Convergent activation dynamics in continuous time networks

Neural Networks

Volumn 2, Issue 5, 1989, Pages 331-349

  Hirsch, Morris W ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Cascade; Chaotic dynamics; Convergence; Excitatory net; Global asymptotic stability; Inhibitory net; Liapunov function

Indexed keywords

MATHEMATICAL TECHNIQUES--CONVERGENCE OF NUMERICAL METHODS;

CHAOTIC DYNAMICS; CONVERGENT DYNAMICS; EXCITATORY NET; INHIBITORY NET; LIAPUNOV FUNCTION; NEURAL NETWORK;

SYSTEMS SCIENCE AND CYBERNETICS;

EID: 0024909476     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(89)90018-X     Document Type: Review

References (76)

1. The dynamics of two interacting populations
2. A learning rule for asynchronous perceptrons with feedback in a combinatorial environment
3. Competitive and cooperative aspects in dynamics of neural excitation and self-organization
4. Characteristics of random nets of analog neuron-like elements
5. Models of certain nonlinear systems
6. Strange attractors in Volterra equations for species in competition
7. Nonlinear dynamics of pattern formation and pattern recognition in rabbit olfactory bulb
8. A bifurcation theory approach to vector field programming for periodic attractors
9. Learning to represent state
10. A massively parallel architecture for a self-organizing neural pattern recognition machine
11. Comportement asymptotique des systèmes différentiels du type “compétition d'espèces”
12. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
13. Isolated invariant sets and the Morse Index
14. About the theory of competing species
15. Asymptotic behaviors in the dynamics of competing species
16. A mathematical theory of central nervous activity
17. Pattern formation, contrast control, and oscillation in the short term memory of shunting on-center off-surround networks
18. Finding structure in time
19. Simulation of chaotic EEG patterns with a dynamic model of the olfactory system
20. EEG spatial pattern differences with discriminated odors manifest chaotic an limit cycle attractors in olfactory bulb of rabbits
21. Correlation of olfactory EEG with behavior: Time series analysis
22. Limit cycles in competition communities
23. The “brain state-in-a box” neural model is a gradient descent algorithm
24. A unified framework for connectionist systems
25. On learning and energy-entropy dependence in recurrent and nonrecurrent signed networks
26. Neural expectation: Cerebellar and retinal analogs of cells fired by learnable or unlearned pattern classes
27. Adaptive pattern classification and universal recoding, I: Parallel development and coding of neural feature detectors
28. Competition, decision, and consensus
29. Hirsch, M. W. (1980). Unpublished manuscript.
30. Systems of differential equations that are competitive or cooperative I Limit sets
31. The dynamical systems approach to differential equations
32. Systems of differential equations that are competitive or cooperative II Convergence almost everywhere
33. Convergence in Neural Nets
34. Stability and convergence in strongly monotone dynamical systems
35. Systems of differential equations that are competitive or cooperative III Competing species
36. Stable manifolds and hyperbolic sets
37. Neurons with graded response have collective computational properties like those of two-state neurons
38. A contribution to the mathematical theory of competing predators
39. Competing predators
40. Attractor dynamics and parallelism in a connectionist sequential machine
41. On the Volterra-Lotka principle
42. Stability theory for ordinary differential equations
43. Community equilibria and stability and an extension of the competitive exclusion principle
44. Species packing, or what competition minimizes
45. Self organization of orientation sensitive cells in the striate cortex
46. Nonlinear aspects of competition between three species
47. A focused back-propagation algorithm for temporal pattern recognition
48. Learning state space trajectories in recurrent neural networks: A preliminary report
49. Generalization of back propagation to recurrent and higher order neural networks
50. The utility driven dynamic error propagation network
51. Training time-dependence in neural networks
52. Learning internal representations by error propagation
53. On ω-limits for competition between three species
54. Storing covariance with nonlinearly interacting neurons
55. Learning and internal representations in recurrent networks
56. How brains make chaos in order to make sense of the world
57. On the differential equations of species in competition
58. Competitive and cooperative tridiagonal systems of differential equations
59. Systems of differential equations which generate a monotone flow. A survey of results
60. A dynamical approach to temporal pattern processing
61. A learning algorithm for continually running fully recurrent neural networks
62. Hopf bifurcations in three-dimensional competitive Volterra-Lotka systems