Skip to main content

Optimization for Fairness-aware Machine Learning

Ms. Yao Yao University of Iowa Thursday, February 8, 2024 11:00AM – 12:00PM TC 222 | Zoom Abstract Artificial intelligence (AI) and machine learning technologies have been used in high-stakes decision making systems such as lending decision, criminal justice sentencing and resource allocation. A new challenge arising with these AI systems is how to avoid…...
Read More

Graph Based Machine Learning: Enhancing Artificial Intelligence to Better Understand Relations of Concepts

Announcing the Final Examination of Sijie Zhu for the degree of Doctor of Philosophy in Computer Science...
Read More

Reconstructing 3D Humans From Visual Data

Announcing the Final Examination of Sijie Zhu for the degree of Doctor of Philosophy in Computer Science...
Read More

Towards Secure, Privacy-preserving and Fair Artificial Intelligence

Dr. Murat Kantarcioglu The University of Texas at Dallas Wednesday, September 6, 2023 10:00AM – 11:00AM HEC 101A | Zoom Abstract In the age of big data and Artificial Intelligence (AI), protecting the security and privacy of stored data is paramount for maintaining public trust, accountability and getting the full value from the collected data.…...
Read More

Towards Efficient Learning under Label Noise: From Dawid-Skene to Deep Neural Networks

Ms. Shahana Ibrahim Oregon State University Friday, June 30, 2023 2:00PM – 3:00PM CREOL 102/103 | Zoom Abstract With the rise of the AI revolution, there is an exceptionally high demand for data labeling. However, most data labeling is done through crowdsourcing techniques, where non-expert annotators often provide labels. This results in considerably noisy labels,…...
Read More

Towards Optimal and Adaptive Algorithms for Optimization in Games

Mr. Junchi Yang ETH Zurich Thursday, June 29, 2023 10:00AM – 11:00AM TC2 222 | Zoom Abstract Recent advancements in Artificial Intelligence (AI), such as AlphaZero and ChatGPT, have significantly impacted various fields. Reinforcement learning (RL) plays a crucial role in these achievements. However, deploying RL in real-world applications, including robotics, finance, and healthcare, presents…...
Read More

Deployable Reinforcement Learning: Addressing Real-World Challenges of Artificial Intelligence

Dr. Amrit Singh Bedi University of Maryland Monday, June 26, 2023 10:00AM – 11:00AM Research I 101 | Zoom Abstract Recent advancements in Artificial Intelligence (AI), such as AlphaZero and ChatGPT, have significantly impacted various fields. Reinforcement learning (RL) plays a crucial role in these achievements. However, deploying RL in real-world applications, including robotics, finance,…...
Read More

Advanced Machine Learning Techniques for Processing Complex Data

Dr. Dixon Vimalajeewa Texas A&M University Thursday, May 25, 2023 10:00AM – 11:00AM Technology Commons II 222 | Zoom Abstract The recent advancements in Internet of Things (IoT), Internet of Nano-Things (IoNT), and Information and Communication Technologies have made it possible to collect large amounts of data from previously inaccessible locations, such as the human…...
Read More

A Tale of Two Worlds: The Variational Approach to Machine Learning

Dr. Alexander Alemi Google Wednesday, May 24, 2023 10:00AM – 11:00AM Research I 101 | Zoom Abstract We are in the era of deep learning. The alchemy that is deep learning enables us to tractably search in the space of functions. Our challenge then is to provide meaningful objectives to guide that search. I will…...
Read More

Interactive Decision Making in Multi-agent Intelligent Systems

Mr. Chuanhao Li University of Virginia Monday, May 22, 2023 11:30AM – 11:30PM HEC 101B | Zoom Abstract Interactive decision making (e.g., bandit and reinforcement learning) is a promising paradigm for developing intelligent systems capable of efficiently exploring unknown environments. It has achieved remarkable success in recommender systems, clinical decision systems, robotics and cyber-physical systems,…...
Read More

Trustworthy and Explainable Artificial Intelligence

Dr. Anh Nguyen Auburn University Wednesday, May 17, 2023 11:00AM – 12:00PM HEC 101A | Zoom Abstract Artificial Intelligence (AI) is becoming ubiquitous and a key that enables humankind to reach unprecedented horizons (e.g. in protein folding). However, in high-stake applications (e.g. cancer diagnosis, automated target detection, or face identification), a single incorrect decision of…...
Read More

Enabling Urban Intelligence by Harnessing Human-Generated Spatial-Temporal Data

Ms. Xin Zhang Worcester Polytechnic Institute Tuesday, May 16, 2023 2:00PM – 3:00PM HEC 101A | Zoom Abstract Technology advancement in mobile sensing and communication has enabled a massive amount of mobility data to be generated from human decision-makers, which we call human-generated spatial-temporal data (HSTD). Applying the HSTD to extract the unique decision-making strategies…...
Read More

Robust Reinforcement Learning under Model Uncertainty

Mr. Yue Wang University at Buffalo Monday, May 15, 2023 10:00AM – 11:00AM HEC 101A | Zoom Abstract Reinforcement learning has achieved remarkable success in various applications, such as video games, the game of Go, and the development of ChatGPT. However, most traditional reinforcement learning methods suffer from performance degradation due to the gap between…...
Read More

Distance Metric Learning and its application in high dimensional data analysis

Dr. Maryam Bagherian Yale University Monday, May 8, 2023 10:30AM – 11:00AM MSB 318 Abstract Distance metric learning is an approach in high-dimensional analysis which facilitates the exploration of underlying structures among data points in an effective and efficient manner. By learning a suitable distance metric, distance-based algorithms can better capture the intrinsic structure of…...
Read More

Integrated AI Systems for Translational Biomedicine

Dr. Laura Brattain MIT Lincoln Laboratory Wednesday, May 3, 2023 3:30PM – 4:30PM COM 302 | Zoom Abstract With the rapid advances in artificial intelligence (AI), biomedical AI is poised to transform healthcare at scale. To spearhead the translation from bench to bedside, we need to go beyond standalone AI algorithms but instead endeavor to…...
Read More

Topological Graph Machine Learning

Dr. Cuneyt Akcora Manitoba University Tuesday, May 2, 2023 3:00PM – 4:00PM Zoom Abstract Recently, there has been an increasing interest among machine learning researchers in topological approaches. Topological Data Analysis (TDA) is an emerging field that combines algebraic topology, statistics, and computer science to analyze data sampled from a metric space and recover the…...
Read More

Peeling Back the Layers of Deep Neural Networks—A Venture from Implementation Perspective

Dr. Aritra Dutta University of Southern Denmark Monday, May 1, 2023 10:00AM – 11:00AM MSB 318 | Zoom Abstract When there is a lot of training data or the deep neural network is too large, distributed parallel training becomes essential, which refers to either data or model parallelism. In both cases, parallelism introduces various overheads.…...
Read More

Algorithmic and Field Robotics for Environmental Monitoring

Dr. Nare Karapetyan University of Maryland Tuesday, April 18, 2023 1:30PM – 2:30PM Zoom Abstract In the pursuit of understanding the world around us, significant efforts are dedicated to developing dependable autonomous systems capable of planning out exploration tasks. These tasks encompass a range of applications, such as scientific sampling, environmental monitoring, surveillance, and search…...
Read More

Embracing Change: Tackling In-the-Wild Shifts in Machine Learning

Dr. Huaxiu Yao Stanford University Thursday, April 13, 2023 10:00AM – 11:00AM Zoom Abstract The real-world deployment of machine learning algorithms often poses challenges due to shifts in data distributions and tasks. These shifts can lead to a degradation in model performance, as the model may not have seen such changes during training. It can…...
Read More

Advancing Data-Aspect AI: From Efficient Data Annotation to High-Quality Data Creation

Dr. Siyu Huang Harvard University Tuesday, April 11, 2023 11:30AM – 12:30PM Zoom Abstract The real-world deployment of machine learning algorithms often poses challenges due to shifts in data distributions and tasks. These shifts can lead to a degradation in model performance, as the model may not have seen such changes during training. It can…...
Read More