Neural networks advantages and limitations

Livingstone, D. J., Manallack, D. T. Tetko, I. V. (1997). Data modelling with neural networks advantages and limitations. J Comput Aided Mol Des 11,135-42. 

Data Modeling With Neural Networks—Advantages and Limitations. 

Computer-aided modelling for drug design is another approach for drug discovery that has become standard and the advantages and limitations of a neural networks for computer-aided molecular design and sequence analysis are a hot topic today. 

The advantages and limitations of artificial neural networks for predicting the properties of rabber compounds are... 

A neural network has the advantage that it is a universal approximator and the inner PLS model is therefore not limited to some predefined functional form. In Qin McAvoy (1992) the neural network PLS (NNPLS) algorithm is introduced by replacing the linear inner relationship in equation (4) with a feed-forward multilayer perceptron neural network, such that... 

The two components (SASLM 1 and SASLM 2) can now be combined with CGHs to route (fan-out) the light through the optical neural network, as in Fig. 64. SASLM 1 is used as the neurons and SASLM 2 makes up the synaptic weights. The system is almost entirely optical and the advantages are inherent compared to electronic neural nets, as the interconnections are total and performed in free space. The problem is that for n SASLM 1 neurons, SASLM 2 weighting smart pixels are required, which limits the processing power of the neural net due to VLSI constraints [75]. 

---