Unsupervised Tuning of Cochlear Implants

PI: Bonny Banerjee

Since noteworthy events happen only occasionally in any data, it is imperative for smart sensors to learn the norms in data so that an appropriate action can be taken at the occurrence of an abnormal or noteworthy event. The aim of this project is to develop algorithms that can learn the norm in terms of a hierarchy of meaningful features from data in an unsupervised and online manner. The application testbed is the problem of automatically tuning cochlear implants (CIs) of patients with severe-to-profound hearing loss by continuously monitoring their speech output.

Hearing loss is the most common birth defect in the U.S. with slightly over 15,000 new pediatric cases each year and societal losses amounting to $4.6 billion over a lifetime. The working hypothesis is that deficiencies in hearing for people with significant hearing loss are reflected in their speech production. This project will develop and use unsupervised, online, and biologically plausible machine learning algorithms to learn feature hierarchies from the speech output data of severely-to-profoundly hearing-impaired patients. The learned feature hierarchy from the speech of a patient will be compared to those learned from the speech of a comparable normal hearing population. Deficiencies in the patient's hearing will be ascertained by identifying the missing or distorted features. Algorithms will be developed to map this information into the signal processing strategies used in CIs to enhance the audibility of speech.

Funding:

• Algorithms for Unsupervised and Online Learning of Hierarchy of Features for Tuning Cochlear Implants for the Hearing Impaired. Funding Agency: NSF. $298,203

Selected Publications:

• Banerjee, B., Dutta, J. K., & Gu, J. (in press). SELP: A general-purpose framework for learning the norms from saliencies in spatiotemporal data. Neurocomputing: Special Issue on Brain Inspired Models of Cognitive Memory.
• Banerjee, B. (2012). Learning lateral connections among neurons from correlations of their surprises. Center for Visual Science's 28th Symposium: Computational Foundations of Perception and Action, June 1–3, 2012, University of Rochester, NY.
• Dutta, J. K., Gu, J., Kasani, R. P., & Banerjee, B. (2012). A multilayered neural network model for verifying the common cortical algorithm hypothesis. Center for Visual Science's 28th Symposium: Computational Foundations of Perception and Action, June 1–3, 2012, University of Rochester, NY.