메뉴 건너뛰기




Volumn 3, Issue 1, 1996, Pages 11-15

Improving reinforcement learning in stochastic RAM-based neural networks

Author keywords

Hardware realisation; RAM based nodes; Reinforcement learning; Reward penalty

Indexed keywords

ALGORITHMS; COMPUTER HARDWARE; LEARNING SYSTEMS; PERFORMANCE; RANDOM ACCESS STORAGE;

EID: 0030124873     PISSN: 13704621     EISSN: None     Source Type: Journal    
DOI: 10.1007/BF00417784     Document Type: Article
Times cited : (2)

References (7)
  • 1
    • 0028762674 scopus 로고
    • Design, manufacture, and evaluation of a scalable high-performance neural system
    • 3 March
    • H. Bolouri, P. Morgan and K.N. Gurney, "Design, manufacture, and evaluation of a scalable high-performance neural system", Electronics Letters, Vol. 30 (3 March), pp. 426-427, 1994.
    • (1994) Electronics Letters , vol.30 , pp. 426-427
    • Bolouri, H.1    Morgan, P.2    Gurney, K.N.3
  • 3
    • 0006057505 scopus 로고
    • Learning in networks of structured hypercubes
    • Department of Electronical Engineering, Brunel University, UK, June
    • K.N. Gurney, "Learning in networks of structured hypercubes", Technical Memorandum CN/R/144, Department of Electronical Engineering, Brunel University, UK, June 1989.
    • (1989) Technical Memorandum CN/R/144
    • Gurney, K.N.1
  • 5
    • 0000683869 scopus 로고
    • Gradient following without back-propagation in layered networks
    • A.G. Bartlo and M.I. Jordan, "Gradient following without back-propagation in layered networks", Proc. of the Int. Conf. on Neural Networks, Vol. 2, pp. 629-636, 1987.
    • (1987) Proc. of the Int. Conf. on Neural Networks , vol.2 , pp. 629-636
    • Bartlo, A.G.1    Jordan, M.I.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.