Machine Learning Model
Machine learning models aim to create systems that can learn from data and make predictions or decisions without explicit programming. Current research emphasizes improving model accuracy, interpretability, and robustness, focusing on architectures like deep neural networks, decision tree ensembles, and transformer models, as well as exploring decentralized learning and techniques for mitigating biases and vulnerabilities. These advancements are crucial for diverse applications, ranging from optimizing resource management (e.g., smart irrigation) to improving healthcare diagnostics and enhancing the security and trustworthiness of AI systems.
Papers
Systematic Training and Testing for Machine Learning Using Combinatorial Interaction Testing
Tyler Cody, Erin Lanus, Daniel D. Doyle, Laura Freeman
Developing a Machine-Learning Algorithm to Diagnose Age-Related Macular Degeneration
Ananya Dua, Pham Hung Minh, Sajid Fahmid, Shikhar Gupta, Sophia Zheng, Vanessa Moyo, Yanran Elisa Xue
Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning
Jie Zhang, Lei Zhang, Gang Li, Chao Wu
FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients
Jianyu Wang, Hang Qi, Ankit Singh Rawat, Sashank Reddi, Sagar Waghmare, Felix X. Yu, Gauri Joshi
Using Shape Metrics to Describe 2D Data Points
William Franz Lamberti
Prediction of GPU Failures Under Deep Learning Workloads
Heting Liu, Zhichao Li, Cheng Tan, Rongqiu Yang, Guohong Cao, Zherui Liu, Chuanxiong Guo
A Systematic Study of Bias Amplification
Melissa Hall, Laurens van der Maaten, Laura Gustafson, Maxwell Jones, Aaron Adcock
A Method for Controlling Extrapolation when Visualizing and Optimizing the Prediction Profiles of Statistical and Machine Learning Models
Jeremy Ash, Laura Lancaster, Chris Gotwalt
The Fairness Field Guide: Perspectives from Social and Formal Sciences
Alycia N. Carey, Xintao Wu
Certifiable Robustness for Nearest Neighbor Classifiers
Austen Z. Fan, Paraschos Koutris
Blackbox Post-Processing for Multiclass Fairness
Preston Putzel, Scott Lee
Intra-domain and cross-domain transfer learning for time series data -- How transferable are the features?
Erik Otović, Marko Njirjak, Dario Jozinović, Goran Mauša, Alberto Michelini, Ivan Štajduhar
Predicting Terrorist Attacks in the United States using Localized News Data
Steven J. Krieg, Christian W. Smith, Rusha Chatterjee, Nitesh V. Chawla