Bartlett P, Ben-david S. (2002). Hardness results for neural network approximation problems Theoretical Computer Science. 284

Blum A, Rivest RL. (1992). Training a three-node neural network is NP-complete Neural Netw. 5

Garey MR, Johnson DS. (1979). Computers and intractability: A guide to the theory of NP-completeness.

Hammer B. (1998). Some complexity results for perceptron networks International Conference on Artificial Neural Networks 98.

Hammer B. (1998). Training a sigmoidal network is difficult European Symposium on Artificial Neural Networks 98.

Hammer B, Dasgupta B. (2000). On approximate learning by multilayered feedforward circuits Algorithmic learning theory 2000.

Hoffgen KU, Simon HU, Vanhorn KS. (1995). Robust trainability of single neurons J Computer Sys Sci. 50

Judd JS. (1990). Neural network design and the complexity of learning.

Muroga S, Toda I, Takasu S. (1961). Theory of majority decision elements Journal Of The Franklin Institute. 271

Rumelhart DE, Hinton GE, Williams RJ. (1986). Learning representations by back-propagating errors. Nature. 323

Sima J. (1994). Loading deep networks is hard Neural Comput. 6

Sima J. (1996). Back-propagation is not efficient Neural Netw. 9

Síma J. (2002). Training a single sigmoidal neuron is hard. Neural computation. 14 [PubMed]

Vu VH. (1998). On the infeasibility of training neural networks with small squared errors Advances in neural information processing systems. 10

de_Souto MCP, de_Oliveira WR. (1999). The loading problem for pyramidal neural networks Electronic Journal on Mathematics of Computation (Available at: http:--gmc.ucpel.tche.br-ejmc-).