no code implementations • 5 May 2017 • Ming Sun, Anirudh Raju, George Tucker, Sankaran Panchapagesan, Geng-Shen Fu, Arindam Mandal, Spyros Matsoukas, Nikko Strom, Shiv Vitaladevuni
Finally, the max-pooling loss trained LSTM initialized with a cross-entropy pre-trained network shows the best performance, which yields $67. 6\%$ relative reduction compared to baseline feed-forward DNN in Area Under the Curve (AUC) measure.
no code implementations • 22 Oct 2016 • Zois Boukouvalas, Rami Mowakeaa, Geng-Shen Fu, Tulay Adali
ICA algorithms cast in the ML framework often deviate from its theoretical optimality properties due to poor estimation of the source PDF.
no code implementations • 29 Mar 2013 • Matthew Anderson, Geng-Shen Fu, Ronald Phlypo, Tülay Adalı
Thus, we provide the additional conditions for when the arbitrary ordering of the sources within each dataset is common.