Computational-complexity reduction for neural network algorithms

Journal Article · Tue Feb 28 23:00:00 EST 1989 · IEEE (Institute of Electrical and Electronics Engineers) Transactions on Systems, Man, and Cybernetics; (USA)

DOI:https://doi.org/10.1109/21.31043· OSTI ID:5242987

Guez, A; Kam, M ^[1]; Eilbert, J L ^[2]

---

1. Drexel Univ., Philadelphia, PA (USA). Dept. of Electrical and Computer Engineering
2. Grumman Corp., Bethpage, NY (USA)

An important class of neural models is described as a set of coupled nonlinear differential equations with state variables corresponding to the axon hillock potential of neurons. Through a nonlinear transformation, these models can be converted to an equivalent system of differential equations whose state variables correspond to firing rates. The new firing rate formulation has certain computational advantages over the potential formulation of the model. The computational and storage burdens per cycle in simulations are reduced, and the resulting equations become quasi-linear in a large significant subset of the state space. Moreover, the dynamic range of the state space is bounded, alleviating the numerical stability problems in network simulation. These advantages are demonstrated through an example, using their model for the neural solution to the traveling salesman proposed by Hopfield and Tank.

• OSTI ID: 5242987
• Journal Information: IEEE (Institute of Electrical and Electronics Engineers) Transactions on Systems, Man, and Cybernetics; (USA), Journal Name: IEEE (Institute of Electrical and Electronics Engineers) Transactions on Systems, Man, and Cybernetics; (USA) Vol. 19:2; ISSN 0018-9472; ISSN ISYMA
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ALGORITHMS
ANIMAL CELLS
ARRAY PROCESSORS
COMPUTER CALCULATIONS
COMPUTER NETWORKS
DIFFERENTIAL EQUATIONS
EQUATIONS
MATHEMATICAL LOGIC
MATHEMATICAL MODELS
NERVE CELLS
NONLINEAR PROBLEMS
PARALLEL PROCESSING
PROGRAMMING
SIMULATION
SOMATIC CELLS