239 citations
- Cornell UniversityUS6 papers
- Brookhaven National LaboratoryUS4 papers
- Rutgers, The State University of New JerseyUS4 papers
- United States Air Force Research LaboratoryUS4 papers
- University of WashingtonUS4 papers
- Lawrence Berkeley National LaboratoryUS3 papers
- Princeton UniversityUS3 papers
- University of California San DiegoUS3 papers
- University of Central FloridaUS3 papers
- University of OxfordGB3 papers
- University of VirginiaUS3 papers
- Apple (Israel)IL2 papers
14 papers · 1 filter
Fuzzy-UCS Revisited: Self-Adaptation of Rule Representations in Michigan-Style Learning Fuzzy-Classifier Systems
Hiroki Shiraishi, Yohei Hayamizu, Tomonori Hashiyama
This paper focuses on the impact of rule representation in Michigan-style Learning Fuzzy-Classifier Systems (LFCSs) on its classification performance. A well-representation of the…
Critical Learning Periods in Federated Learning
Gang Yan, Hao Wang, Jian Li
Federated learning (FL) is a popular technique to train machine learning (ML) models with decentralized data. Extensive works have studied the performance of the global model; howe…
Learning with Retrospection
Xiang Deng, Zhongfei Zhang
Deep neural networks have been successfully deployed in various domains of artificial intelligence, including computer vision and natural language processing. We observe that the c…
Collegial Ensembles
Etai Littwin, Ben Myara, Sima Sabah +3
Modern neural network performance typically improves as model size increases. A recent line of research on the Neural Tangent Kernel (NTK) of over-parameterized networks indicates…
RelEx: A Model-Agnostic Relational Model Explainer
Yue Zhang, David Defazio, Arti Ramesh
In recent years, considerable progress has been made on improving the interpretability of machine learning models. This is essential, as complex deep learning models with millions…
AutoEG: Automated Experience Grafting for Off-Policy Deep Reinforcement Learning
Keting Lu, Shiqi Zhang, Xiaoping Chen
Deep reinforcement learning (RL) algorithms frequently require prohibitive interaction experience to ensure the quality of learned policies. The limitation is partly because the ag…