Deep learning (DL) is a prominent and growing area of machine learning that is rapidly changing how complex data in the world is modeled, interpreted, and utilized. To model these complexities, building accurate and robust DL models can often require heavy computation, memory, and energy costs. Because of this, researchers have been exploring methods to construct deep neural networks with small model sizes, light computation costs, and high segmentation accuracy. Knowledge distillation, a process in which a larger, cumbersome model is “distilled” into a smaller, student model, is a model compression method growing in popularity. In this research, we design efficient and compact deep networks using knowledge distillation to be applied to lane detection in autonomous vehicles with a low-cost computing environment in a classroom, such as Raspberry Pi. We address this by developing a student Convolutional Neural Network that reduces model size and minimizes accuracy loss as measured by the differences in MSE and R2 between the cumbersome model and the student model. Our research suggests that knowledge distillation can be applied to deep learning models trained for lane detection with improved model compactness and moderate accuracy preservation.

LeAnn Mendoza (she/her) is a graduate student pursuing an M.S. in Data Science at Northeastern University, San Jose. She has a B.S. in Bioengineering: Bioinformatics from UC San Diego and over 3 years of professional experience in machine learning, deep learning, data science, and computer vision. Currently, she is a co-op at Unum under Finance Analytics Enablement and also works as a Data Science Student Ambassador at Northeastern University, Khoury College of Computer Sciences.

Beyond her career and academic pursuits, she is passionate about promoting accessibility and inclusion in data and computer science. LeAnn is an advocate for STEM and computer science education accessibility and works to promote diversity and inclusion in the field through her work as a volunteer elementary school computer science teacher, robotics mentor, ACM-W student chapter chair and co-founder, and student ambassador for the Northeastern Align program.

LeAnn seeks to pursue a career to make a positive impact in the world by leveraging data science to create great things and using her experiences to help others do the same. If you’d like to connect, please feel free to reach out through email (leannmarie.mendoza@gmail.com) or LinkedIn (https://www.linkedin.com/in/leannmendoza/).