This is Graham Neubig's lab at the Language Technologies Institute of Carnegie Mellon University. We do research on natural language processing and machine learning, specifically machine translation, ...

I am a postdoctoral fellow at Carnegie Mellon University. I was awarded a PhD from CMU's Machine Learning Department in December 2010. I am interested in machine learning techniques for structured ...

The exact topics of the lectures are subject to change. We do not anticipate changing any of the other dates (exams, assignments, etc.) To watch the lecture videos, sign in to YouTube using your ...

The handout Automated Theorem Proving contains a complete set of notes as of the indicated date. This includes all incremental handouts with possible corrections and updates. Note that I do not ...

From smart phones, to multi-core CPUs and GPUs, to the world's largest supercomputers, parallel processing is ubiquitous in modern computing. The goal of this course is to provide a deep understanding ...

The NyquistIDE program combines many helpful functions and interfaces to help you get the most out of Nyquist. NyquistIDE is implemented in Java, and you will need the Java runtime system or ...

Symbolic logic is fundamental to computer science, providing a foundation for the theory of programming languages, the theory of databases, AI, knowledge representation, automated reasoning, and ...

This course covers the design and implementation of compiler and runtime systems for high-level languages, and examines the interaction between language design, compiler design, and runtime ...

The Hubbard Professional Mark Super VII is the most sophisticated and expensive e-meter yet developed by the Church of Scientology. Its retail price in 1995 was US $3,850. It is the standard e-meter ...

Miaomiao Wen, Diyi Yang and Carolyn Penstein Rose. Linguistic Reflections of Student Engagement in Massive Open Online Courses. ICWSM'14, 2014(Oral Paper, fulltext). Miaomiao Wen and Carolyn Penstein ...

Advantage learning is a form of reinforcement learning similar to Q-learning except that it uses advantages rather than Q-values. For a state x and action u, the advantage for that state-action pair A ...

I am a final year Ph.D. student in the Robotics Institute at Carnegie Mellon University, advised by Dr. Maxim Likhachev. My general research interests span Artificial Intelligence (AI), Perception, ...