1. Connectivity versus entropy;Abu-Mostafa,1988
2. N. Alon, J. Bruck, Explicit construction of depth-2 majority circuits for comparison and addition, Tech. Rep. RJ 8300 (75661), IBM Almaden, San Jose, CA, 1991.
3. P.L. Bartlett, The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network, Tech. Rep. (ftp:syseng.anu.edu.au/pub/peter/TR96d.ps.Z), Department of Systems Engineering, Research School of Information Science and Engineering, Australian National Univ., Canberra 0200 Australia, 7 May 1996; short version as: Valid generalization, the size of the weights is more important than the size of the network, in: M.C. Mozer, M.I. Jordan, T. Petsche (Eds.), Advances in Neural Information Processing Systems 9, MIT Press, Cambridge, MA, 1997.
4. V. Beiu, Direct synthesis of neural networks, in: Proc. Intl. Conf. on Microelectronics for Neural Networks, IEEE CS Press, Los Alamitos, 1996, pp. 257–264.
5. V. Beiu, Entropy bounds for classification algorithms, Neural Network World 6 (1996) pp 497–505.