Uploaded May 2021 | Updated September 2026, 2 weeks ago
UCI AI/ML Seminar Series
https://cml.ics.uci.edu/aiml/
Megan Peters
Assistant Professor
Department of Cognitive Sciences
UC Irvine
How do we evaluate our own uncertainty? Uncovering our metacognitive computations
Abstract: TBA
Bio:
In March 2020 I joined the UCI Department of Cognitive Sciences. I’m also a Cooperating Researcher in the Department of Decoded Neurofeedback at Advanced Telecommunications Research Institute International in Kyoto, Japan. Prior to that, from 2017 I was on the faculty at UC Riverside in the Department of Bioengineering. I received my Ph.D. in computational cognitive neuroscience (psychology) from UCLA, and then was a postdoc there as well. My research aims to reveal how the brain represents and uses uncertainty, and performs adaptive computations based on noisy, incomplete information. I specifically focus on how these abilities support metacognitive evaluations of the quality of (mostly perceptual) decisions, and how these processes might relate to phenomenology and conscious awareness. I use neuroimaging, computational modeling, machine learning and neural stimulation techniques to study these topics.
UCI AI/ML Seminar Series
https://cml.ics.uci.edu/aiml/
Megan Peters
Assistant Professor
Department of Cognitive Sciences
UC Irvine
How do we evaluate our own uncertainty? Uncovering our metacognitive computations
Abstract: TBA
Bio:
In March 2020 I joined the UCI Department of Cognitive Sciences. I’m also a Cooperating Researcher in the Department of Decoded Neurofeedback at Advanced Telecommunications Research Institute International in Kyoto, Japan. Prior to that, from 2017 I was on the faculty at UC Riverside in the Department of Bioengineering. I received my Ph.D. in computational cognitive neuroscience (psychology) from UCLA, and then was a postdoc there as well. My research aims to reveal how the brain represents and uses uncertainty, and performs adaptive computations based on noisy, incomplete information. I specifically focus on how these abilities support metacognitive evaluations of the quality of (mostly perceptual) decisions, and how these processes might relate to phenomenology and conscious awareness. I use neuroimaging, computational modeling, machine learning and neural stimulation techniques to study these topics.


![AI/ML Seminar Series: Joe Marino (2/1/2021)
UCI AI/ML Seminar Series
https://cml.ics.uci.edu/aiml/
Joe Marino
PhD Student
Computation and Neural Systems
California Institute of Technology
Connecting Variational Autoencoders Back to the Brain
Unsupervised machine learning has recently dramatically improved our ability to model and extract structure from data. One such approach is deep latent variable models, which includes variational autoencoders (VAEs) [Kingma & Welling, 2014; Rezende et al., 2014]. These models can be traced back to the Helmholtz machine [Dayan et al., 1995], which, in turn, was inspired by ideas from theoretical neuroscience [Mumford, 1992]. In the intervening years, neuroscientists have further developed these ideas into a popular theory: predictive coding [Rao & Ballard, 1999; Friston, 2005]. Yet, the machine learning community remains largely unaware of these connections. In this talk, I discuss the links between modern deep latent variable models and predictive coding, yielding several striking implications for the correspondences between machine learning and neuroscience. This motivates a more nuanced view in connecting these fields, including the search for backpropagation in the brain.
Bio:
Joe Marino is a PhD candidate in the Computation & Neural Systems program at Caltech, advised by Yisong Yue. His work focuses on improving probabilistic models and inference techniques, using neuroscience-inspired ideas, within the areas of generative modeling and reinforcement learning. AI/ML Seminar Series: Joe Marino (2/1/2021)](https://i.ytimg.com/vi/iVz6uwD7i6A/mqdefault.jpg)

![Interaction-Centric AI: Designing Useful and Usable AI Applications
Juho Kim
Associate Professor, KAIST; Chief Scientist, Ringle
Abstract:
AI-powered services and applications are introduced at a rapid pace and massive scale across various domains. Remarkable model performance, however, does not necessarily translate to an improved user experience. I argue that human-AI interaction should be considered a first-class object in designing AI-powered systems. In this talk, I will present a few novel interactive systems that use AI to support complex real-life tasks. I will discuss how we considered human-AI interaction in designing these systems, what tensions we encountered and how we addressed them, and how to design better AI-powered systems for real-world users. My ultimate proposal is that we need a fundamental shift to “interaction-centric AI”—an approach to systematically designing and engineering human-AI interaction that overcomes the limitations of the model- and data-centric views.
Bio:
Juho Kim [juhokim.com] is an Associate Professor in the School of Computing at KAIST, affiliate faculty in the Kim Jaechul Graduate School of AI at KAIST, and a director of KIXLAB (the KAIST Interaction Lab) [kixlab.org]. His research in human-computer interaction and human-AI interaction focuses on building interactive and intelligent systems that support interaction at scale, with the goal of improving the ways people learn, collaborate, discuss, make decisions, and take action online. He earned his Ph.D. from MIT in 2015, M.S. from Stanford University in 2010, and B.S. from Seoul National University in 2008. In 2015-2016, he was a Visiting Assistant Professor and a Brown Fellow at Stanford University. He is a recipient of KAIST’s Songam Distinguished Research Award, Grand Prize in Creative Teaching, and Excellence in Teaching Award, as well as 14 paper awards from ACM CHI, ACM CSCW, ACM Learning at Scale, ACM IUI, ACM DIS, and AAAI HCOMP. He is currently spending his sabbatical year at Ringle Inc., a startup building an online language tutoring platform, to transfer his research on automatically analyzing and diagnosing learners’ English proficiency into a real product. Interaction-Centric AI: Designing Useful and Usable AI Applications](https://i.ytimg.com/vi/j0v1Cr74kN8/mqdefault.jpg)





