Select a calendar:
Filter July Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for July
-
NL Seminar-Visual Question Answering the Good, the Bad, and the Ugly
Fri, Jul 20, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Wei-Lun Harry Chao , USC
Talk Title: Visual Question Answering: the Good, the Bad, and the Ugly
Series: Natural Language Seminar
Abstract: Visual question answering Visual QA requires comprehending and reasoning with both visual and language information, a characteristic ability that AI should strive to achieve. Merely in the past three years, over a dozen datasets have been released, together with many learning based models that have been narrowing the gap between the humans performance and the machines. On one popular dataset VQA, the state of the art model achieves 71.4 percent accuracy, just percent shy of that by humans.
While seemingly remarkable, it needs a deeper investigation on what knowledge the machine actually learns does it understand the multi modal information? Or it relies on and over fits to the incidental dataset statistics. Moreover, current experimental setups mainly focus on training and testing within the same dataset. It is unclear how the learned model can be applied to the real environment where both the visual and language data might have mismatch.
In this talk, I will present our recent studies to answer these questions. We show that the dataset design has a significant impact on what a model learns. Specifically, the resulting model can ignore the visual information, the question, or both while still doing well on the task. We thus propose automatic procedures to remedy such design deficiencies. We then show that the mismatch in language hinders transferring a learned model across datasets. To this end, we develop a domain adaptation algorithm for Visual QA to facilitate knowledge transfer. Finally, I will present a probabilistic framework of Visual QA algorithms to effectively leverage the answer semantics, drastically increasing the transferability. I will conclude the talk with future directions to advance Visual QA.
Biography: Wei Lun Harry Chao is a Computer Science PhD candidate at University of Southern California, working with Fei Sha. His research interests are in machine learning and its applications to computer vision, artificial intelligence, and health care. His recent work has focused on transfer learning toward vision and language understanding in the wild. His earlier research includes work on probabilistic inference, structured prediction for video summarization, and face understanding. He will be joining The Ohio State University as an assistant professor in 2019 Fall, following a one-year postdoc at Cornell University.
Host: Nanyun Peng
More Info: http://nlg.isi.edu/nl-seminar/
Location: 11th Flr Conf Rm # 1135, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
-
Electrical Engineering Seminar
Fri, Jul 20, 2018 @ 03:30 PM - 04:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Yi-Hsuan Yang , Academia Sinica, Taiwan
Talk Title: Machine Learning for Creative AI Applications in Music
Abstract: In this talk, I will briefly introduce three latest projects in our lab at Academia Sinica on creative applications in music, including the singing voice separation project, GenMusic (music generation) project, and the DJnet project. The first project is about separating the singing voice from the musical accompaniments, which can be used as a pre-processing step for many music related applications. The second project is about learning from massive collection of MIDI files to generate multi-track music by a generative adversarial network (GAN). The generative model can be used for generating music either from scratch, or by accompanying a given (instrument) track. The third project is about creating an AI DJ that knows how to manipulate, sample, and sequence musical pieces to create a personalized playlist. The goal of these projects is to enrich the way people create and interact with music in their daily lives, using the latest machine learning (deep learning) techniques.
Biography: Yi-Hsuan Yang is an Associate Research Fellow with Academia Sinica. He received his Ph.D. degree in Communication Engineering from National Taiwan University in 2010. He is also a Joint-Appointment Associate Professor with the National Cheng Kung University, Taiwan. His research interests include music information retrieval, affective computing, multimedia, and machine learning. Dr. Yang was a recipient of the 2011 IEEE Signal Processing Society Young Author Best Paper Award, the 2012 ACM Multimedia Grand Challenge First Prize, the 2014 Ta-You Wu Memorial Research Award of the Ministry of Science and Technology, Taiwan, and the 2015 Best Conference Paper Award of the IEEE Multimedia Communications Technical Committee. He is an author of the book Music Emotion Recognition (CRC Press 2011). In 2014, he served as a Technical Program Co-Chair of the International Society for Music Information Retrieval Conference (ISMIR). In 2016, he started his term as an Associate Editor for the IEEE Transactions on Affective Computing and the IEEE Transactions on Multimedia. Dr. Yang is a senior member of the IEEE.
Host: C.-C. Jay Kuo
More Information: Yi-Hsuan Yang Seminar Announcement .pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Gloria Halfacre
-
NL Seminar-A Tale of Two Question Answering Systems
Fri, Jul 27, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Matt Gardner, Allen Institute for Artificial Intelligence AI2
Talk Title: A Tale of Two Question Answering Systems
Series: Natural Language Seminar
Abstract: The path to natural language understanding goes through increasingly challenging question answering tasks. I will present research that significantly improves performance on two such tasks: answering complex questions over tables, and open-domain factoid question answering. For answering complex questions, I will present a type-constrained encoder decoder neural semantic parser that learns to map natural language questions to programs. For open-domain factoid QA, I will show that training paragraph level QA systems to give calibrated confidence scores across paragraphs is crucial when the correct answer containing paragraph is unknown. I will conclude with some thoughts about how to combine these two disparate QA paradigms, towards the goal of answering complex questions over open-domain text.
Biography: Matt Gardner is a research scientist at the Allen Institute for Artificial Intelligence AI2, where he has been exploring various kinds of question answering systems. He is the lead designer and maintainer of the AllenNLP toolkit, a platform for doing NLP research on top of pytorch. Matt is also the cohost of the NLP Highlights podcast, where, with Waleed Ammar, he gets to interview the authors of interesting NLP papers about their work. Prior to joining AI2, Matt earned a PhD from Carnegie Mellon University, working with Tom Mitchell on the Never Ending Language Learning project.
Host: Nanyun Peng
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
