July 01, 2017 conference-paper All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings DOI: 10.1109/cvpr.2017.539 OpenAlex Authors 0 Author list not loaded yet. Cited by 3 stored of 136 Search Sort Most cited Newest Oldest Patent citations Title Any typearticle review book-chapter conference-paper preprint dissertation book dataset other Any fieldAgricultural and Biological Sciences Arts and Humanities Biochemistry, Genetics and Molecular Biology Business, Management and Accounting Chemical Engineering Chemistry Computer Science Decision Sciences Dentistry Earth and Planetary Sciences Economics, Econometrics and Finance Energy Engineering Environmental Science Health Professions Immunology and Microbiology Materials Science Mathematics Medicine Neuroscience Nursing Pharmacology, Toxicology and Pharmaceutics Physics and Astronomy Psychology Social Sciences Veterinary Open access Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks 2021 arXiv (Cornell University) preprint Computer Science Advanced Neural Network Applications Open access 1 citations Norm Loss: An efficient yet effective regularization method for deep neural networks 2021 Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition conference-paper Computer Science Advanced Neural Network Applications 3 citations Ensemble Kalman Filter Optimizing Deep Neural Networks: An Alternative Approach to Non-performing Gradient Descent 2020 Lecture notes in computer science conference-paper Computer Science Stochastic Gradient Optimization Techniques 7 citations 3 results References 0