological neural networks, the book has a strong research character. It is, on the other hand, accessible to non-specialists for its concise exposition on the basics</subfield></datafield><datafield tag="588" ind1="0" ind2=" "><subfield code="a">Print version record.</subfield></datafield><datafield tag="650" ind1=" " ind2="0"><subfield code="a">Neural networks (Computer science)</subfield><subfield code="0">http://id.loc.gov/authorities/subjects/sh90001937</subfield></datafield><datafield tag="650" ind1=" " ind2="0"><subfield code="a">Chaotic behavior in systems.</subfield><subfield code="0">http://id.loc.gov/authorities/subjects/sh85022562</subfield></datafield><datafield tag="650" ind1=" " ind2="2"><subfield code="a">Neural Networks, Computer</subfield><subfield code="0">https://id.nlm.nih.gov/mesh/D016571</subfield></datafield><datafield tag="650" ind1=" " ind2="6"><subfield code="a">Réseaux neuronaux (Informatique)</subfield></datafield><datafield tag="650" ind1=" " ind2="6"><subfield code="a">Chaos.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">COMPUTERS</subfield><subfield code="x">Neural Networks.</subfield><subfield code="2">bisacsh</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Chaotic behavior in systems</subfield><subfield code="2">fast</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Neural networks (Computer science)</subfield><subfield code="2">fast</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Print version:</subfield><subfield code="a">Whittle, Peter, 1927-</subfield><subfield code="t">Neural nets and chaotic carriers.</subfield><subfield code="b">2nd ed.</subfield><subfield code="d">London : Imperial College Press ; Hackensack, NJ : Distributed by World Scientific Pub., ©2010</subfield><subfield code="z">9781848165908</subfield><subfield code="w">(OCoLC)645707637</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">Advances in computer science and engineering.</subfield><subfield code="p">Texts ;</subfield><subfield code="v">v. 5.</subfield><subfield code="0">http://id.loc.gov/authorities/names/no2007041420</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="l">FWS01</subfield><subfield code="p">ZDB-4-EBA</subfield><subfield code="q">FWS_PDA_EBA</subfield><subfield code="u">https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=374799</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">Askews and Holts Library Services</subfield><subfield code="b">ASKH</subfield><subfield code="n">AH24682659</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">Coutts Information Services</subfield><subfield code="b">COUT</subfield><subfield code="n">18078458</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">EBL - Ebook Library</subfield><subfield code="b">EBLB</subfield><subfield code="n">EBL731354</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">ebrary</subfield><subfield code="b">EBRY</subfield><subfield code="n">ebr10479953</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">EBSCOhost</subfield><subfield code="b">EBSC</subfield><subfield code="n">374799</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">YBP Library Services</subfield><subfield code="b">YANK</subfield><subfield code="n">6964868</subfield></datafield><datafield tag="994" ind1=" " ind2=" "><subfield code="a">92</subfield><subfield code="b">GEBAY</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-4-EBA</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-863</subfield></datafield></record></collection> |
| id | ZDB-4-EBA-ocn738439505 |
| illustrated | Illustrated |
| indexdate | 2024-11-27T13:17:54Z |
| institution | BVB |
| isbn | 9781848165915 1848165919 |
| language | English |
| oclc_num | 738439505 |
| open_access_boolean | |
| owner | MAIN DE-863 DE-BY-FWS |
| owner_facet | MAIN DE-863 DE-BY-FWS |
| physical | 1 online resource (xii, 230 pages) : illustrations |
| psigel | ZDB-4-EBA |
| publishDate | 2010 |
| publishDateSearch | 2010 |
| publishDateSort | 2010 |
| publisher | Imperial College Press ; Distributed by World Scientific Pub., |
| record_format | marc |
| series | Advances in computer science and engineering. Texts ; |
| series2 | Advances in computer science and engineering: Texts ; |
| spelling | Whittle, Peter, 1927- https://id.oclc.org/worldcat/entity/E39PBJcWpMGMGMcpxPXFDVmjmd http://id.loc.gov/authorities/names/n81099090 Neural nets and chaotic carriers / Peter Whittle. 2nd ed. London : Imperial College Press ; Hackensack, NJ : Distributed by World Scientific Pub., ©2010. 1 online resource (xii, 230 pages) : illustrations text txt rdacontent computer c rdamedia online resource cr rdacarrier Advances in computer science and engineering: Texts ; v. 5 Includes bibliographical references and index. 1. Introduction and aspirations -- 2. Optimal statistical procedures. 2.1. The optimisation of actions. 2.2. Effective estimation of state. 2.3. The quadratic/Gaussian case : estimation and certainty equivalence. 2.4 The linear model, in Bayesian and classic versions -- 3. Linear links and nonlinear knots : The basic neural net. 3.1. Neural calculations : The linear gate and the McCulloch-Pitts net. 3.2. Sigmoid and threshold functions. 3.3. Iteration. 3.4. Neural systems and feedback in continuous time. 3.5. Equilibrium excitation patterns. 3.6. Some special-purpose nets -- 4. Bifurcations and chaos. 4.1. The Hopf bifurcation. 4.2. Chaos -- 5. What is a memory? The Hamming and Hopfield nets. 5.1. Associative memories. 5.2. The Hamming net. 5.3. Autoassociation, feedback and storage. 5.4. The Hopfield net. 5.5. Alternative formulations of the Hopfield net -- 6. Compound and 'spurious' traces. 6.1. Performance and trace structure. 6.2. The recognition of simple traces. 6.3. Inference for compound traces. 6.4. Network realisation of the quantised regression. 6.5. Reliability constraints for the quantised regression. 6.6. Stability constraints for the quantised regression. 6.7. The Hopfield net -- 7. Preserving plasticity : A Bayesian approach. 7.1. A Bayesian view. 7.2. A robust estimation method. 7.3. Dynamic and neural versions of the algorithm -- 8. The key task : the fixing of fading data. Conclusions I. 8.1. Fading data, and the need for quantisation. 8.2. The probability-maximising algorithm (PMA). 8.3. Properties of the vector activation function F(z). 8.4. Some special cases. 8.5. The network realisation of the full PMA. 8.6. Neural implementation of the PMA. 8.7. The PMA and the exponential family. 8.8. Conclusions I -- 9. Performance of the probability-maximising algorithm. 9.1. A general formulation. 9.2. Considerations for reliable inference. 9.3. Performance of the PMA for simple stimuli. 9.4. Compound stimuli : The general pattern. 9. 5. Compound stimuli in the Gaussian case -- 10. Other memories -- other considerations. 10.1. The supervised learning of a linear relation. 10.2. Unsupervised learning : The criterion of economy. Neural Nets and Chaotic Carriers develops rational principles for the design of associative memories, with a view to applying these principles to models with irregularly oscillatory operation so evident in biological neural systems, and necessitated by the meaninglessness of absolute signal levels. Design is based on the criterion that an associative memory must be able to cope with "fading data", i.e., to form an inference from the data even as its memory of that data degrades. The resultant net shows striking biological parallels. When these principles are combined with the Freeman specification of a neural oscillator, some remarkable effects emerge. For example, the commonly-observed phenomenon of neuronal bursting appears, with gamma-range oscillation modulated by a low-frequency square-wave oscillation (the "escapement oscillation"). Bridging studies and new results of artificial and biological neural networks, the book has a strong research character. It is, on the other hand, accessible to non-specialists for its concise exposition on the basics Print version record. Neural networks (Computer science) http://id.loc.gov/authorities/subjects/sh90001937 Chaotic behavior in systems. http://id.loc.gov/authorities/subjects/sh85022562 Neural Networks, Computer https://id.nlm.nih.gov/mesh/D016571 Réseaux neuronaux (Informatique) Chaos. COMPUTERS Neural Networks. bisacsh Chaotic behavior in systems fast Neural networks (Computer science) fast Print version: Whittle, Peter, 1927- Neural nets and chaotic carriers. 2nd ed. London : Imperial College Press ; Hackensack, NJ : Distributed by World Scientific Pub., ©2010 9781848165908 (OCoLC)645707637 Advances in computer science and engineering. Texts ; v. 5. http://id.loc.gov/authorities/names/no2007041420 FWS01 ZDB-4-EBA FWS_PDA_EBA https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=374799 Volltext |
| spellingShingle | Whittle, Peter, 1927- Neural nets and chaotic carriers / Advances in computer science and engineering. Texts ; 1. Introduction and aspirations -- 2. Optimal statistical procedures. 2.1. The optimisation of actions. 2.2. Effective estimation of state. 2.3. The quadratic/Gaussian case : estimation and certainty equivalence. 2.4 The linear model, in Bayesian and classic versions -- 3. Linear links and nonlinear knots : The basic neural net. 3.1. Neural calculations : The linear gate and the McCulloch-Pitts net. 3.2. Sigmoid and threshold functions. 3.3. Iteration. 3.4. Neural systems and feedback in continuous time. 3.5. Equilibrium excitation patterns. 3.6. Some special-purpose nets -- 4. Bifurcations and chaos. 4.1. The Hopf bifurcation. 4.2. Chaos -- 5. What is a memory? The Hamming and Hopfield nets. 5.1. Associative memories. 5.2. The Hamming net. 5.3. Autoassociation, feedback and storage. 5.4. The Hopfield net. 5.5. Alternative formulations of the Hopfield net -- 6. Compound and 'spurious' traces. 6.1. Performance and trace structure. 6.2. The recognition of simple traces. 6.3. Inference for compound traces. 6.4. Network realisation of the quantised regression. 6.5. Reliability constraints for the quantised regression. 6.6. Stability constraints for the quantised regression. 6.7. The Hopfield net -- 7. Preserving plasticity : A Bayesian approach. 7.1. A Bayesian view. 7.2. A robust estimation method. 7.3. Dynamic and neural versions of the algorithm -- 8. The key task : the fixing of fading data. Conclusions I. 8.1. Fading data, and the need for quantisation. 8.2. The probability-maximising algorithm (PMA). 8.3. Properties of the vector activation function F(z). 8.4. Some special cases. 8.5. The network realisation of the full PMA. 8.6. Neural implementation of the PMA. 8.7. The PMA and the exponential family. 8.8. Conclusions I -- 9. Performance of the probability-maximising algorithm. 9.1. A general formulation. 9.2. Considerations for reliable inference. 9.3. Performance of the PMA for simple stimuli. 9.4. Compound stimuli : The general pattern. 9. 5. Compound stimuli in the Gaussian case -- 10. Other memories -- other considerations. 10.1. The supervised learning of a linear relation. 10.2. Unsupervised learning : The criterion of economy. Neural networks (Computer science) http://id.loc.gov/authorities/subjects/sh90001937 Chaotic behavior in systems. http://id.loc.gov/authorities/subjects/sh85022562 Neural Networks, Computer https://id.nlm.nih.gov/mesh/D016571 Réseaux neuronaux (Informatique) Chaos. COMPUTERS Neural Networks. bisacsh Chaotic behavior in systems fast Neural networks (Computer science) fast |
| subject_GND | http://id.loc.gov/authorities/subjects/sh90001937 http://id.loc.gov/authorities/subjects/sh85022562 https://id.nlm.nih.gov/mesh/D016571 |
| title | Neural nets and chaotic carriers / |
| title_auth | Neural nets and chaotic carriers / |
| title_exact_search | Neural nets and chaotic carriers / |
| title_full | Neural nets and chaotic carriers / Peter Whittle. |
| title_fullStr | Neural nets and chaotic carriers / Peter Whittle. |
| title_full_unstemmed | Neural nets and chaotic carriers / Peter Whittle. |
| title_short | Neural nets and chaotic carriers / |
| title_sort | neural nets and chaotic carriers |
| topic | Neural networks (Computer science) http://id.loc.gov/authorities/subjects/sh90001937 Chaotic behavior in systems. http://id.loc.gov/authorities/subjects/sh85022562 Neural Networks, Computer https://id.nlm.nih.gov/mesh/D016571 Réseaux neuronaux (Informatique) Chaos. COMPUTERS Neural Networks. bisacsh Chaotic behavior in systems fast Neural networks (Computer science) fast |
| topic_facet | Neural networks (Computer science) Chaotic behavior in systems. Neural Networks, Computer Réseaux neuronaux (Informatique) Chaos. COMPUTERS Neural Networks. Chaotic behavior in systems |
| url | https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=374799 |
| work_keys_str_mv | AT whittlepeter neuralnetsandchaoticcarriers |