This research program is aimed at developing modern machine learning methods that lead to improved design of signal processing algorithms, e.g., for audio processing or quantified-self applications. Specifically, in our approach we study computational models of learning and adaptation in brains and apply these ideas to the design of artificial intelligent agents that learn to design (signal processing) algorithms from in-situ interactions with their environment. Key areas of interest include Bayesian machine learning, computational neurosciences and signal processing. Please browse our web page
biaslab.org for more information on our research goals.