I-DISC has built up a comprehensive library of presentations and other materials from workshops and events they have hosted since the inception of the institute in 2019
NSF TRIPODS+X Workshops (2019-2023)
These were a series of collaborative, interdisciplinary specialized workshops on the topic of machine learning as it applies to a variety of emerging applications and academic pursuits. The goal was to enable the sharing of expertise across various areas of science and engineering that have a stake in the surge in the adoption of machine learning technologies and tools.
Foundational & Applied Data Science for Molecular & Material Science & Engineering Conference
Iacocca Hall, Lehigh University. (Held May 22-24, 2019)
Data science has become ubiquitous in science and engineering. There is a tremendous recent surge in the adoption of machine learning tools in physics, chemistry, chemical engineering, materials science, and related disciplines to elucidate and design complex processes (chemical/biological, engineered/natural) or material systems with wide ranging applications addressing grand challenges in energy, health, environment, and water. At this critical juncture, the “practitioners” of ML in these fields, in both academia and industry, will benefit from close interaction with “developers” of modern ML tools (i.e. data scientists) who, in turn, can learn the problems and the needs of specific domains. To foster this relationship in the spirit of the NSF TRIPODS+X program, this interdisciplinary conference brings together foundational data scientists and domain practitioners to give talks to a common audience. The specific focal area of the conference is the development and application of data science algorithms and tools to address problems in molecular and materials science and engineering (i.e. any problem spanning the length scale of atoms to bulk materials).
Srinivas Rangarajan and Jeetain Mittal, Chemical & Biomolecular Engineering.
Payel Das, IBM Research AI, T J Watson Research Center.
Joshua Agar, Materials Science & Engineering, Lehigh University.
Paulette Clancy, Johns Hopkins University
“Merging Physical Science and Machine Learning to Tackle Complexity and Combinatorics in Materials Processing.”
Robot Learning Workshop - Overview
Iacocca Hall, Lehigh University. (Held October 14-15, 2019)
This was a 2 day NSF funded workshop consisiting of a series of presentations on emerging directions within intersection of robotics, deep and reinforcement learning, control systems, and operational research. The primary objective of this event was to facilitate interactions between researchers from different disciplines interested in designing and implementing the envisioned autonomous robots. The broader impact of this workshop aimed to inspire the research community on new interdisciplinary directions in robotics, controls, and machine learning. We believe that presenting challenging and important problems, in a coherent fashion, to these communities will open up tremendous intellectual opportunities for research and attract young researchers and students to this timely and important research field.
Organizing Committee: Nader Motee, Lehigh University; Hector Munoz-Avila, Lehigh University; Katya Scheinberg, Cornell University; Jeff Trinkle, Lehigh University.
Workshop Schedule (pdf)
Workshop Presentations, Bios, Abstracts and Videos
I-DISC wishes to thank all the speakers that kindly gave us permission to record and share their presentations with you:
Adaptive Learning for Multi-Agent Navigation
Presentation by Maria Gini, University of Minnesota
Abstract: In crowded multi-agent navigation, the motion of the agents is constrained by the motion of nearby agents. This makes planning paths difficult and leads to inefficient global motion. We formulate the problem as an action-selection problem, and propose an approach that enables agents to compute in real-time efficient and collision-free motions. We demonstrate experimentally how the approach works in a variety of scenarios in simulation and with a few real robots.
Learning Geometry-Aware Representations: 3D Object and Human Pose Inference
Presentation Kostas Daniilidis, University of Pennsylvania
Abstract: Traditional convolutional networks exhibit unprecedented robustness to intraclass nuisances when trained on big data. However, such data have to be augmented to cover geometric Transformations. Several approaches have shown recently that data augmentation can be avoided if networks are structured such that feature representations are transformed the same way as the input, a desirable property called equivariance. We show in this talk that global equivariance can be achieved for the case of 2D scaling, rotation, and translation as well as 3D rotations. We show state of the art results using an order of magnitude lower capacity than competing approaches. Moreover, we show how such geometric embeddings can recover the 3D pose of objects without key points or using groundtruth pose on regression. We finish by showing how graph convolutions enable the recovery of human pose and shape without any 2D annotation.
Autonomous Systems in the Intersection of Controls, Learning Theory and Formal Methods
Presentation by Ufuk Topcu, The University of Texas at Austin
Abstract: Autonomous systems are emerging as a driving technology for countlessly many applications. Numerous disciplines tackle the challenges toward making these systems agile, adaptable, reliable, user friendly and economical. On the other hand, the existing disciplinary boundaries delay and possibly even obstruct progress. I argue that the non-conventional problems that arise in the design and verification of autonomous systems require hybrid solutions at the intersection of learning, formal methods and controls. I will present examples of such hybrid solutions in several problems in autonomy at varying levels of detail.
Learning Dynamical Systems with Side Information
Presentation by Amir Ali Ahmadi, Princeton University
Abstract: In several safety-critical applications, one has to learn the behavior of an unknown dynamical system from noisy observations of a very limited number of trajectories. For example, to autonomously land an airplane that has just gone through engine failure, limited time is available to learn the modified dynamics of the plane before appropriate control action can be taken. Similarly, when a new infectious disease breaks out, few observations are initially available to understand the dynamics of contagion. In situations of this type where data is limited, it is essential to exploit “side information -e.g. physical laws or contextual knowledge--to assist the task of learning. We present a mathematical formalism of the problem of learning a dynamical system with side information, where side information can mean a concrete collection of local or global properties of the dynamical system. We show that sum of squares optimization is particularly suited for learning a dynamical system that best agrees with the observations and respects the side information. Based on joint work with Bachir El Khadir (Princeton).
Deep Learning for Semantic Visual Navigation
Presentation by Alexander Toshev, Google AI
Abstract: One of the fundamental problems for autonomous intelligent agents is the ability to move in visually and spatially complex environments for the purpose of finding objects, places, etc. This problem, commonly referred to as Visual Semantic Navigation, has been heavily studied in various settings. However, in its generality, unexplored and dynamic environments, complex semantics, continuous adaptation to the environment, it still presents many challenges. Deep Learning, by enabling models to learn complex concepts from experience, has huge potential in solving these challenges. In this talk, we present a framework towards a learning-based solution for Visual Semantic Navigation. We focus on two recent results. First, we talk about visual representations suitable for learning navigation algorithms. These representations result in systems for object-driven navigation that generalize to unexplored environments and utilize large synthetic data. Second, we present an approach towards continuous exploration of a novel environment using a model with general external memory.
Kinodynamic Motion Planning with Q-Learning: An Online, Model-Free, and Safe Navigation Framework
Presentation by Kyriakos Vamvoudakis, Georgia Institute of Technology
Abstract: This talk will present an online kinodynamic motion planning algorithmic framework using asymptotically optimal rapidly-exploring random tree (RRT*) and continuous-time Q-learning, which we term as RRT-Q*. I will formulate a model-free Q-based advantage function and I will utilize integral reinforcement learning to develop tuning laws for the online approximation of the optimal cost and the optimal policy of continuous-time linear systems. A terminal state evaluation procedure is introduced to facilitate the online implementation. I will then propose a static obstacle augmentation and a local replanning framework, which are based on topological connectedness, to locally recompute the robot's path and ensure collision-free navigation. I will finally show simulations and a qualitative comparison to evaluate the efficacy of the proposed methodology.
Leveraging Deep Learning Models to Create a Natural Interface for Quadcopter Photography
Presentation by Gita Sukthankar, University of Central Florida
Abstract: A quadcopter can capture photos from vantage points unattainable for a human photographer, but teleoperating it to a good viewpoint is a non-trivial task. Since humans are good at composing photos, the aim of our research is to leverage deep learning to create a customizable flight controller that can capture photos under the guidance of a human photographer. Our system, the Selfie Drone Stick, allows the user to assign a vantage point to the quadcopter based on the phone’s sensors. The user takes a selfie with the phone once, and the quadcopter autonomously flies to the target viewpoint. The proliferation of open source deep learning models provided us with a large variety of options for the computer vision and flight control systems. This article describes three key innovations required to deploy the models on a real robot: 1) a new architecture for rapid object detection, DUNet; 2) an abstract state representation for transferring learning from simulation to the hardware platform; 3) reward shaping and staging paradigms for training a deep reinforcement learning controller. Without these improvements, we were unable to learn a flight controller that adequately supported the intuitive user interface.
From Optimization Algorithms to Dynamical Systems and Back
Presentation by Rene Vidal, Johns Hopkins University
Abstract: Recently, there has been an increasing interest in using tools from dynamical systems to analyze the behavior of simple optimization algorithms such as gradient descent and accelerated variants. This talk will present differential equations that model the continuous limit of the sequence of iterates generated by the alternating direction method of multipliers, as well as an accelerated variant. We employ the direct method of Lyapunov to analyze the stability of critical points of the dynamical systems and to obtain associated convergence rates.
Robust Guarantees for Perception-Based Control
Presentation by Nikolai Matni, University of Pennsylvania
Abstract: Motivated by vision-based control of autonomous vehicles, we consider the problem of controlling a known linear dynamical system for which partial state information, such as vehicle position, can only be extracted from high-dimensional data, such as an image. Our approach is to learn a perception map from high-dimensional data to partial-state observation, and its corresponding error profile, and then design a robust controller. We show that under suitable smoothness assumptions on the perception map and generative model relating state to high-dimensional data, an affine error model is sufficiently rich to capture all possible error profiles, and can further be learned via a robust regression problem. We then show how to integrate the learned perception map and error model into a novel robust control synthesis procedure, and prove that the resulting perception and control loop has favorable generalization properties. Finally, we illustrate the usefulness of our approach on a synthetic example and on the self-driving car simulation platform CARLA.
Perceptual Robot Learning
Presentation by David Held, Carnegie Mellon University
Abstract: Robots today are typically confined to operate in relatively simple, controlled environments. One reason for these limitations is that current methods for robotic perception and control tend to break down when faced with occlusions, viewpoint changes, poor lighting, unmodeled dynamics, and other challenging but common situations that occur when robots are placed in the real world. I argue that, in order to handle these variations, robots need to learn to understand how the world changes over time: how the environment can change as a result of the robot’s own actions or from the actions of other agents in the environment. I will show how we can apply this idea of understanding changes to a number of robotics problems, such as object segmentation, tracking, and velocity estimation for autonomous driving as well as perception and control for various object manipulation tasks, including transparent, reflective, and deformable objects. By learning how the environment can change over time, we can enable robots to operate in the complex, cluttered environments of our daily lives.
Show and Tell: Robots Learning Actions from Vision and Language
Presentation by Yiannis Aloimonos, University of Maryland
Abstract: Context-free grammars have been in fashion in linguistics because they provide a simple and precise mechanism for describing the methods by which phrases in some natural language are built from smaller blocks. Also, the basic recursive structure of natural languages, the way in which clauses nest inside other clauses, and the way in which lists of adjectives and adverbs are followed by nouns and verbs, is described exactly. Similarly, for manipulation actions, every complex activity is built from smaller blocks involving hands and their movements, as well as objects, tools and the monitoring of their state. Thus, interpreting a “seen” action is like understanding language, and executing an action from knowledge in memory is like producing language. Several experiments will be shown interpreting human actions in the arts and crafts or assembly domain, through a parsing of the visual input, on the basis of the manipulation grammar. This parsing, in order to be realized, requires a network of visual processes that attend to objects and tools, segment them and recognize them, track the moving objects and hands, and monitor the state of objects to calculate goal completion. These processes will also be explained and we will conclude with demonstrations of robots learning how to perform tasks by watching videos of relevant human activities.
Topics in Graph Deep Learning
Presentation by Radu Balan, University of Maryland
Abstract: In this talk we discuss two problems seemingly unrelated: representations of permutation invariant data sets and quadratic assignment optimization problems. Two matrices of same size are called permutation equivalent if they are equal to one another up to a row permutation. The first problem asks for an Euclidian embedding of the quotient space induced by the row permutation equivalence relation. As we shall see, the problem admits several equivalent formulations. We shall discuss representations inspired by results from commutative algebra theory, measure theory, and reproducing kernel Hilbert space theory. This problem has direct application to graph classification problems where the underlying network has a natural equivariance property. The quadratic assignment problem is a NP hard optimization problem. We shall analyze an approach using graph convolution networks (GCN). We prove that a specially designed GCN produces the optimal solution for a broad class of assignment problems.
Distributed Image Classification using Deep Reinforcement Learning
Presentation by Martin Takac, Lehigh University
Abstract: We propose a planning and perception mechanism for robots (agents), that can only observe the underlying environment partially, in order to solve an image classification problem. We study two different settings: a) using a single agent which is choosing a goal location where we plans to get; b) and multiple agent scenarios where agents learn how to communicate to achieve the classification goal. Our proposed methodology is tested on the MNIST dataset of handwritten digits, which provides us with a level of explainability while interpreting the agent's understanding of the world and actions. Coauthors: Hossein K. Mousavi, Guangyi Liu, Weihang Yuan, Mohammad Reza Nazari, Héctor Muñoz-Avila, Nader Motee Papers: https://arxiv.org/abs/1909.09705 https://arxiv.org/abs/1905.04835 Bio: Prof Takác received his B.S. (2008) and M.S. (2010) degrees in Mathematics from Comenius University, Slovakia, and Ph.D. (2014) degree in Mathematics from The University of Edinburgh, United Kingdom. He received several awards during this period, including the Best Ph.D. Dissertation Award by the OR Society (2014), Leslie Fox Prize (2nd Prize; 2013) by the Institute for Mathematics and its Applications, and INFORMS Computing Society Best Student Paper Award (runner up; 2012). Since 2014, he is a Tenure Track Assistant Professor in the Department of Industrial and Systems Engineering at Lehigh University, USA. His current research interests include the design, analysis and application of algorithms for machine learning, optimization, highperformance computing, operations research and energy systems.
The Many Faces of Learning
Presentation by Don Perlis, University of Maryland
Abstract: Machine learning (ML) is only one of various forms of learning. I will describe several of these, and how they may fit together in a "complete robotic system”.
Learning Stabilizable Nonlinear Dynamics with Contraction-Based Regularization
Presentation by Sumeet Singh, Stanford University¹
Abstract: When it works, model-based Reinforcement Learning (RL) typically offers major improvements in sample efficiency in comparison to model-free techniques such as policy gradients that do not explicitly estimate the underlying dynamical system. Yet, all too often, when standard supervised learning is applied to model complex dynamics, the resulting controllers do not perform at par with model-free RL methods in the limit of increasing sample size, due to compounding errors across long time horizons. In this talk, I will present novel algorithmic tools leveraging Lyapunovbased analysis and semi-infinite convex programming to derive a control-theoretic regularizer for dynamics fitting, rooted in the notion of trajectory stabilizability. I will demonstrate how to embed these control-theoretic conditions as constraints within a semi-supervised algorithm for learning dynamical systems from user demonstrations. The constraints act as a form of context-driven hypothesis pruning to yield learned models that jointly balance regression performance and stabilizability, ultimately resulting in generated trajectories for the robot that are conditioned for feedback control. Experimental results on a quadrotor testbed will illustrate the efficacy of the proposed algorithms and clear connections between theory and hardware.
1Now at Google Brain Robotics
Iacocca Hall, Lehigh University.
Held: December 13-14, 2021
The TRIPODS+X workshop on Machine Learning & Supply Chain Management featured speakers from academia and industry whose research and practice makes innovative use of machine learning (ML) for making decisions in supply chains. Most recent applications of ML for supply chains fall under the categories of either descriptive or predictive analytics. For example, clustering methods have been used to segment customers or suppliers (descriptive), and deep neural networks have been applied to forecast demands (predictive). In contrast, the focus of this workshop was on the use of ML for prescriptive analytics within the supply chain—on using ML to optimize supply chains.
The aim of this workshop was to bring together researchers from both the ML and supply chain communities in order to foster a vibrant exchange of ideas and to stimulate new collaborations. The workshop featured:
- 13 invited speakers
- poster session for students
- panel discussion
Joren Gijsbrechts, Universidade Católica Portuguesa, Portugal
- Swati Gupta, Georgia Tech, USA
- Andrea Lodi, Cornell Tech, USA
- Polly Mitchell-Guthrie, Kinaxis, USA
- Richard Pibernik, Julius-Maximilians-University, Würzburg, Germany
- Cynthia Rudin, Duke University, USA
- Zuo-Jun Max Shen, UC-Berkeley, USA / Univ. of Hong Kong
- David B. Shmoys, Cornell University, NY, USA
- Larry Snyder, Lehigh University, USA
- Jiankun Sun, Imperial College London, UK
- Martin Takáč, Lehigh University, Bethlehem, USA / Mohamed bin Zayed University of Artificial Intelligence, UAE
- Barrett Thomas, University of Iowa, USA
- Michael Watson, Coupa Software, USA
Organizers: Larry Snyder & Jan Van Mieghem
WORKSHOP ON CATASTROPHE MODELING AND DATA
The Catastrophe Modeling Center hosted its first outreach event: a workshop at the Millennium Downtown Hotel in New York. Stakeholders and experts from private sector, public sector, and academia participated, shared their experience, and exchanged ideas.
This workshop will bring together researchers and practitioners from academia and industry to discuss challenges and recent advances in the field. Panels and presentations will showcase how machine learning, optimization and other algorithmic tools can make cities more equitable, efficient and sustainable.
Technological innovations are creating opportunities for cities to rethink the way in which they address pressing and complex challenges. These include: mitigating and adapting to climate change, which has prompted researchers to design innovative prevention tools and disaster relief measures with the goal of making cities more robust; responding to the algorithmic economy (e.g., ride-hailing, bike-sharing systems, delivery systems), which has revolutionized our interactions with each other in the city; innovations in real-time information to help users’ decision-making, including smart infrastructure that aims to create a more sustainable ecosystem (e.g., energy efficient buildings, robust communication networks, smart grids); and other developments across mobility, healthcare and, in general, public and private services, including the adoption of autonomous vehicles, computer-assisted healthcare, analytics for water management, robust supply chains, among others. These developments bring myriad new questions around security, privacy, efficiency, equity, and complexity, alongside old challenges in urban planning. This workshop will consider how machine learning and data-driven approaches can be used to improve quality of life in urban environments.
Data and Computing Equity and Justice (DCEJ)
- A.I. Nation: An artificial intelligence podcast - WHYY | Princeton University
A.I. Nation is a new podcast from WHYY and Princeton University that reveals how artificial intelligence is operating in the background, and sometimes foreground, of every major story, trend, and event in our modern lives.
"...I've listened to the first few episodes , and so far they seem to do a good job of taking a balanced view of AI and its advantages, risks, pitfalls etc.." Larry Snyder (ISE)
- WNYC Studios - Radiolab Presents: G
Investigating a strange world.
"This is a very good series about inequalities in IQ test." Josh Agar (MSE)
- Rabbit Hole
What is the internet doing to us? “Rabbit Hole,” a new narrative audio series from The New York Times, explores what happens when our lives move online. Follow the tech columnist Kevin Roose as he dives into stories of how the internet is changing, and how we’re changing along with it.
- When We Know More We Can Do More Part 2 - Internet2
Lehigh University is a member of Internet2.
This special virtual session continues the discussion with Avis Yates Rivers about diversity, equity and inclusion.
- Beibei Dong on the Risks of Letting AI Choose Your News | Lehigh Business
Research by two Lehigh Business faculty members suggests there is cause for concern over the increasing role AI plays in choosing what appears in our news feeds.
- The Hechinger Report: OPINION: A lack of diversity in research and analytics is not just unethical — it is dangerous
Today, people of color are underrepresented in all aspects of STEM. This matters and we are working to change it.
- NYT article Sep 3, 2021. By Ryan Mac
Facebook Apologizes After A.I. Puts ‘Primates’ Label on Video of Black Men
Facebook called it “an unacceptable error.” The company has struggled with other issues related to race.
- ACM CSCW: Datasheets for Datasets help ML engineers notice and understand ethical issues in training data
"A study showing some progress" -- Brian Davison
"Interesting [article]. Actually the Datasheets for Datasets idea originates from a paper by Timnit Gebru, who was later fired by Google for another paper she wrote criticizing large language models. Haven’t seen the DfD idea tested or implemented though — that’s cool." --Larry Snyder
References and Guidelines
- A Guide to Gender Identity Terms (NPR)
- A Guide Toward Diversity, Equity, and Inclusion (DEI) in Data Collection - Digital Promise
- OptML Talk by Larry Snyder created a lot of examples of ML bias and fairness on his Twitter feed: https://twitter.com/LarrySnyder610/status/1435956821299245061
Other Links to Resources
- The Alan Turing Institute - trying to build a diverse community
Equality, diversity and inclusion
- "For everyone who has opinions on on AI fairness, bias, security, etc., the federal government wants your thoughts..." -- Brian Davison https://cccblog.org/2021/08/19/request-for-information-rfi-on-an-implementation-plan-for-a-national-artificial-intelligence-research-resource-2/