105061528_homework0

README.md

@@ -5,4 +5,24 @@ To avoid writing the same person, please report the person's name in
 https://docs.google.com/spreadsheets/d/153XruMO7DPONzBTkxh8ZoYSto1E_2zO021vs0prWZ_Q/edit?usp=sharing
 First come first serve!
 -------
-Write here
+## Trevor Darrell
+<img src="Prof. Darrell photo.png"  width="150px" />
+
+##### [Website](https://people.eecs.berkeley.edu/~trevor/)
+
+### Introduction
+Prof. Darrell is on the faculty of the CS and EE Divisions of the EECS Department at UC Berkeley. He leads Berkeley’s DeepDrive (BDD) Industrial Consortia, is co-Director of the Berkeley Artificial Intelligence Research (BAIR) lab, and is Faculty Director of PATH at UC Berkeley. He received the S.M., and PhD. degrees from MIT in 1992 and 1996, and respectively, he obtained the B.S.E. degree from the University of Pennsylvania in 1988.
+
+His group develops algorithms for large-scale perceptual learning, including object and activity recognition and detection, for a variety of applications including autonomous vehicles, media search, and multimodal interaction with robots and mobile devices. 
+
+His areas of interest include computer vision, machine learning, natural language processing, and perception-based human computer interfaces. His reasech area is very wide, I know the famous professor because I previously did a project about domain adaptation and self-driving car related. Moreover, last semester I took a course about NLP, and I found an impressive paper, titled "Learning to reason: End-to-end module networks for visual question answering" as I survey the final project topic. The paper teaches a machine VQA tasks by decomposing the question into modular sub-problems and step by step reasoning. It inspires me a lot.
+
+### Current Teaching 
+##### CS294-43: Object and Activity Recognition Seminar 
+##### CS294-131: Deep Learning Seminar (Fall, Spring)
+
+### Recent Publications
+##### [Learning modular neural network policies for multi-task and multi-robot transfer](https://arxiv.org/pdf/1609.07088.pdf)
+##### [Learning to reason: End-to-end module networks for visual question answering](https://arxiv.org/pdf/1704.05526.pdf)
+
+