This thesis is a conceptual and empirical approach to embody modelling of continuous sequential behaviour in neural learning. The aim is to enhance the feasibility of training and capacity for generalisation. By examining the sequential aspects of the passing of time in a neural network, it is suggested that an alteration to the usual goal weight condition may be made to model these aspects. The notion of a goal weight path is introduced, with a path-based backpropagation (PBP) framework being proposed. Two models using PBP have been investigated in the thesis. One is called Feedforward Continuous BackPropagation (FCBP) which is a generalization of conventional BackPropagation; the other is called Recurrent Continuous BackPropagation (RCBP) which provides a neural dynamic system for I/O associations. Both models make use of the continuity underlying analogue-binary associations and analogue-analogue associations within a fixed neural network topology. A graphical simulator cbptool for Sun workstations has been designed and implemented for supporting the research. The capabilities of FCBP and RCBP have been explored through experiments. The results for FCBP and RCBP confirm the modelling theory. The fundamental alteration made on conventional backpropagation brings substantial improvement in training and generalization to enhance the power of backpropagation.