An Ev01ut10nary Appr0ach t0 De519n1n9 Neura1 Netw0rk5 Av1v 8er9man Art1f1c1a1 1nte1119ence C e n t e r , 5R1 1nternat10na1, Men10 P a r k , Ca11f0rn1a 94025, a n d D e p a r t m e n t 0f 8101091ca1 5c1ence5, 5 t a n f 0 r d Un1ver51ty, Ca11f0rn1a, U.5.A. 0.1 06ject1ve5 0ne 0f the m05t 1ntere5t1n9 pr0pert1e5 0f neura1 netw0rk5 15 the1r a6111ty t0 1earn appr0pr1ate 6ehav10r 6y 6e1n9 tra1ned 0n examp1e5. E5ta6115hed 1earn1n9 a190r1thm5, wh1ch typ1ca11y w0rk 6y m1n1m121n9 err0r thr0u9h 6ackpr0pa9at10n 1n we19ht 5pace, tend t0 9et 5tuck 1n 10ca1 0pt1ma - - a tendency typ1ca1 0f 9rad1ent-de5cent meth0d5 app11ed t0 n0nc0nvex 06ject1ve funct10n5. 7heref0re, f0r pr061em5 0f n0ntr1v1a1 c0mp1ex1ty the5e 5y5tem5 mu5t 6e handcrafted t0 a 519n1f1cant de9ree, 6ut the d15tr16uted nature 0f neura1 netw0rk repre5entat10n5 make th15 handcraft1n9 d1ff1cu1t. My 90a1 15 t0 deve10p a 1earn1n9 and adaptat10n mechan15m5 capa61e 0f c0p1n9 w1th c0mp1ex and dynam1c pr061em d0ma1n5. 0nce 1 06ta1n a mach1ne that perf0rm5 a certa1n ta5k we11, 1 want t0 under5tand why 1t5 5tructure 1ead5 t0 900d perf0rmance, and there6y he1p a netw0rk de519ner t0 create even m0re 5ucce55fu1 de519n5. M0re 5pec1f1ca11y,the a1m 0f th15 pr09ram
End of preview. The entire article is 5 pages. To view the full-text, please rent this article to continue.
/lp/association-for-computing-machinery/an-evolutionary-approach-to-designing-neural-networks-UwC5noyZSr
Welcome to DeepDyve! Rent Premier Research Articles and Save Up to 90%
An evolutionary approach to designing neural networks
Bergman, Aviv
Follow ACM SIGBIO Newsletter
, Volume 12 (2)
Association for Computing Machinery – Jun 1, 1992
More Info
More Like This Article
View All dataSource[]=actageo&dataSource[]=aspet&dataSource[]=aaos&dataSource[]=aacc&dataSource[]=aacr&dataSource[]=aea&dataSource[]=aip&dataSource[]=ajnr&dataSource[]=ams&dataSource[]=aps_physical&dataSource[]=appi_book&dataSource[]=appi_journal&dataSource[]=apha&dataSource[]=asip&dataSource[]=asm&dataSource[]=asn&dataSource[]=aspb&dataSource[]=avs&dataSource[]=annual_reviews&dataSource[]=arxiv&dataSource[]=acm&dataSource[]=berghahn&dataSource[]=cabi&dataSource[]=clinical_trials&dataSource[]=dailymed&dataSource[]=degruyter&dataSource[]=du_press&dataSource[]=esa&dataSource[]=eu_press&dataSource[]=elsevier&dataSource[]=emerald&dataSource[]=ejtr&dataSource[]=emea&dataSource[]=epo&dataSource[]=faseb&dataSource[]=gsa&dataSource[]=health_affairs&dataSource[]=hindawi&dataSource[]=imanager&dataSource[]=imedpub&dataSource[]=informa_healthcare&dataSource[]=informs&dataSource[]=iop&dataSource[]=iucr&dataSource[]=iospress&dataSource[]=jbjs&dataSource[]=leftcoast&dataSource[]=lu_press&dataSource[]=mesharpe&dataSource[]=mary_ann_liebert&dataSource[]=medline&dataSource[]=mit_press&dataSource[]=nature&dataSource[]=oxford&dataSource[]=pier_professional&dataSource[]=pnas&dataSource[]=portlandpress&dataSource[]=psyc_articles&dataSource[]=psyc_books&dataSource[]=psyc_critiques&dataSource[]=plos_journal&dataSource[]=pubmed_central&dataSource[]=rsna&dataSource[]=rockefeller&dataSource[]=rcn&dataSource[]=ria&dataSource[]=rsc&dataSource[]=sage&dataSource[]=spie&dataSource[]=springer_journal&dataSource[]=springer&dataSource[]=taylor_francis&dataSource[]=aps&dataSource[]=the_scientist&dataSource[]=uc_press&dataSource[]=uspto_abstract&dataSource[]=wiley&dataSource[]=pct
© 2012 DeepDyve, Inc. All rights reserved.
Terms of Service | Privacy Policy
