![]() ![]() He is also a CIFAR Fellow of Learning in Machines & Brains and an Associate Member of the National Academy of Engineering of Korea. Kyunghyun Cho is an associate professor of computer science and data science at New York University and a senior director of frontier research at the Prescient Design team within Genentech Research & Early Development (gRED). Finally for inference, I will lay out two consistencies that must be satisfied by a large-scale language model and demonstrate that most of the language models do not fully satisfy such consistencies. For optimization, I will talk about how we can systematically study and investigate learning trajectories. For model assumption and construction, I will discuss our recent work on generative multitask learning and incidental correlation in multimodal learning. Specifically, I will discuss three such aspects in this talk (1) model assumption and construction, (2) optimization and (3) inference. There are however many aspects in building a machine learning system that require more attention. The machine learning community has however continued to stick to this paradigm until now (2023), relying almost entirely and exclusively on the test-set accuracy, which is a rough proxy to the true quality of a machine learning system we want to measure. Talks Beyond Test Accuracies for Studying Deep Neural NetworksĪlready in 2015, Leon Bottou discussed the prevalence and end of the training/test experimental paradigm in machine learning. The Lunch and Poster Session will take place at 370 Jay St, Room 233. The workshop will be hosted in New York University's Pfizer Auditorium, 5 MetroTech Center - Dibner Hall, in Brooklyn, NY. We will only be able to accommodate a limited number of participants, so we encourage those interested in attending this event to register as soon as possible by sending an email to with your name and affiliation. ![]() Schedule Click on the talk title to jump to the abstract and bio.Īudio-Visual Learning for Video Understandingĭeep Hybrid Learning and Its Application to Unsupervised Singing Voice Separationĭefining "Source" in Audio Source Separationīeyond Test Accuracies for Studying Deep Neural NetworksĪudio-Text Learning for Automated Audio Captioning and GenerationĪudio Large Language Models: From Sound Perception to Understanding Venue: Pfizer Auditorium, New York University, 5 MetroTech Center - Dibner Hall, Brooklyn, New York.It will also feature a lively poster session, open to both students and researchers. SANE 2023 will feature invited talks by leading researchers from the Northeast as well as from the wider community. This year's SANE will take place in conjunction with the WASPAA workshop, held October 22-25 in upstate New York. ![]() Since the first edition, the audience has steadily grown, with a record 200 participants and 45 posters in 2019. It is the 10th edition in the SANE series of workshops, which started in 2012 and is typically held every year alternately in Boston and New York. SANE 2023, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, will be held on Thursday Octoat NYU in Brooklyn, New York. SANE 2023 - Speech and Audio in the Northeast October 26, 2023
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |