Miguel Á. Carreira-Perpiñán is a professor in Electrical Engineering and Computer Science at the University of California, Merced. He received the degree of “licenciado en informática” (MSc in computer science) from the Technical University of Madrid in 1995 and a PhD in computer science from the University of Sheffield in 2001.
Prior to joining UC Merced, he did postdoctoral work at Georgetown University (in computational neuroscience) and the University of Toronto (in machine learning), and was an assistant professor at the Oregon Graduate Institute (Oregon Health & Science University). He is the recipient of an NSF CAREER award, a Google Faculty Research Award and best (student) paper awards at AISTATS and Interspeech. He is an associate editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence and has been an area chair for several machine learning, computer vision and data mining conferences (NIPS, ECCV, SDM).
His research interests lie in machine learning and optimization. Most recently, he is interested in the optimization of nested systems, such as deep neural nets, using auxiliary coordinates. Other interests are in unsupervised learning problems such as dimensionality reduction, clustering and denoising, mean-shift algorithms, and applications to speech processing (e.g. articulatory inversion and model adaptation), computer vision, sensor networks, information retrieval and other areas. My research is inspired by pattern recognition problems such as speech processing and computer vision, and by computational neuroscience. My long-term research goals are to design algorithms for complex information processing problems, and to understand how neural systems solve such problems.