Abstract:
Stability and encoding properties of two-layer nonlinear feedback neural networks are examined. Bidirectionality is introduced in neural nets to produce two-way associati...Show MoreMetadata
Abstract:
Stability and encoding properties of two-layer nonlinear feedback neural networks are examined. Bidirectionality is introduced in neural nets to produce two-way associative search for stored associations. The bidirectional associative memory (BAM) is the minimal two-layer nonlinear feedback network. The author proves that every n-by-p matrix M is a bidirectionally stable heteroassociative content-addressable memory for both binary/bipolar and continuous neurons. When the BAM neutrons are activated, the network quickly evolves to a stable state of two-pattern reverberation, or resonance. The stable reverberation corresponds to a system energy local minimum. Heteroassociative information is encoded in a BAM by summing correlation matrices. The BAM storage capacity for reliable recall is roughly m
Published in: IEEE Transactions on Systems, Man, and Cybernetics ( Volume: 18, Issue: 1, Jan.-Feb. 1988)
DOI: 10.1109/21.87054
References is not available for this document.
Select All
1.
S. Amari, K. Yoshida and K. Kanatani, "A mathematical foundation for statistical neurodynamics", STAM J. Appl. Math, vol. 33, no. 1, pp. 95-126, July 1977.
2.
J. A. Aiiderson, "Cognitive and psychological computation with neural models", IEEE Trans. Syst. Man. Cyber., vol. SMC-13, no. 5, Sept./Oct. 1983.
3.
J. A. Anderson and M. Mozer, "Categorization and selective neurons" in Parallel Models of Associative Memory, NJ, Hillsdale:Erlbaum, 1981.
4.
J. A. Anderson, J. W. Silverstein, S. A. Ritz and R. S. Jones, "Distinctive features categorical perception and probability learning: Some applications of a neural model", Psych. Rev., vol. 84, pp. 413-451, 1977.
5.
G. A. Carpenter and S. Grossberg, "A massively parallel architecture for a self-organizing neural pattern recognition machine", Comput. Vis. Graphics Image Processing, vol. 37, pp. 54-116, 1987.
6.
G. A. Carpenter and S. Grossberg, "Associative learning adaptive pattern recognition and cooperative-competitive decision making by neural networks", Proc. SPIE: Hybrid Opt. Syst., vol. 634, pp. 218-247, 1986-Mar.
7.
M. A. Cohen and S. Grossberg, "Absolute stability of global pattern formation and parallel memory storage by competitive neural networks", IEEE Trans. Syst. Man. Cybern., vol. SMC-13, pp. 815-826, Sept./Oct. 1983.
8.
S. Grossberg, "Some nonlinear networks capable of learning a spatial pattern of arbitrary complexity", Proc. Nat. Acad. Sci., vol. 60, pp. 368-372, 1968.
9.
S. Grossberg, "On the serial learning of lists", Math. Bioscivol., vol. 4, pp. 201-253, 1969.
10.
S. Grossberg, "Some networks that can leam remember and reproduce any number of complicated space-time patterns I", J. Math. Mechan., vol. 19, pp. 53-91, 1969.
11.
"On learning of spatiotemporal patterns by networks with ordered sensory and motor components I", Stud. Appl. Math., vol. 48, pp. 105-132, 1969.
12.
"Some networks that can learn remember and reproduce any number of complicated space-time patterns II", Stud. Appl. Math., vol. 49, pp. 135-166, 1970.
13.
"Contour enhancement short term memory and constancies in reverberating neural networks", Stud. Appl. Math., vol. 52, pp. 217-257, 1973.
14.
"Adaptive pattern classification and universal recoding I: Parallel development and coding of neural feature detectors", Biol. Cybern., vol. 23, pp. 121-134, 1976.
15.
"A theory of human memory: Self-organization and performance of sensory-motor codes maps and plans" in Progress in Theoretical Biology, New York:Academic, vol. 5, 1978.
16.
"How does a brain build a cognitive code?", Psych. Rev., vol. 1, pp. 1-51, 1980.
17.
"Adaptive resonance in development perception and cognition" in Mathematical Psychology and Psychophysiology, RI, Providence:Amer. Math. Soc., 1981.
18.
Studies of Mind and Brain: Neural Principles of Learning Perception Development Cognition and Motor Control, MA, Boston:Reidel Press, 1982.
19.
S. Grossberg and M. Kuperstein, Neural Dynamics of Adaptive Sensory-Motor Control: Ballistic Eye Movements, The Netherlands, Amsterdam:North-Holland, 1986.
20.
S. Grossberg and M. A. Cohen, "Masking fields: A massively parallel neural architecture for learning recognizing and predicting multiple groupings of patterned data", Appl. Opt..
21.
R. Hecht-Nielsen, "Performance limits of optical electro-optical and electronic neurocomputers", Proc. SPIE: Hybrid Opt. Syst., pp. 277-306, 1986-Mar.
22.
Y. Hirai, "A template matching model for pattern recognition: Self-organization of template and template matching by a disinhibitory neural network", Biol. Cybern., vol. 38, pp. 91-101, 1980.
23.
Y. Hirai, "A model of human associative processor (HASP)", IEEE Trans. Syst. Man. Cybern., vol. SMC-13, no. 5, pp. 851-857, Sept./Oct. 1983.
24.
J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities", Proc. Nat. Acad. Sci. USA, vol. 79, pp. 2554-2558, 1982.
25.
J. J. Hopfield, "Neurons with graded response have collective computational properties like those of two-state neurons", Proc. Nat. Adad. Sci. USA, vol. 81, pp. 3088-3092, 1984.
26.
J. J. Hopfield and D. W. Tank, "Neural computation of decisions in optimization problems", Biol. Cybern., vol. 52, pp. 141, 1985.
27.
T. Kohonen, "Correlation matrix memories", IEEE Trans. Comput., vol. C-21, pp. 353-359, 1972.
28.
T. Kohonen, Associative Memory: A System-Theoretical Approach, Berlin:Springer-Verlag, 1977.
29.
T. Kohonen, E. Oja and P. Lehtio, "Storage and processing of information in distributed associative memory systems" in Parallel Models of Associative Memory, NJ, Hillsdale:Erlbaum, 1981.
30.
T. Kohonen, Self-Organization and Associative Memory, Berlin:Springer-Verlag, 1984.
