In this project, we propose an edge computing solution that enables distributed machine learning on resource constrained IoT devices. We develop a scalable algorithm to automatically dispatch neural networks to edge devices. The design is tested on Raspberry Pis for image classification tasks. 
Poisson process plays a fundamental role in the theory and application of stochastic process. However, the intensity estimation of inhomogeneous Poisson process remains difficult. In this project, we compare the performance of three existing estimation methods: smoothing kernel method, Mercer kernel method, and Bayesian method. 
This is a collection of homework and course projects for CMU 11785: Introduction to Deep Learning (Term: 18 Fall). 
Brain waves have been widely used to measure human’s physical and mental activities. With the help of cutting edge machine learning technologies, we successfully detect two activity patterns from EEG signal: blink and concentration.
This is a collection of parallel and distributed computing projects I did. Levels of parallelism vary from data level SIMD to thread level OpenMP to Spark based map-reduce. 
This is a collection of course projects and homework for Berkeley CS162: Operating Systems and Systems Programming (Term: 17 Spring). 
This is a collection of course projects for Berkeley CS186/286: Introduction to Database Systems (Term: 16 Fall). 
This is a collection of course projects for Berkeley CS161: Computer Security (Term: 17 Fall). 
For more projects, please visit my GitHub.