— This paper examines the bit error probability (BEP) of bit-interleaved coded modulation and iterative decoding (BICM-ID) in OFDM systems with modulation diversity (MD) over cor...
—We propose a non-coherent receiver for the fixed detect-and-forward relay channel and derive a closed-form tight upper bound on its bit error probability in Rayleigh fading cha...
We introduce a computationally feasible, "constructive" active learning method for binary classification. The learning algorithm is initially formulated for separable cl...
One of the main research concern in neural networks is to find the appropriate network size in order to minimize the trade-off between overfitting and poor approximation. In this ...
We introduce a general-purpose learning machine that we call the Guaranteed Error Machine, or GEM, and two learning algorithms, a real GEM algorithm and an ideal GEM algorithm. Th...