We studied and compared two types of connectionist learning methods for model-free regression problems in this paper. One is the popular back-propagation learning (BPL) well known in the artificial neural networks literature; the other is the projection pursuit learning (PPL) emerged in recent years in the statistical estimation literature. Both the BPL and the PPL are based on projections of the data in directions determined from interconnection weights. However, unlike the use of fixed nonlinear activations (usually sigmoidal) for the hidden neurons in BPL, the PPL systematically approximates the unknown nonlinear activations. Moreover, the BPL estimates all the weights simultaneously at each iteration, while the PPL estimates the weights cyclically (neuron-by-neuron and layer-by-layer) at each iteration. Although the BPL and the PPL have comparable training speed when based on a Gauss-Newton optimization algorithm, the PPL proves more parsimonious in that the PPL requires a fewer hi...

Abstract-In the previous paper, we established the theoretical foundations of a new class of area-efficient architectures for the Viterbi algorithm. In this paper, we will show area-efficient ar-chitectures for practical codes to illustrate the design procedures and demonstrate the favorable area-time tradeoff results. Three examples from convolutional codes, matched-spectral-null (MSN) trellis codes, and Ungerboeck codes will be presented. We will also discuss the application of our area-efficient techniques to codes with a very large numbers of states, codes with time-varying trellises, and a programmable Viterbi decoder. I.