Excited to have launched the USC Center for Neurotechnology & grateful for this new NIH BRAIN grant that will help us develop AI-based #neurotech for multimodal neural-behavioral-physiological symptom monitoring in brain disorders like depression. Story: viterbischool.usc.edu/news/2024/05/s…

In this new Review Maryam Shanechi discusses how BCIs could be used to model the brain response to stimulation and decode a patient’s symptom-state from brain activity as feedback to personalize the stimulation therapy in closed loop. bit.ly/3RcD5Sr

🎉New in Nature Rev Bioeng Nature Reviews Bioengineering, we provide a roadmap for developing #BCI's as therapies for mental health conditions. We discuss how AI & control theory can help design them & review progress. 👏Congrats Lucine Oganesian nature.com/articles/s4422… View rdcu.be/dJMiY

A Review in Nature Reviews Bioengineering reviews the progress on developing brain-computer interfaces for neuropsychiatric care, focusing on neural biomarkers for decoding symptom states, stimulation site selection and closed-loop stimulation strategies. 🔒 go.nature.com/4c79kL1

Our paper in Nature Reviews Bioengineering on developing brain-computer interfaces as potential therapies for neuropsychiatric disorders is now free to access! ⬇️ We provide a roadmap for their design, discuss how AI can help and review progress. #BCI w/Lucine Oganesian nature.com/articles/s4422…

🧠🎙️Neurotech Pub is back this week! Our latest episode features Amit Etkin from Alto Neuroscience, Maryam Shanechi from USC, and Prasad Shirvalkar ShirvalkarLab UCSF from UC San Francisco. paradromics.com/podcast/engine…

DPAD is finally out in Nature Neuroscience! 🎉 I actually started this work during the last year of my PhD back in 2020 (!) & we posted the preprint 3 years ago!!! Some things really do take time... Huge thanks to Maryam Shanechi for her unwavering support throughout this journey! 🙌

Published in Nature Neuroscience, Maryam Shanechi and her team develop a new #AI method that can ID brain patterns related to specific behaviors and better decode behavior. This can improve brain-computer interfaces that restore movement in paralyzed patients. viterbischool.usc.edu/news/2024/09/i…

DPAD, a deep learning method for dynamical neural-behavioral modeling, dissociates behaviorally relevant neural dynamics, better predicts neural-behavioral data, and reveals where their nonlinearities can be isolated Omid Sani Maryam Shanechi nature.com/articles/s4159…

Thank you, USC Viterbi School!

Truly honored to be named a Blavatnik National Awards Finalist! Thanks Blavatnik Awards for recognizing our lab for having "Pioneered research at the intersection of engineering, AI, & neuroscience to develop advanced neurotechnologies". USC Viterbi School USC viterbischool.usc.edu/news/2024/09/m…