Title :
How many bits from how many sensors? A trade-off in distributed nearest-neighbor learning
Author :
Marano, Stefano ; Matta, Vincenzo ; Willett, P.
Author_Institution :
Dept. of Inf. & Electr. Eng. & Appl. Math., Univ. of Salerno, Fisciano, Italy
Abstract :
In one of his landmark papers, Cover established the fundamental scaling laws of learning with nearest-neighbor rules (T.M. Cover, 1968). With the recent advances on distributed nearest-neighbor learning in sensor networks novel trade-offs arise, involving the faithfulness of message representation (quantization bits) and the number of delivered messages (transmitting sensors). This is the main theme of this paper.
Keywords :
learning (artificial intelligence); quantisation (signal); wireless sensor networks; distributed nearest-neighbor learning; fundamental scaling laws; message representation; nearest-neighbor rules; quantization bits; sensor networks; transmitting sensors; Approximation methods; Artificial neural networks; Estimation; Limiting; Quantization (signal); Sensors; Training;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
Conference_Location :
Florence
DOI :
10.1109/ICASSP.2014.6855082
