We describe, implement, and evaluate classifiers to recognize individual vehicle maneuvers. We show that using deep learning visual odometry to estimate location is superior to consumer-grade high-resolution GPS. We describe and implement a greedy approach to classify maneuvers and evaluate our approach on common road maneuvers.

For computer architecture educators, we describe technical aspects of the final project and common advanced features implemented by students. We hope describing our experience serves not only to demonstrate a method of teaching modern computer architecture, but also to inspire other course designs centered around other aspects of modern computer architecture (GPUs, FPGAs, hardware/software codesign, etc).

We describe our experience teaching an undergraduate capstone (and elective graduate course) in computer architecture with a semester-long project in which teams of five students design and implement an out-of-order (OoO) pipelined processor core using the open-source RISC-V instruction set.

We present a novel approach for detecting vehicle maneuvers from monocular dash-cam video building upon a deep learning visual odometry model (DeepV2D) to estimate frame-accurate ego-vehicle movement.

Understanding dynamic program behavior is critical in many stages of the software development lifecycle, for purposes as diverse as optimization, debugging, testing, and security. This paper focuses on the problem of predicting dynamic program behavior statically. We introduce a novel technique to statically identify hot paths that leverages emerging deep learning techniques to take advantage of their ability to learn subtle, complex relationships between sequences of inputs.