Low-Power Analog Associative Processors Employing Resonance-Type Current-Voltage Characteristics

Data-matching function plays an essential role in a number of information processing systems, such as those for voice/ image recognition, codebook-based data compression, image coding, data search applications etc. In order to implement such functions effectively, both proper data representation algorithms and powerful search engines are essential. Concerning the former, robust image representation algorithms such as projected principle edge distribution (PPED) (Shibata et al., 1999; Yagi & Shibata, 2003; Yamasaki & Shibata, 2007) etc. have been developed on the basis of the edge information extracted from original images. Such an algorithm is robust against illumination, rotation, and scale variations, and has been successfully applied to various image recognition problems. Concerning the latter, because search operations are computationally very expensive and time-consuming, it would be better if these operations are carried out by dedicated VLSI associative processors rather than programs running on a general-purpose computer. In this regard, dedicated highly parallel associative processor chips have been developed for the purpose of real-time processing and low-power operation. It has been demonstrated that associative processors can serve as the basis of humanlike flexible computation, and many examples of flexible pattern perception have been demonstrated that are based on analog and digital technologies as well as mixed signal technologies. Digital approaches are accurate in computation, but often require large chip real estate and often consume large power. Analog implementations are preferred in terms of low-power consumption and high-integration density. In this regard, various distancecalculating circuits, which are used to evaluate the similarity (or dissimilarity) between two vectors, have been proposed. Euclidean distance circuits (Tuttle et al., 1993) utilizing MOSFET square-law cells were employed in an 8-bit parallel analog vector quantization (VQ) chip. Konda et al. (1996) and Cauwenberghs & Pedroni (1997) proposed neuron MOSFET (νMOS)-based and charged-based Manhattan-distance evaluation cells, respectively. A νMOS-based Euclidean distance calculator used in a recognition system for handwritten digits was proposed (Vlassis et al., 2001). Kramer et al. (1997) also proposed an analog Manhattan-distance-based content-addressable memory (CAM) using the analog Source: Solid State Circuits Technologies, Book edited by: Jacobus W. Swart, ISBN 978-953-307-045-2, pp. 462, January 2010, INTECH, Croatia, downloaded from SCIYO.COM