Select a calendar:
Filter May Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for May 12, 2015
-
Learning Longer Memory in Recurrent Networks
Tue, May 12, 2015 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Tomas Mikolov , Research Scientist at Facebook AI Reseach
Talk Title: Learning Longer Memory in Recurrent Networks
Series: AISeminar
Abstract: Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due to the so-called vanishing gradient problem. In this talk, I will show that learning longer term patterns in real data, such as in natural language, is perfectly possible using gradient descent. This is achieved by using a slight structural modification of the simple recurrent neural network architecture. Some of the hidden units are encouraged to change their state slowly by constraining part of the recurrent weight matrix to be close to identity, thus forming kind of a longer term memory. We evaluate our model in language modeling experiments, where we obtain similar performance to the much more complex Long Short Term Memory (LSTM) networks. This is a joint work with Armand Joulin, Sumit Chopra, Michael Mathieu and Marc'Aurelio Ranzato.
Biography: Tomas Mikolov is a research scientist at Facebook AI Research. His work includes introduction of recurrent neural networks to statistical language modeling (published as open-source RNNLM toolkit), and an efficient algorithm for estimating word representations in continuous space (the Word2vec project). His current interest is in developing techniques and datasets that would help to advance research towards artificial intelligence systems capable of natural communication with people.
Website: https://research.facebook.com/researchers/643234929129233/tomas-mikolov/
Host: Ashish Vaswani
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=19140806ae5e4116ab2644b1c1d86bbe1dLocation: Information Science Institute (ISI) - 1135
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=19140806ae5e4116ab2644b1c1d86bbe1d
Audiences: Everyone Is Invited
Contact: Alma Nava / Information Sciences Institute
-
PhD Defense - Aaron St. Clair
Tue, May 12, 2015 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
Date: Tuesday, May 12, 2015
Time: 12pm
Location: RTH 406
PhD Candidate: Aaron St. Clair
Committee:
Maja MatariÄ (Chair)
Gaurav Sukhatme
Nora Ayanian
Aaron Hagedorn
Title: Coordinating Communication in Human-Robot Task Collaborations
Abstract:
Robots have become increasingly capable of performing a variety of tasks in real-world dynamic environments, including those involving people. Beyond competently performing the tasks required of them, service robots should also be able to coordinate their actions with those of the people around them in order to minimize conflicts, provide feedback, and build rapport with human teammates in both work environments (e.g., manufacturing) and home settings. Humans coordinate their actions in various task settings through structured social interaction aimed at representational alignment and intentional feedback. In order for robots to coordinate their actions using similar modalities, they must be capable of contextualizing the actions of human partners and producing relevant natural communicative behaviors as the task progresses. This dissertation is motivated by the high-level goal of producing effective social feedback during task performance, and alleviating the burden of coordinating the team's joint activity by allowing human users to interact with robots through natural social modalities as partners rather than as operators.
This dissertation develops an approach for constructing and generalizing models of role-based coordinating communication during physically-decoupled human-robot task scenarios, specifically pairwise collaborations in which a person and a robot work together to achieve a shared goal. The approach is validated in different task contexts with different user populations using objective and subjective measures of task performance and user preferences. To support role-allocative communication observed in our pilot experiments with two-person teams, the human-robot collaboration problem is formulated as a Markov decision process in which roles are represented by a set of policies capturing different action selection preferences and accounting for unequal capabilities between human and robot collaborators. A probabilistic method is used to track the user's activity over time and to recognize the role assumed by the user, communication is then planned given the expected policy of the user, the policy of the robot, and the current task state. The communication generated by the robot consists of three types of speech actions and associated co-verbal behavior: 1) self-narration of the robot's activities, 2) role allocation suggestions for the user, and 3) empathetic displays when positive and negative state changes occur.
The approach was validated initially on a dynamic augmented reality herding task with a population of convenience users using objective metrics (idle time, distance traveled) as well as subjective evaluations (user preference, perceived intelligence of the robot), where a higher utilization of the robot and more equitable path distance was observed in comparison to a non-communicating robot. The generalizability of the approach to a different task setting and user population was also evaluated on a cooking task with an elderly user population. The contributions of this dissertation lie in the development of an approach for modeling human-robot task performance for the planning and production of effective robot verbal feedback.Location: Ronald Tutor Hall of Engineering (RTH) - 406
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
