Title :
A learning sequential detection method based on neural networks
Author :
Guo, Chengan ; Kuh, Anthony
Author_Institution :
Dalian Univ. of Technol., China
Abstract :
This paper presents a neural network method for sequential detection. A theorem is stated that there exists a reinforcement learning algorithm which can approach the performance of the optimal sequential probability ratio test (SPRT) in the minimum mean squared-error. Then a suitable network architecture and learning algorithm are developed to implement the reinforcement learning. Simulations have shown that this learning detector can operate as optimum as SPRT while using much less statistical knowledge than SPRT
Keywords :
learning (artificial intelligence); neural net architecture; signal detection; learning sequential detection method; minimum mean squared error; network architecture; neural networks; optimal sequential probability ratio test; performance; reinforcement learning algorithm; simulations; statistical knowledge; theorem; Density functional theory; Detection algorithms; Detectors; Learning; Neural networks; Paper technology; Probability; Propagation delay; Sequential analysis; Testing;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.566587
