#  Model-Based Deep Learning for Sensing and Imaging: Efficient and Interpretable AI 

 



####  calendar\_today Date and Time 

 **November 20, 2025** 

 03:00PM EST 

####  pin\_drop Location 

 **Pierce Hall 209**  

 [29 Oxford St  
Cambridge, MA 02138  
United States



 ](<https://www.google.com/maps?q=US MA Cambridge 02138 29 Oxford St>) 



 

 [ More event details from SEAS arrow\_circle\_right ](https://events.seas.harvard.edu/event/model-based-deep-learning-for-sensing-and-imaging-efficient-and-interpretable-ai) 

 



 

Deep neural networks have achieved unprecedented performance gains across numerous real-world signal and image processing tasks. However, their widespread adoption and practical deployment are often limited by their black-box nature—characterized by a lack of interpretability and a reliance on large training datasets.

In contrast, traditional approaches in signal processing, sensing, and communications have long leveraged classical statistical modeling techniques, which incorporate mathematical formulations based on underlying physical principles, prior knowledge, and domain expertise. While these models offer valuable insights, they can be overly simplistic and sensitive to inaccuracies, leading to suboptimal performance in complex or dynamic real-world scenarios.

This talk explores various approaches to model-based learning which merge parametric models with optimization tools and classical algorithms to create efficient, interpretable deep networks that require significantly smaller training datasets. We demonstrate the advantages of this approach through applications in image deblurring, image separation, super-resolution for ultrasound and microscopy, radar for clinical diagnostics, efficient communication systems, low-power sensing devices, and more. Additionally, we present theoretical results that establish the performance advantages of model-based deep networks over purely data-driven black-box methods.



 

 



 

 See also:- [ AI ](/event-categories/ai)
 
 

 Share on:- [     Facebook ](#)
- [     Twitter ](#)
- [     Linkedin ](#)
 


 Save: [ Add to calendar calendar\_today ](https://www.fas.harvard.edu/node/2666/event-feed.ics)  Copy link link