Chapter 13 - Artificial Neural Network as Helping Tool for Drug Formulation and Drug Administration Strategies

Abstract

The major issue of success of an ongoing engineering process or a process projected to be performed in the near future lies mainly in efficiency. Efficiency includes the reproducibility of the process, cost-effectiveness, simplicity, etc. The quality of the final product is of the upmost importance to the pharmaceutical industry. If drugs are to remain effective and safe, then this requires the highest possible precision in the manufacturing process. It is difficult to approach pharmaceutical formulation development using classical engineering procedures. Hence, heuristic methodology is being applied nowadays and has recently warranted more attention. To fulfill the demand, computational intelligence tools are used. Among these, artificial neural networks (ANNs) are one of the most widely used processing systems. An ANN is a biologically inspired computational model formed from hundreds of single units (artificial neurons) connected with coefficients (weights) that constitute the neural structure. ANN research has experienced three periods of extensive activity. The first peak in the 1940s was due to McCulloch and Pitts' pioneering research. The second occurred in the 1960s with Rosenblatt's perceptron convergence theorem and Minsky and Papert's work showing the limitations of a simple perceptron. Minsky and Papert's results dampened the enthusiasm of most researchers, especially those in the computer science community. The resulting lull in neural network research lasted almost 20years. Since the early 1980s, ANNs have received considerable renewed interest. The major developments behind this resurgence include Hopfield's energy approach in 1982 and the backpropagation learning algorithm for multilayer perceptrons (multilayer feed-forward networks) first proposed by Werbos, reinvented several times, and then popularized by Rumelhart et al. in 1986.