- Ai - Engineering Mailing Lists

AI alignment reading group: Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges
by Turner, Alex 02 Jun '21

02 Jun '21

This week, we'll be reading Rudin et al's "Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges": "Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic. We also identify 10 technical challenge areas in interpretable machine learning and provide history and background on each problem. Some of these problems are classically important, and some are recent problems that have arisen in the last few years. These problems are: (1) ... (9) Characterization of the "Rashomon set" of good models; and (10) Interpretable reinforcement learning." This is a long paper, but I'm particularly interested in discussing (9): Rashomon sets of models. In what situations should we expect black-box models (e.g. deep neural networks) to have interpretable counterparts (e.g. sparse logical models / decision trees) with similar performance? The answer to this question will help govern competitive pressures for using/not using interpretable models, and also inform the difficulty of supervising the computation performed by potential future human-level ML systems. The paper: https://arxiv.org/abs/2103.11251 We'll meet Friday at 1. https://oregonstate.zoom.us/j/2739792686?pwd=VkRUeHJkYnhvTzlvZzR6YnZWNERKQT… Best, Alex Turner

1 0

OSU AI Seminar - June 2 2021 | Jiajun Wu - Stanford University
by Patravali, Jay Sanjay 29 May '21

29 May '21

Dear All, Our last speaker for this Spring term will be Prof. Jiajun Wu from Stanford University. He will be presenting *"*Learning to See the Physical World *"* on *Wednesday 6/2 from 1.00-2.00PM PT.* Zoom Link: https://tinyurl.com/5wn8zczw Please find attached the poster flyer for more information. *Title*: Learning to See the Physical World *Abstract*: Human intelligence is beyond pattern recognition. From a single image, we're able to explain what we see, reconstruct the scene in 3D, predict what's going to happen, and plan our actions accordingly. In this talk, I will present our recent work on physical scene understanding---building versatile, data-efficient, and generalizable machines that learn to see, reason about, and interact with the physical world. The core idea is to exploit the generic, causal structure behind the world, including knowledge from computer graphics, physics, and language, in the form of approximate simulation engines, and to integrate them with deep learning. Here, deep learning plays two major roles: first, it learns to invert simulation engines for efficient inference; second, it learns to augment simulation engines for constructing powerful forward models. I'll focus on a few topics to demonstrate this idea: building scene representation for both object geometry and physics; learning expressive dynamics models for planning and control; perception and reasoning beyond vision. *Bio*: Jiajun Wu is an Assistant Professor of Computer Science at Stanford University, working on computer vision, machine learning, and computational cognitive science. Before joining Stanford, he was a Visiting Faculty Researcher at Google Research. He received his Ph.D. at the Massachusetts Institute of Technology. Wu's research has been recognized through the ACM Doctoral Dissertation Award Honorable Mention, the AAAI/ACM SIGAI Doctoral Dissertation Award, the 2020 Samsung AI Researcher of the Year, the IROS Best Paper Award on Cognitive Robotics, and faculty research awards and graduate fellowships from Samsung, Amazon, Facebook, Nvidia, and Adobe. Please plan on attending! Thanks, Jay Patravali Graduate Student, CoRIS-EECS. Oregon State University ---- AI Seminar Important Reminders: -> The AI Seminar has a strict "no electronics" and "no recordings" policy. -> For graduate students in the AI program, attendance is strongly encouraged.

1 0

[CoRIS-List] Starting Now: Antonio Bicchi
by Hatton, Ross 21 May '21

21 May '21

Hi All, Today's seminar is starting now: Antonio Bicchi (Istituto Italiano di Tecnologia) Speaker bio: https://roboticstoday.github.io/ Watch link: https://roboticstoday.github.io/watch.html Pre- and post-seminar Gather space for OSU Robotics attendees (with an integrated link to the main talk) is at https://gather.town/app/HeC6WAB1zL6cKWp5/OSU%20Robotics%20Seminar -Ross =========== Ross L. Hatton Associate Professor, Robotics and Mechanical Engineering Collaborative Robotics and Intelligent Systems Institute Oregon State University coris.oregonstate.edu research.engr.oregonstate.edu/lram/ rosslhatton.com ross.hatton(a)oregonstate.edu

1 0

[CoRIS-List] Reminder: Friday Noon: Antonio Bicchi
by Hatton, Ross 19 May '21

19 May '21

Hi All, As a reminder, we have a Robotics Today broadcast seminar at noon on Friday: Antonio Bicchi (Istituto Italiano di Tecnologia) Speaker bio: https://roboticstoday.github.io/ Watch link: https://roboticstoday.github.io/watch.html Pre- and post-seminar Gather space for OSU Robotics attendees (with an integrated link to the main talk) is at https://gather.town/app/HeC6WAB1zL6cKWp5/OSU%20Robotics%20Seminar -Ross =========== Ross L. Hatton Associate Professor, Robotics and Mechanical Engineering Collaborative Robotics and Intelligent Systems Institute Oregon State University coris.oregonstate.edu research.engr.oregonstate.edu/lram/ rosslhatton.com ross.hatton(a)oregonstate.edu

1 0

OSU AI Seminar - **Today** 1PM | Stephen Ramsey - Oregon State University
by Patravali, Jay Sanjay 19 May '21

19 May '21

Dear All, A gentle reminder that our next seminar will be by Prof. Stephen Ramsey from Oregon State University. He will be presenting *"*Computationally analyzing knowledge graphs and using machine-learning for drug repositioning and precision oncology applications*"* *today 5/19 from 1.00-2.00PM PT.* Zoom Link: https://tinyurl.com/yup7cppa Please find attached the poster flyer for more information. *Title*: Computationally analyzing knowledge graphs and using machine-learning for drug repositioning and precision oncology applications *Abstract*: I will describe our work on two projects: an NIH consortium project, the Biomedical Data Translator, and a project to use machine learning to improve outcomes in cancer treatment. The Biomedical Data Translator project's broad aim is to advance translational science using computer-aided knowledge exploration and reasoning. Our team is developing a reasoning system, ARAX, that is geared toward drug repositioning for common diseases and therapeutic recommendation for rare inherited diseases. I will describe some of the principles behind this system and key challenges inherent to building scalable reasoning systems. For the precision oncology project, I will also present some recent work in our lab on using machine-learning to predict response to chemotherapy based on transcriptome data acquired from tumor samples. *Bio*: Stephen is a computational biologist whose PhD work was in computational physics. At OSU, Stephen holds a dual appointment in the Department of Biomedical Sciences and in the School of Electrical Engineering and Computer Science. Stephen's research has been recognized by multiple awards including an NIH K25 Career Development Award, a PhRMA New Investigator Award, an NSF CAREER award, and the Carlson College of Veterinary Medicine Zoetis Award. Please plan on attending! Thanks, Jay Patravali Graduate Student, CoRIS-EECS. Oregon State University ---- AI Seminar Important Reminders: -> The AI Seminar has a strict "no electronics" and "no recordings" policy. -> For graduate students in the AI program, attendance is strongly encouraged.

1 0

Alignment reading group: the lottery ticket hypothesis
by Turner, Alex 18 May '21

18 May '21

This Friday, we'll discuss "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" and related papers: "The Lottery Ticket Hypothesis: A randomly-initialized, dense neural network contains a subnetwork that is initialised such that — when trained in isolation — it can match the test accuracy of the original network after training for at most the same number of iterations." Paper: https://openreview.net/forum?id=rJl-b3RcF7 Literature survey: https://towardsdatascience.com/the-lottery-ticket-hypothesis-a-survey-d1f0f… Additional LTH-related papers found in this post and comment: https://www.alignmentforum.org/posts/dpzLqQQSs7XRacEfK/understanding-the-lo… We'll meet Friday at 1. https://oregonstate.zoom.us/j/2739792686?pwd=VkRUeHJkYnhvTzlvZzR6YnZWNERKQT…

1 0

Alignment reading group: cooperative AI
by Turner, Alex 14 May '21

14 May '21

This Friday, we'll discuss "Cooperative AI: machines must learn to find common ground": "AI needs social understanding and cooperative intelligence to integrate well into society. The coming years might give rise to diverse ecologies of AI systems that interact in rapid and complex ways with each other and with humans: on pavements and roads, in consumer and financial markets, in e-mail communication and social media, in cybersecurity and physical security. Autonomous vehicles or smart cities that do not engage well with humans will fail to deliver their benefits, and might even disrupt stable human relationships." Comment: https://www.nature.com/articles/d41586-021-01170-0 Alignment newsletter summary: https://www.alignmentforum.org/posts/3zmKzbMPjPvEcZfkn/an-150-the-subtypes-… We'll meet Friday at 1. https://oregonstate.zoom.us/j/2739792686?pwd=VkRUeHJkYnhvTzlvZzR6YnZWNERKQT…

1 0

[CoRIS-List] Reminder: Friday, 10am: Hannah Stuart
by Hatton, Ross 12 May '21

12 May '21

Hi All, As a reminder, we have an OSU Robotics Zoom seminar at 10am on Friday: Hannah Stuart (UC Berkeley) Watch link: *https://oregonstate.zoom.us/j/97644079157?pwd=WXRZeEhOR0padXVzb2NkVkVkVEFmZz09 <https://oregonstate.zoom.us/j/97644079157?pwd=WXRZeEhOR0padXVzb2NkVkVkVEFmZ…>* Title: Hands for underwater manipulation: Design for robust and sensitive grasping Abstract: Capable dexterous manipulation allows marine robots and remotely operated vehicles (ROV) to perform more useful manual tasks. The focus of interaction is often delegated to a set of robotic hands that grip natural objects, tools and structures. Not only must end-effectors meet desired performance (e.g., not damaging delicate items, handling structures with strength, etc.), but withstand uncertainty, collisions, and the extreme pressures associated with depth. In this talk, I will discuss the design of resilient and compliant underwater-capable grippers, including the field-tested hands of the Ocean One ROV. Small changes to contact conditions, such as gentle suction flow or soft skin, can have a disproportionate effect for underwater hands. In particular, suction flow can be harnessed as a useful tactile sensor suitable for the submerged environment. Discussion will compare and contrast the utility of different technologies in air versus under water. Bio: Dr. Hannah Stuart is an Assistant Professor in the Department of Mechanical Engineering at the University of California at Berkeley. She received her BS in Mechanical Engineering at the George Washington University in 2011, and her MS and PhD in Mechanical Engineering at Stanford University in 2013 and 2018, respectively. Her research focuses on understanding the mechanics of physical interaction in order to better design systems for dexterous manipulation, especially in unstructured environments. Applications range from remote robotics to assistive orthotics. Recent awards include the NASA Early Career Faculty grant, Hellman Fellows Fund grant, and Johnson & Johnson Women in STEM2D grant. Pre- and post-seminar Gather space for OSU Robotics attendees (with an integrated link to the main talk) is at https://gather.town/app/HeC6WAB1zL6cKWp5/OSU%20Robotics%20Seminar -Ross =========== Ross L. Hatton Associate Professor, Robotics and Mechanical Engineering Collaborative Robotics and Intelligent Systems Institute Oregon State University coris.oregonstate.edu research.engr.oregonstate.edu/lram/ rosslhatton.com ross.hatton(a)oregonstate.edu

1 0

Signup and Officer Nominations for AIGSA Club
by Buss, Christopher 11 May '21

11 May '21

Hi AI Grads, The AI Graduate Student Association (AIGSA) is a new club whose goal is to build community among AI Graduate students through fun networking and professional development events. However, before we can start planning these events, we need *members* and *officers*. *Become a Member:* Funding for AIGSA is provided by the University, so becoming a member is free. Since AIGSA is a new club, it's important that you sign up <https://apps.ideal-logic.com/osusli?key=F3T9-25VWY_5878-CZ4R_f7b06f23> as a member if you are interested in taking part in future AIGSA events: funding is based on our membership count and we want to make sure that events have the capacity to include everyone who wants to participate. Once you sign up, you can also join us on our dedicated Slack workspace <http://eecs-aigsa.slack.com>. *Nominate Officers:* In order to plan events for next year, we also need officers. AIGSA has four officer positions: Co-Presidents (currently Matthew Olson and Christopher Buss), Secretary of Communication and Events, Secretary of Finances (currently Anurag Koul), and Secretary of Faculty Relations. You can learn more about each of the positions as well as submit nominations for them by checking out the individual nomination forms: - Co-Presidents Nomination Form <https://docs.google.com/forms/d/e/1FAIpQLSdzG0-J25ttH69P0gTolcSIc1KpQfiGnFZ…> - Secretary of Communication and Events Nomination Form <https://docs.google.com/forms/d/e/1FAIpQLScSQS3mK1XQpUGb7ZfDPUmCubaYdEs1YTu…> - Secretary of Finances Nomination Form <https://docs.google.com/forms/d/e/1FAIpQLSckvYMS2U_LRLV1pZhpDOTIVuV_61aF7GT…> - Secretary of Faculty Relations Nomination Form <https://docs.google.com/forms/d/e/1FAIpQLSfdSnNMrEdOtnGhWjg8PjcCDaMTWiKa9OY…> Feel free to submit multiple forms if you want to nominate multiple people. *The deadline for nominations is May 25th.* We hope to see you at future AIGSA events! Regards, AIGSA Officers

1 0

OSU AI Seminar - May 19 2021 | Stephen Ramsey - Oregon State University
by Patravali, Jay Sanjay 11 May '21

11 May '21

Dear All, Our next seminar will be by Prof. Stephen Ramsey from Oregon State University. He will be presenting *"*Computationally analyzing knowledge graphs and using machine-learning for drug repositioning and precision oncology applications*"* on *Wednesday 5/19 from 1.00-2.00PM PT.* Zoom Link: https://tinyurl.com/yup7cppa Please find attached the poster flyer for more information. *Title*: Computationally analyzing knowledge graphs and using machine-learning for drug repositioning and precision oncology applications *Abstract*: I will describe our work on two projects: an NIH consortium project, the Biomedical Data Translator, and a project to use machine learning to improve outcomes in cancer treatment. The Biomedical Data Translator project's broad aim is to advance translational science using computer-aided knowledge exploration and reasoning. Our team is developing a reasoning system, ARAX, that is geared toward drug repositioning for common diseases and therapeutic recommendation for rare inherited diseases. I will describe some of the principles behind this system and key challenges inherent to building scalable reasoning systems. For the precision oncology project, I will also present some recent work in our lab on using machine-learning to predict response to chemotherapy based on transcriptome data acquired from tumor samples. *Bio*: Stephen is a computational biologist whose PhD work was in computational physics. At OSU, Stephen holds a dual appointment in the Department of Biomedical Sciences and in the School of Electrical Engineering and Computer Science. Stephen's research has been recognized by multiple awards including an NIH K25 Career Development Award, a PhRMA New Investigator Award, an NSF CAREER award, and the Carlson College of Veterinary Medicine Zoetis Award. Please plan on attending! Thanks, Jay Patravali Graduate Student, CoRIS-EECS. Oregon State University ---- AI Seminar Important Reminders: -> The AI Seminar has a strict "no electronics" and "no recordings" policy. -> For graduate students in the AI program, attendance is strongly encouraged.

1 0