Title: On Building Digital Humans Speaker: Michael Black Abstract: The human body is complex and deformable. For many applications in computer vision, graphics, fashion, and medicine, having a realistic, low-dimensional, 3D model of the body is useful. Getting a good one, however, is difficult. This talk will review the history of our work on learning 3D…
Read more
Distinguished Speaker Series – Regina Barzilay
Title: Finding Simple Solutions for Hard NLP Problems Speaker: Regina Barzilay Abstract: Progress on many well-established problems in Natural Language Processing comes from applying generic machine learning techniques to the task at hand. While successful, this perspective omits the hidden simplicity of many tasks or ways that they could be made simpler to solve. In this…
Read more
Distinguished Speaker Series – David Sontag
Title: How is Machine Learning Going to Change Health Care? Speaker: David Sontag Abstract: Machine learning has transformed the technology industry over the last decade, forming the basis for web search, speech recognition, product recommendations, and self-driving cars. With the increased adoption of electronic health records and a surge in funding for health IT startups, health…
Read more
Distinguished Speaker Series – Sham Kakade
Title: The Promise and Challenge of Unsupervised Learning Speaker: Sham Kakade Abstract: Representational learning is one of the central challenges in machine learning, where the goal is to find transformations of our data which support improvements in downstream tasks of interest. The algorithmic challenge is in designing methods which learn such representations in an automated manner…
Read more
Distinguished Speaker Series – Dharmendra Modha
Title: A New Architecture for Brain-inspired Computing Speaker: Dharmendra S. Modha Abstract: I will describe a decade-long, multi-disciplinary, multi-institutional effort spanning neuroscience, supercomputing, and nanotechnology to build and demonstrate a brain-inspired computer and describe the architecture, programming model, and applications. For more information, see: modha.org. Bio: Dr. Dharmendra S. Modha is an IBM Fellow and IBM Chief…
Read more
Distinguished Speaker Series – Matt Ginsberg
Title: Is The Universe Continuous or Discrete? (And Why People in AI Should Care) Speaker: Matt Ginsberg Abstract: Recent years have seen increasing tension between people who believe in so-called "good old-fashioned AI", or GOFAI (and who believe that problems should in general be solved using discrete methods and without learning) and people who believe…
Read more
Distinguished Speaker Series – Kevin Knight
Title: Language Translation and Code-Breaking Speaker: Kevin Knight Abstract: In 1949, information theorist Warren Weaver suggested applying code-breaking methods to the problem of automatic language translation. He said: "When I look at an article in Russian, I say: this is really written in English, but it has been coded in some strange symbols. I will now proceed…
Read more
Distinguished Speaker Series – Leslie Kaebling
Title: Making Robots Believe Speaker: Leslie Pack Kaelbling Abstract: The fields of AI and robotics have made great improvements in many individual subfields, including in motion planning, symbolic planning, probabilistic reasoning, perception, and learning. Our goal is to develop an integrated approach to solving very large problems that are hopelessly intractable to solve optimally. We make a…
Read more
- 1
- 2