From post

копировать удалить добавить публикацию в буфер
Запись сообщества
посмотреть историю данной записи
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks.

L. Xiao, Y. Bahri, J. Sohl-Dickstein, S. Schoenholz, и J. Pennington. ICML, том 80 из Proceedings of Machine Learning Research, стр. 5389-5398. PMLR, (2018)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed.

Fang Xiao

Wenjiang Xiao

Chun Xiao

Meifang Xiao

Jianping Xiao

Другие публикации лиц с тем же именем

Neural Tangents: Fast and Easy Infinite Neural Networks in Python.R. Novak, L. Xiao, J. Hron, J. Lee, A. Alemi, J. Sohl-Dickstein, и S. Schoenholz. ICLR, OpenReview.net, (2020)Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models.A. Singh, J. Co-Reyes, R. Agarwal, A. Anand, P. Patil, X. Garcia, P. Liu, J. Harrison, J. Lee, K. Xu и 31 other автор(ы). Trans. Mach. Learn. Res., (2024)Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability.J. Hron, L. Culp, G. Elsayed, R. Liu, B. Adlam, M. Bileschi, B. Bohnet, J. Co-Reyes, N. Fiedel, C. Freeman и 21 other автор(ы). CoRR, (2024)Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression.L. Xiao, H. Hu, T. Misiakiewicz, Y. Lu, и J. Pennington. NeurIPS, (2022)Disentangling Trainability and Generalization in Deep Neural Networks.L. Xiao, J. Pennington, и S. Schoenholz. ICML, том 119 из Proceedings of Machine Learning Research, стр. 10462-10472. PMLR, (2020)The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks.W. Hu, L. Xiao, B. Adlam, и J. Pennington. NeurIPS, (2020)Finite Versus Infinite Neural Networks: an Empirical Study.J. Lee, S. Schoenholz, J. Pennington, B. Adlam, L. Xiao, R. Novak, и J. Sohl-Dickstein. NeurIPS, (2020)Small-scale proxies for large-scale Transformer training instabilities.M. Wortsman, P. Liu, L. Xiao, K. Everett, A. Alemi, B. Adlam, J. Co-Reyes, I. Gur, A. Kumar, R. Novak и 6 other автор(ы). ICLR, OpenReview.net, (2024)Bayesian Deep Convolutional Networks with Many Channels are Gaussian ProcessesR. Novak, L. Xiao, J. Lee, Y. Bahri, G. Yang, J. Hron, D. Abolafia, J. Pennington, и J. Sohl-Dickstein. (2018)cite arxiv:1810.05148Comment: Published as a conference paper at ICLR 2019.Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?C. Freeman, L. Culp, A. Parisi, M. Bileschi, G. Elsayed, A. Rizkowsky, I. Simpson, A. Alemi, A. Nova, B. Adlam и 20 other автор(ы). CoRR, (2023)

BibSonomy

Disambiguation