Machine Learning
Machine learning (ML) focuses on developing algorithms that allow computers to learn from data without explicit programming, aiming to improve prediction accuracy, automate tasks, and extract insights. Current research emphasizes areas like fairness in federated learning, efficient model training and deployment (including techniques to reduce communication overhead), and enhancing model interpretability and robustness against adversarial attacks. ML's impact spans diverse fields, from healthcare (e.g., disease prediction) and industrial quality control to astrophysics (e.g., galaxy classification) and cybersecurity, demonstrating its broad applicability and significant potential for scientific advancement and practical problem-solving.
Papers
Challenges, Methods, Data -- a Survey of Machine Learning in Water Distribution Networks
Valerie Vaquet, Fabian Hinder, André Artelt, Inaam Ashraf, Janine Strotherm, Jonas Vaquet, Johannes Brinkrolf, Barbara Hammer
Approaching Metaheuristic Deep Learning Combos for Automated Data Mining
Gustavo Assunção, Paulo Menezes
Advancing Healthcare: Innovative ML Approaches for Improved Medical Imaging in Data-Constrained Environments
Al Amin, Kamrul Hasan, Saleh Zein-Sabatto, Liang Hong, Sachin Shetty, Imtiaz Ahmed, Tariqul Islam
MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from μWatts to MWatts for Sustainable AI
Arya Tschand (1), Arun Tejusve Raghunath Rajan (2), Sachin Idgunji (3), Anirban Ghosh (3), Jeremy Holleman (4), Csaba Kiraly (5), Pawan Ambalkar (6), Ritika Borkar (3), Ramesh Chukka (7), Trevor Cockrell (6), Oliver Curtis (8), Grigori Fursin (9), Miro Hodak (10), Hiwot Kassa (11), Anton Lokhmotov (12), Dejan Miskovic (3), Yuechao Pan (13), Manu Prasad Manmathan (7), Liz Raymond (6), Tom St. John (14), Arjun Suresh (15), Rowan Taubitz (8), Sean Zhan (8), Scott Wasson (16), David Kanter (16), Vijay Janapa Reddi (1) ((1) Harvard University, (2) Self / Meta, (3) NVIDIA, (4) UNC Charlotte / Syntiant, (5) Codex, (6) Dell, (7) Intel, (8) SMC, (9) FlexAI / cTuning, (10) AMD, (11) Meta, (12) KRAI, (13) Google, (14) Decompute, (15) GATE Overflow, (16) MLCommons)
Encoding architecture algebra
Stephane Bersier, Xinyi Chen-Lin
Machine Learning via rough mereology
Lech T. Polkowski
LoKO: Low-Rank Kalman Optimizer for Online Fine-Tuning of Large Models
Hossein Abdi, Mingfei Sun, Andi Zhang, Samuel Kaski, Wei Pan
DDMD: AI-Powered Digital Drug Music Detector
Mohamed Gharzouli
TSDS: Data Selection for Task-Specific Model Finetuning
Zifan Liu, Amin Karbasi, Theodoros Rekatsinas
Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples
Thomas T. Zhang, Bruce D. Lee, Ingvar Ziemann, George J. Pappas, Nikolai Matni
An Explainable AI Model for Predicting the Recurrence of Differentiated Thyroid Cancer
Mohammad Al-Sayed Ahmad, Jude Haddad
Physics-informed AI and ML-based sparse system identification algorithm for discovery of PDE's representing nonlinear dynamic systems
Ashish Pal, Sutanu Bhowmick, Satish Nagarajaiah
Enhancing Peer Review in Astronomy: A Machine Learning and Optimization Approach to Reviewer Assignments for ALMA
John M. Carpenter, Andrea Corvillón, Nihar B. Shah
How to unlearn a learned Machine Learning model ?
Seifeddine Achour
Learning from the past: predicting critical transitions with machine learning trained on surrogates of historical data
Zhiqin Ma, Chunhua Zeng, Yi-Cheng Zhang, Thomas M. Bury
Mastering AI: Big Data, Deep Learning, and the Evolution of Large Language Models -- AutoML from Basics to State-of-the-Art Techniques
Pohsun Feng, Ziqian Bi, Yizhu Wen, Benji Peng, Junyu Liu, Caitlyn Heqi Yin, Tianyang Wang, Keyu Chen, Sen Zhang, Ming Li, Jiawei Xu, Ming Liu, Xuanhe Pan, Jinlang Wang, Qian Niu
From Theory to Practice: Implementing and Evaluating e-Fold Cross-Validation
Christopher Mahlich, Tobias Vente, Joeran Beel