Sponsored by VAIL Systems
Friday, Feburary 26
12:00 – 15:00
Zoom link in registration email
The goal of Machine Learning is to understand fundamental principles and capabilities of learning from data, as well as designing and analyzing machine learning algorithms. We invite you to the Machine Learning and Signal Processing Session of the CSL student conference if you are curious about when, how, and why machine learning algorithms work.
The session consists of a keynote speech given by Prof. Sameer Singh, followed by several student talks in which students present their current research. Besides the theoretical aspects of machine learning, this session covers topics including (but not limited to) computer vision, NLP, statistical inference, deep learning, graphical models, signal processing, etc.
Keynote Speaker – Prof. Sameer Singh, University of California, Irvine
Title: Evaluating and Testing Natural Language Processing Models
Time: 14:00 – 15:00, Feburary 26
Abstract: Current evaluation of natural language processing (NLP) systems, and much of machine learning, primarily consists of measuring the accuracy on held-out instances of the dataset. Since the held-out instances are often gathered using similar annotation process as the training data, they include the same biases that act as shortcuts for machine learning models, allowing them to achieve accurate results without requiring actual natural language understanding. Thus held-out accuracy is often a poor proxy for measuring generalization, and further, aggregate metrics have little to say about where the problem may lie.
In this talk, I will introduce a number of approaches we are investigating to perform a more thorough evaluation of NLP systems. I will first provide an overview of automated techniques for perturbing instances in the dataset that identify loopholes and shortcuts in NLP models, including semantic adversaries and universal triggers. I will then describe recent work in creating comprehensive and thorough tests and evaluation benchmarks for NLP that aim to directly evaluate comprehension and understanding capabilities. The talk will cover a number of NLP tasks, including sentiment analysis, textual entailment, paraphrase detection, and question answering.
Biography: Sameer Singh is an Assistant Professor of Computer Science at the University of California, Irvine (UCI). He is working primarily on robustness and interpretability of machine learning algorithms, along with models that reason with text and structure for natural language processing. Sameer was a postdoctoral researcher at the University of Washington (w/ Carlos Guestrin and late Ben Taskar) and received his PhD from the University of Massachusetts, Amherst (w/ Andrew McCallum), during which he also worked at Microsoft Research, Google Research, and Yahoo! Labs. He was selected as a DARPA Riser, and has been awarded the grand prize in the Yelp dataset challenge, the Yahoo! Key Scientific Challenges (story), UCI Mid-Career Excellence in research award, and recently received the Hellman Fellowship in 2020. His group has received funding from Amazon, Allen Institute for AI, NSF, DARPA, Adobe Research, Base 11, and FICO. Sameer has published extensively at machine learning and natural language processing conferences and workshops, including paper awards at KDD 2016, ACL 2018, EMNLP 2019, AKBC 2020, and ACL 2020.
Student Keynote Speaker – Ye Yuan
Title: Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
Time: 12:05 – 12:35, Feburary 26
Abstract: Reinforcement learning has shown great promise for synthesizing realistic human behaviors by learning humanoid control policies from motion capture data. However, it is still very challenging to reproduce sophisticated human skills like ballet dance, or tostably imitate long-term human behaviors with complex transitions. The main difficulty lies in the dynamics mismatch between the humanoid model and real humans. That is, motions of real humans may not be physically possible for the humanoid model. To overcome the dynamics mismatch, we propose a novel approach, residual force control (RFC), that augments a humanoid control policy by adding external residual forces into the action space. During training, the RFC-based policy learns to apply residual forces to the humanoid to compensate for the dynamics mismatch and better imitate the reference motion. Experiments on a wide range of dynamic motions demonstrate that our approach outperforms state-of-the-art methods in terms of convergence speed and the quality of learned motions. Notably, we showcase a physics-based virtual character empowered by RFC that can perform highly agile ballet dance moves such as pirouette, arabesque and jeté. Furthermore, we propose a dual-policy control framework, where a kinematic policy and an RFC-based policy work in tandem to synthesize multi-modal infinite-horizon human motions without any task guidance or user input. Our approach is the first humanoid control method that successfully learns from a large-scale human motion dataset (Human3.6M) and generates diverse long-term motions.
Student Speakers
Kiran Ramnath, UofI
Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings
12:35 – 12:55, Feburary 26
Nikhita Sharma (Vail Systems) and Patrick Su (UofI)
CLAIRE: Clean Room Automation using Conversational AI
12:55 – 13:20, Feburary 26
Anadi Chaman, UofI
Truly Shift-invariant Convolutional Neural Networks
13:20 – 13:40, Feburary 26
Corey Snyder (UofI) and Molly Dasso (UofI)
SMILE: A Semi-supervised Multiple Instance Learning Framework for Object Detection
13:40 – 14:00, Feburary 26