About Me

I am a Ph.D. candidate in the Computer Science and Engineering (CSE) department at the University of Michigan, Ann Arbor. I joined the Compilers Creating Custom Processors (CCCP) research group in Fall of 2014 and started working under the supervision of Prof. Scott Mahlke. I received my Bachelor's degree in Electrical Engineering from the Sharif University of Technology in 2014.

Research Interests

My research interests lie in neural networks, energy-efficient deep learning and domain-specific architectures. Nowadays, due to the large and rapidly increasing quantities of available data, Deep Neural Network (DNN) models trained on large datasets significantly outperform traditional machine learning techniques in various domains. The high computational complexity of these models highlights the need for leveraging hardware and software techniques to accelerate deep learning for improved energy efficiency and performance. Currently, I am investigating efficient machine learning algorithms and domain-specific hardware architectures to dynamically distribute the computation among a group of automatically designed DNNs with different levels of accuracy and complexity. The goal is achieving maximum energy efficiency and performance while maintaining the output accuracy of the most accurate model.