High-performance DSP architectures for intelligence and control applications
I.P. Radivojevic, Jayantha Herath, William Steven Gray · IEEE Control Systems · 1991
An overview of digital signal processor (DSP) capabilities is given, and the architectural features that make them applicable to intelligent control are discussed. The impact of parallel features on numeric processing capabilities and efficient program execution is described. Input/output (I/O) and real-time features of DSPs are discussed, and examples of several control applications are given. The role of numerical computations in preprocessing vocal, visual, and written input data in real-time artificial intelligence (AI) systems is examined, and the parallels between neural and DSP computations are illustrated. A node configuration for the intelligent experiment neurocomputer (IX-n) virtual implementation of a neural network, based on a commercially available DSP chip, is proposed.>