Implementing plastic weights in neural networks using low precision arithmetic

Neurocomputing

Volumn 72, Issue 4-6, 2009, Pages 968-972

  Johansson, Christopher ^a   Lansner, Anders ^a  

^a ROYAL INSTITUTE OF TECHNOLOGY   (Sweden)

Author keywords

Exponentially weighted moving average; Fixed point arithmetic; Leaky integrator; Low precision variables; Neural networks; Plastic weights

Indexed keywords

ATTRACTOR NEURAL NETWORKS; CONNECTIONIST NETWORKS; DIGITAL HARDWARES; EXPONENTIALLY WEIGHTED MOVING AVERAGE; FIXED-POINT ARITHMETIC; LEAKY INTEGRATOR; LOW PRECISION VARIABLES; PRECISION ARITHMETICS; TRUNCATION ERRORS;

COMPUTATIONAL EFFICIENCY; DIFFERENCE EQUATIONS; DIGITAL ARITHMETIC; METROPOLITAN AREA NETWORKS; VEGETATION;

NEURAL NETWORKS;

ACCURACY; ANALYTIC METHOD; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER; COMPUTER MEMORY; EXPERIMENTAL STUDY; MATHEMATICAL COMPUTING; MICROPROCESSOR; PRIORITY JOURNAL; PROCESS DESIGN; WEIGHT;

EID: 58149468833     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2008.04.007     Document Type: Article

References (17)

1. Draghici S. On the capabilities of neural networks using limited precision weights. Neural Networks 15 3 (2002) 395-414
2. Hoehfeld M., and Fahlman S.E. Learning with limited numerical precision using the cascade-correlation algorithm. IEEE Trans. Neural Networks 3 4 (1992) 602-611
3. Johansson C., and Lansner A. Towards cortex sized artificial neural systems. Neural Networks 20 1 (2006) 48-61
4. Johansson C., and Lansner A. Imposing biological constraints onto an abstract neocortical attractor network model. Neural Comput. 19 7 (2007) 1871-1896
5. C. Koch, I. Segev, Compartmental models of complex neurons (Chapter 3), in: T.J. Sejnowski, T.A. Poggio (Eds.), Methods in Neural Modeling: from Ions to Networks, second ed., A Bradford Book, London, England, 1998.
6. Lansner A., and Ekeberg O. A one-layer feedback artificial neural network with a Bayesian learning rule. Int. J. Neural Syst. 1 1 (1989) 77-87
7. Lansner A., and Holst A. A higher order Bayesian neural network with spiking units. Int. J. Neural Syst. 7 2 (1996) 115-128
8. Mattia M., and Giudice P.D. Efficient event-driven simulation of large networks of spiking neurons and dynamical synapses. Neural Comput. 12 (2000) 2305-2329
9. Mehrtash N., et al. Synaptic plasticity in spiking neural networks (SP2INN): a system approach. IEEE Trans. Neural Networks 14 5 (2003) 980-992
10. Melton M., et al. The TInMANN VLSI chip. IEEE Trans. Neural Networks 3 3 (1992) 375-384
11. Mitchell T.M. Machine Learning (1997), McGraw-Hill Inc., New York
12. Oppenheim A.V., and Willsky A.S. Signals & systems. In: Nawab H. (Ed). Signal Processing. second ed. (1997), Prentice-Hall International, London
13. Orre R., et al. Bayesian neural networks with confidence estimations applied to data mining. Comput. Stat. Data Anal. 34 8 (2000) 473-493
14. Rolls E.T., and Treves A. Neural Networks and Brain Function (1998), Oxford University Press, New York
15. Sandberg A., et al. A Bayesian attractor network with incremental learning. Network: Comput. Neural Syst. 13 2 (2002) 179-194
16. Sutton R.S., and Barto A.G. Reinforcement Learning: An Introduction (1998), MIT Press, Cambridge, MA
17. Tseng S.-T., et al. A study of variable EWMA controller. IEEE Trans. Semiconductor Manuf. 16 4 (2003) 633-643