 Hi, I am Annesha. I will give a quick overview of our project, Neural Network Models, described by the role of plasticity in cochlear implant outcomes. Cochlear implants or CI's are one of the most successful neural prostheses that have been able to partially restore hearing perception in people with severe sensory neural hearing loss. CI users are able to correctly identify speech in a quiet environment. However, their performance in complex auditory tasks such as speech recognition in noise is still extremely poor compared to normal hearing listeners. In this project, we propose to use a computational model of CI-mediated hearing to better understand the different factors behind the successes as well as limitations of current cochlear implants and efficiently explore the space of new signal processing and stimulation strategies that may improve the device's performance. In our proposed model, we implement a deep artificial neural network to simulate the central auditory pathway. We model normal hearing by training the network using simulated auditory neural input from an intact cochlear. To model CI hearing, we test the same trained network on simulated auditory neural input from CI. Further, to simulate the possible consequences of learning to hear through a CI, we retrain this entire network on CI input. Also, to model the possibility that only part of the auditory system exhibits this plasticity, in some models, we retrain only the late stages of the network. We evaluate the model performance using speech recognition in noise tasks and compare it with the performance of normal hearing conditions and data from cochlear implant users. When the entire network was re-optimized for CI input, the model exhibited near-normal speech intelligibility score. Performance and power with CI users was achieved only when just the late stages of the models were re-optimized. Our results are consistent with the possibility that limitations on CI-mediated speech perception relate to incomplete plasticity that prevents the risk of the auditory system from optimally decoding CI input rather than being entirely due to impoverished auditory neural representation from CI stimulation.