A CMOS feedforward neural-network chip with on-chip parallel learning for oscillation cancellation.

The paper presents a mixed signal CMOS feedforward neural-network chip with on-chip error-reduction hardware for real-time adaptation. The chip has compact on-chip weighs capable of high-speed parallel learning; the implemented learning algorithm is a genetic random search algorithm: the random weight change (RWC) algorithm. The algorithm does not require a known desired neural network output for error calculation and is suitable for direct feedback control. With hardware experiments, we demonstrate that the RWC chip, as a direct feedback controller, successfully suppresses unstable oscillations modeling combustion engine instability in real time.

Symbolic substitution system for data compression.

A new application of symbolic substitution is presented for string matching with the goal of data compression. A temporal sequence of input symbols is mapped onto a two-dimensional array that contains a tree structure, which in turn is mapped into another array for string generation. A symbolic substitution system and the necessary rules are developed to implement the mapping of the input mapping and the generation of an output sequence. A nonadaptive scheme of compression and decompression is described first, followed by an adaptive scheme with additional rules for the dynamic adaptation process.