Category: CS

The Department of Computer Science will present a lecture, by Dr. Shane Mueller on Friday, January 22, 2021, at 3:00 p.m.

Mueller is an associate professor in the Applied Cognitive Science and Human Factors program of the Cognitive and Learning Science department. His lecture is titled, “Explainable AI, and principles for building human-centered XAI systems.”

Join the lecture here.

Mueller’s research focuses on human memory and the representational, perceptual, strategic, and decisional factors that support it. He employs applied and basic research methodologies, typically with a goal of implementing formal quantitative mathematical or computational models of cognition and behavior.

He is also the primary developer of the Psychology Experiment Building Language (PEBL), a software platform for creating psychology experiments.

Mueller has undergraduate degrees in mathematics and psychology from Drew University, and a Ph.D. in cognitive psychology from the University of Michigan. He was a senior scientist at Klein Associates Division of Applied Research Associates from 2006 to 2011. His research has been supported by NIH, DARPA, IARPA, the Air Force Research Laboratory, the Army Research Institute, the Defense Threat Reduction Agency, and others.

Lecture Title:

Explainable AI, and principles for building human-centered XAI systems

Lecture Abstract

In recent years, Explainable Artificial Intelligence (XAI) has re-emerged in response to the development of modern AI and ML systems. These systems are complex and sometimes biased, but they nevertheless make decisions that impact our lives. XAI systems are frequently algorithm-focused; starting and ending with an algorithm that implements a basic untested idea about explainability. These systems are often not tested to determine whether the algorithm helps users accomplish any goals, and so their explainability remains unproven. I will discuss some recent advances and approaches to developing XAI, and describe how many of these systems are likely to incorporate many of the lessons from past successes and failures to build explainable systems. I will then review some of the basic concepts that have been used for user-centered XAI systems over the past 40 years of research. Based on this, I will describe a set of empirically-grounded, human user-centered design principles that may guide developers to create successful explainable systems.

Michigan Tech’s BS in Software Engineering is in the top 10 nationwide according to College Rank. The website ranked the 35 Best Bachelor’s in Software Engineering.

Michigan Tech, which appears at number nine on the list, was one of only two Michigan colleges to make the ranking. The University of Michigan – Dearborn was ranked 15th.

“It’s great to see our program get this well-deserved recognition,” says Professor and Chair Linda Ott, Computer Science. “We consistently hear from industries that hire our graduates that our alumni are well-prepared and quickly become productive developers in their organizations.”

“Our students gain a solid theoretical framework, which provides the foundation for life-long career growth and success, as well as extensive practical, hands-on experience through class projects, internships and the Michigan Tech Enterprise program,” Ott explains.

College Rank uses a ranking methodology based on three aspects — Potential Salary After Graduation (40%), Individual Program Accreditation (30%) and Overall Affordability (30%).

“This program will help you to secure your position in a well-regarded profession,” says the College Rank website about Michigan Tech’s Software Engineering program. “You’ll be able to work with teams in your classes as well as labs and in the Senior Enterprise or Design programs. The Enterprise Program is a unique opportunity that brings together students of all majors to work on real projects with real clients in a business-like environment. You’ll receive guidance and coaching from faculty mentors throughout every step of your journey here.”

Two College of Computing RedTeam students are part of a five-member team that finished 3rd in last weekend’s invitation-only Lockheed Martin Advanced Technologies Laboratories (ATL) Capture the Flag cybersecurity competition.

The multi-day virtual event involved 200 students on 40 teams. It opened for answer submission Friday, January 8, at 8:00 p.m., and closed Sunday, January 10, at 8 p.m.

The 3rd Place team, GoBlue!, trailed the 2nd Place team by only 14 points. RedTeam members are Michigan Tech undergraduates Dakoda Patterson, Computer Science, and Trevor Hornsby, Cybersecurity, and three University of Michigan students from the RedTeam’s partnership with that institution.

Michigan Tech RedTeam faculty advisors are Professor Yu Cai, Applied Computing, and Assistant Professor Bo Chen, Computer Science.

“We were lucky to be one of the 40 teams invited,” said Cai. “This was no small task, as the CTF included a large number of points in Reversing and “pwning” challenges, which proved to be fairly difficult. Other challenges were Cryptography, Stegonography, Web Exploitation, and miscellaneous challenges.”

CTF competitions place hidden “flags” in various computer systems, programs, images, messages, network traffic and other computing environments. Each individual or team is tasked with finding these flags. Participants win prizes while learning how to defend against cybersecurity attacks in a competitive and safe arena.

Top Three Teams

Assistant Professor Lan “Emily” Zhang, Electrical and Computer Engineering, will present her lecture, “Augmenting Radio Environments for Better Wireless Ecosystems,” on Friday, January 15, 2021, at 3:00 p.m., via online meeting.

The lecture is hosted by the Michigan Tech Department of Computer Science. Zhang is a member of the Cyber-Physical Systems (CPS) research group of the Institute of Computing and Cybersystems (ICC).

Zhang’s research interest span the fields of cyber-physical systems, distributed machine learning, wireless communications, and cybersecurity. In her talk, she will discuss a series of studies leveraging smart-surfaces, e.g., meta-surfaces or reconfigurable intelligent surfaces (RISs), to augment radio environments for various purposes.

Join the Zoom lecture here. (https://michigantech.zoom.us/j/83259089532)

Lecture Abstract

In the last several decades, wireless technologies have become well-established to fight against propagation obstacles. Most conventional efforts are focused on optimizing end devices, such as transmitters and receivers, in order to adapt to the given transmission environment for better communications. However, the recent rapid convergence of the cyber and physical worlds (Cyber-Physical Systems or CPSs) presents unprecedented challenges to the wisdom of conventional design. Given ever-growing service demands, as well as the diverse wireless application scenarios, it is critical to adaptively augment the radio environments in a cost-effective way, while maintaining the aesthetic nature of living environments.

In her talk, Zhang will discuss a series of studies leveraging smart-surfaces–e.g., meta-surfaces or reconfigurable intelligent surfaces (RISs)–to augment radio environments for various purposes. Specifically, she will focus on three promising areas for enhancing the throughput and reliability of wireless communications, mitigating the physical-layer security threats, and facilitating wireless sensing activities. Both model-based and learning-based methods will be used for theoretical and practical analysis.

Biography

Dr. Lan Zhang is an assistant professor in the Department of Electrical and Computer Engineering at Michigan Tech. She received a Ph.D. degree in computer engineering from the University of Florida in 2020, and M.S. and B.Eng. degrees in telecommunication engineering from the University of Electronic Science and Technology of China in 2016 and 2013, respectively.

Zhang has served as a technical program committee member for several respected conferences, such as NeurIPS-SpicyFL 2020 and the 2020 IEEE IFOCOM poster/demo section. She has also served as reviewer for leading journals, such as IEEE Transactions on Communications, IEEE Transactions on Vehicular Technology, IEEE Transactions on Mobile Computing, and IEEE Transactions on Wireless Computing.

Computer Science graduate student Taylor Morris will present a Master’s Defense on Tuesday, January 5, from 6:00 to 7:00 p.m.

Presentation Title: “Using Text Mining and Machine Learning Classifiers to Analyze Stack Overflow.”

Advisor: Associate Professor Laura Brown, Computer Science

Link to the Michigan Tech Events Calendar entry here.

Join the Zoom meeting here. (michigantech.zoom.us/j/83033288850)

You are invited to spend one-zero-one-zero—that is, ten—minutes with Dr. Nathir Rawashdeh on Wednesday, December 16, from 5:30 to 5:40 p.m.

Rawashdeh is assistant professor of applied computing in the College of Computing at Michigan Tech.

He will present his current research work, including the using artificial intelligence for autonomous driving on snow covered roads, and a mobile robot using ultraviolet light to disinfect indoor spaces. Following, Rawashdeh will field listener questions.

We look forward to spending 1010 minutes with you!

Join 1010 with Nathir Rawashdeh here.

Did you miss last week’s 1010 with Chuck Wallace? Watch the video below.

Play – 1010 with … Chuck Wallace, Assoc. Prof, Computer Science, December 9, 2020.

The 1010 with … series will continue on Wednesday afternoons in the new year on January 6, 13, 20, and 27 … with more to come!

Graduate student Siva Krishna Kakula, Computer Science, will present his PhD defense, “Explainable Feature- and Decision-Level Fusion,” on Monday, December 21, 2020, from 3:00 to 5:00 p.m. EST Kakula is advised by Dr. Timothy Havens, College of Computing.

Link to the virtual lecture here.

Siva Kakula earned his master of science in computer engineering at Michigan Tech in 2014, and completed a bachelor of technology in civil engineering at IIT Guwahati in 2011. His research interests include machine learning, pattern recognition, and information fusion.

Download the informational flier below.

Download

Lecture Abstract

Information fusion is the process of aggregating knowledge from multiple data sources to produce more consistent, accurate, and useful information than any one individual source can provide. In general, there are three primary sources of data/information: humans, algorithms, and sensors. Typically, objective data—e.g., measurements—arise from sensors. Using these data sources, applications such as computer vision and remote sensing have long been applying fusion at different “levels” (signal, feature, decision, etc.). Furthermore, the daily advancement in engineering technologies like smart cars, which operate in complex and dynamic environments using multiple sensors, are raising both the demand for and complexity of fusion. There is a great need to discover new theories to combine and analyze heterogeneous data arising from one or more sources.

The work collected in this dissertation addresses the problem of feature- and decision-level fusion. Specifically, this work focuses on Fuzzy Choquet Integral (ChI)-based data fusion methods. Most mathematical approaches for data fusion have focused on combining inputs relative to the assumption of independence between them. However, often there are rich interactions (e.g., correlations) between inputs that should be exploited. The ChI is a powerful aggregation tool that is capable modeling these interactions. Consider the fusion of N sources, where there are 2^N unique subsets (interactions); the ChI is capable of learning the worth of each of these possible source subsets. However, the complexity of fuzzy integral-based methods grows quickly, as the fusion of N sources requires training 2^N-2 parameters; hence, we require a large amount of training data to avoid the problem of over-fitting. This work addresses the over-fitting problem of ChI-based data fusion with novel regularization strategies. These regularization strategies alleviate the issue of over-fitting while training with limited data and also enable the user to consciously push the learned methods to take a predefined, or perhaps known, structure. Also, the existing methods for training the ChI for decision- and feature-level data fusion involve quadratic programming (QP)-based learning approaches that are exorbitant with their space complexity. This has limited the practical application of ChI-based data fusion methods to six or fewer input sources. This work introduces an online training algorithm for learning ChI. The online method is an iterative gradient descent approach that processes one observation at a time, enabling the applicability of ChI-based data fusion on higher dimensional data sets.

In many real-world data fusion applications, it is imperative to have an explanation or interpretation. This may include providing information on what was learned, what is the worth of individual sources, why a decision was reached, what evidence process(es) were used, and what confidence does the system have on its decision. However, most existing machine learning solutions for data fusion are “black boxes,” e.g., deep learning. In this work, we designed methods and metrics that help with answering these questions of interpretation, and we also developed visualization methods that help users better understand the machine learning solution and its behavior for different instances of data.

We are looking forward to celebrating the accomplishments of our graduates at a Class of 2020 virtual Convocation program on Friday, December 18, 2020, at 3:30 p.m. EST.

Join the virtual event here.

The celebration will include special well-wishes from CC faculty and staff, and many will be sporting their graduation regalia. It is our privilege to welcome Ms. Dianne Marsh, 86, ’92, as our Convocation speaker. Dianne is Director of Device and Content Security for Netflix, and a member of the new College of Computing External Advisory Board.

We may be spread across the country and world this December, but we can still celebrate with some style. We look forward to sharing our best wishes with the Class of 2020 and wishing them continued success as they embark on the next phase of their lives!

This December, 40 students are expected to graduate with College of Computing degrees, joining 92 additional Class of 2020 PhD, MS, and BS alumni.

Dianne Marsh ’86, ’92 is Director of Device and Content Security for Netflix. Her team is responsible for securing the Netflix streaming client ecosystem and advancing the platform security of Netflix-enabled devices. Dianne has a BS (’86) and MS (’92) in Computer Science from Michigan Tech.

Visit the Class of 2020 Webpage

Congratulations Graduates. We’re proud of you.

You are invited to spend one-zero-one-zero—that is, 10 minutes—with Dr. Charles Wallace on Wednesday, December 9, from 5:30 to 5:40 p.m.

Wallace is associate dean for curriculum and instruction and associate professor of computer science in the College of Computing at Michigan Tech. Wallace is a researcher with the ICC’s Human-Centered Computing and Computing Education research groups.

In his informal discussion, Dr. Wallace will talk about computing at Michigan Tech, his research on how humans can better understand, build, and use software, and answer your questions.

We look forward to spending 1010 minutes with you!

Join 1010 with Chuck Wallace here.

Next week, on Wednesday, December 15, at 5:30 p.m., Assistant Professor Dr. Nathir Rawashdeh, Applied Computing, will present his current research work, including his use of artificial intelligence for autonomous driving on snow covered roads, and a mobile robot using ultraviolet light to disinfect indoor spaces.

Did you miss 1010 with Chuck Wallace on December 9? Watch the video below.

Play – 1010 with … Chuck Wallace, Assoc. Prof, Computer Science, December 9, 2020.