Talks, Conferences, and Workshops

2022

• 11/04/2022, presented "Towards understanding underlying principles of Deep Learning" at the MIT Quest for Intelligence event (Cambridge, MA, US).
• 10/13/2022, presented "Dynamics in Deep Classifiers trained with the Square Loss: normalization, low rank, neural collapse, and generalization bounds" at the Center for Brain-Inspired Computing (C-BRIC) industry meeting (Purdue University, West Lafayette, IN, US).
• 09/28/2022, gave an oral presentation on "Dynamic graph representation learning with uncertainty quantification" in the SIAM Conference on Mathematics of Data Science(San Diego, CA, USA).
• 09/19/2022, presented “Stochastic dynamic graph representation learning” in the MIT 9.58 course (Fall 2022) (Instructor: Prof. Tomaso Poggio).
• 08/30/2022, gave an oral presentation on "A multi-graph Gaussian embedding method with uncertainty quantification for Alzheimer's disease progression prediction" in the 22nd BIOMAG Conference (University of Birmingham, Birmingham, UK).
• 04/25/2022, our recent work on the "Hyperbolic graph embedding of magnetoencephalography brain networks to study brain alterations in patients with subjective cognitive decline" was presented in the MIT MGB AI Cures Conference 2022 (Samberg Center, MIT).
• 03/14/2022, gave a webinar presentation on "Graph Embedding with Uncertainty Quantification for Diverse Applications" in the PhILMs: Physics-Informed Learning Machines Center at the Pacific Northwest National Laboratory.
• 02/22/2022, gave a talk on “Graph Representation Learning with Uncertainty Quantification” in the “AI + Math” Colloquia at the Institute of Natural Sciences, Shanghai Jiao Tong University.
• 02/02/2022, presented “Graph Embedding with Uncertainty Quantification for Diverse Applications” in the Institute for Data Science and Department of Data Science in the Ying Wu College of Computing at New Jersey Institute of Technology.

2021

• 09/20/2021, presented “Hyperbolic graph embedding for MEG brain network analysis with multiomics dataset” in the MIT 9.58 course (Fall 2021) (Instructor: Prof. Tomaso Poggio).
• 09/16/2021, attended the “Stanford Graph Learning Workshop 2021”. (Virtual)
• 04/20/2021 - 04/21/2021, attended the “TOPML 2021 Workshop on the Theory of Overparameterized Machine Learning”, our work “Dynamics and Neural Collapse in Deep Classifiers with the Square Loss” was presented by Prof. Tomaso Poggio. (Virtual)
• 02/13/2021, gave a plenary talk on “A new stochastic graph embedding method for Alzheimer’s disease early‐stage prediction and intervention evaluation” in the IEEE EMBS Grand Challenges Forum: Data Science and Engineering in Healthcare. (Virtual)
• 01/15/2021, presented “nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation” at the “Machine Learning +X” CRUNCH Seminar at Brown University. (Virtual)

2020

• 09/09/2020, presented “Learning graph embeddings for network analysis” in the MIT 9.58 course (Fall 2020) for the projects in Science of Intelligence. (Instructor: Prof. Tomaso Poggio)
• 07/31/2020, presented “Understanding deep neural network-based Graph Embedding Methods” at the Massachusetts General Hospital, Harvard Medical School. (Virtual)
• 07/28/2020, presented a poster on “A New Stochastic Graph Embedding Method for Alzheimer’s Disease Early-Stage Prediction and Intervention Evaluation” in the Alzheimer's Association International Conference (AAIC). (Virtual)
• 06/12/2020, presented “Overview of self-supervised learning” in MGH CAMCA group meeting at Harvard Medical School. (Virtual)
• 05/15/2020, presented "Automated data augmentation and their applications" at the “Machine Learning + X” CRUNCH Seminar at Brown University. (Virtual)
• 03/30/2020, presented the work “A deep learning-based graph embedding method for the analysis of brain networks” in Poggio Lab meeting at MIT. (Cambridge, MA, USA)
• 03/19/2020, presented the work “MEG brain network Gaussian embeddings for predicting Alzheimer’s disease progression” in the online OHBM EQUINOX TWITTER CONFERENCE. (Cambridge, MA, USA)
• 01/24/2020, presented the work “A deep learning-based graph gaussian embedding method for the analysis of brain networks” in the Computation in Mind and Brain Seminar Series of Carney Institute for Brain Science at Brown University.