Results 71 to 80 of about 85,077 (292)

End-to-End Learning of Decision Trees and Forests [PDF]

International Journal of Computer Vision, 2019
Abstract Conventional decision trees have a number of favorable properties, including a small computational footprint, interpretability, and the ability to learn from little training data. However, they lack a key quality that has helped fuel the deep learning revolution: that of being end-to-end trainable. Kontschieder et al.
Thomas M. Hehn, Julian F. P. Kooij, Fred A. Hamprecht   +2 more
openaire   +3 more sources

Multi‐Pathway Upconversion Emission in Symmetry‐Broken Nanocavities: Broadband Multiresonant Enhancement and Anti‐Correlated Interfacial Sensitivity

Advanced Functional Materials, EarlyView.
Symmetry‐broken plasmonic nanoantenna arrays achieve broadband multiresonant enhancement of second harmonic generation (SHG), third harmonic generation (THG), and upconversion photoluminescence (UCPL), under femtosecond laser excitation across the near‐infrared range (1000–1600 nm).
Elieser Mejia, Yuming Zhao, Meitong Nie, Benjamin Pittelkau, Aditya Garg, Junyeob Song, Wenqi Zhu, Henri Lezec, Amit Agrawal, Wei Zhou   +9 more
wiley   +1 more source

Active Learning‐Driven Discovery of Sub‐2 Nm High‐Entropy Nanocatalysts for Alkaline Water Splitting

Advanced Functional Materials, EarlyView.
High‐entropy nanoparticles (HENPs) hold great promise for electrocatalysis, yet optimizing their compositions remains challenging. This study employs active learning and Bayesian Optimization to accelerate the discovery of octonary HENPs for hydrogen and oxygen evolution reactions.
Sakthivel Perumal, Da Bean Han, Thandapani Marimuthu, Taewaen Lim, Hyun Woo Kim, Junhyeok Seo   +5 more
wiley   +1 more source

High‐Entropy Magnetism of Murunskite

Advanced Functional Materials, EarlyView.
The study of murunskite (K2FeCu3S4) reveals that its magnetic and orbital order emerges in a simple I4/mmm crystal structure with complete disorder in the transition metal positions. Mixed‐valence Fe ions randomly occupy 1/4 of the tetrahedral sites, with the remaining 3/4 being filled by non‐magnetic Cu+ ions.
Davor Tolj, Priyanka Reddy, Ivica Živković, Luka Akšamović, Jian Rui Soh, Kamila Komȩdera, Izabela Biało, Naveen Kumar Chogondahalli Muniraju, Trpimir Ivšić, Mario Novak, Oksana Zaharko, Clemens Ritter, Thomas LaGrange, Wojciech Tabiś, Ivo Batistić, László Forró, Henrik M. Rønnow, Denis K. Sunko, Neven Barišić   +18 more
wiley   +1 more source

PAC-learning a decision tree with pruning

European Journal of Operational Research, 1996
Abstract Empirical studies have shown that the performance of decision tree induction usually improves when the trees are pruned. Whether these results hold in general and to what extent pruning improves the accuracy of a concept have not been investigated theoretically. This paper provides a theoretical study of pruning.
Department of Management Information Systems, College of Economics and Business Administration, Kookmin University Chongnung-dong Sungbuk-gu, Seoul South Korea ( host institution ), Kim, Hyunsoo, Koehler, Gary J.   +2 more
openaire   +3 more sources

Flow‐Induced Vascular Remodeling on‐Chip: Implications for Anti‐VEGF Therapy

Advanced Functional Materials, EarlyView.
Flow‐induced vascular remodeling plays a critical role in network stabilization and function. Using a vasculature‐on‐chip system, this study reveals how physiological VEGF levels and flow affect vascular remodeling and provides insights into tumor vessel normalization.
Fatemeh Mirzapour‐Shafiyi, Elias Huber, Leonie Karr, Johnny Tong, Andreas Richard Bausch, Friedrich Christian Simmel, Karen Alim   +6 more
wiley   +1 more source

Learning Decision Trees for Unbalanced Data [PDF]

, 2008
Learning from unbalanced datasets presents a convoluted problem in which traditional learning algorithms may perform poorly. The objective functions used for learning the classifiers typically tend to favor the larger, less important classes in such problems.
David A. Cieslak, Nitesh V. Chawla
openaire   +2 more sources

Learning Optimal Dynamic Treatment Regime from Observational Clinical Data through Reinforcement Learning

Machine Learning and Knowledge Extraction
In medicine, dynamic treatment regimes (DTRs) have emerged to guide personalized treatment decisions for patients, accounting for their unique characteristics. However, existing methods for determining optimal DTRs face limitations, often due to reliance
Seyum Abebe, Irene Poli, Roger D. Jones, Debora Slanzi   +3 more
doaj   +1 more source

XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury

Neurotrauma Reports, 2020
The accurate prediction of neurological outcomes in patients with cervical spinal cord injury (SCI) is difficult because of heterogeneity in patient characteristics, treatment strategies, and radiographic findings.
Tomoo Inoue, Daisuke Ichikawa, Taro Ueno, Maxwell Cheong, Takashi Inoue, William D. Whetstone, Toshiki Endo, Kuniyasu Nizuma, Teiji Tominaga   +8 more
doaj   +1 more source

Predicting Aggregation Behavior of Nanoparticles in Liquid Crystals via Automated Data‐Driven Workflows

Advanced Functional Materials, EarlyView.
Herein, a comprehensive framework that enabled the optimization of colloidal solubility within a high‐dimensional parameter space and study of reversible assembly processes is developed. This data‐driven workflow integrated innovations including the robotic platform for automated AuNPs functionalization, machine learning for predicting and revealing ...
Yueyang Gao, Niamh Mac Fhionnlaoich, Max Besenhard, Arun Pankajakshan, Federico Galvanin, Stefan Guldin   +5 more
wiley   +1 more source