暂无分享,去创建一个
Hanlin Goh | Vimal Thilak | Joshua M. Susskind | Shuangfei Zhai | Etai Littwin | Omid Saremi | Greg Yang | J. Susskind | Shuangfei Zhai | Etai Littwin | Vimal Thilak | Hanlin Goh | O. Saremi | Greg Yang
[1] Tommi S. Jaakkola,et al. Steps Toward Deep Kernel Methods from Infinite Neural Networks , 2015, ArXiv.
[2] Laurence Aitchison. Why bigger is not always better: on finite and infinite neural networks , 2020, ICML.
[3] Theodore Papamarkou,et al. Wide Neural Networks with Bottlenecks are Deep Gaussian Processes , 2020, J. Mach. Learn. Res..
[4] Jaehoon Lee,et al. Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes , 2018, ICLR.
[5] Sanjeev Arora,et al. On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization , 2018, ICML.
[6] Ruosong Wang,et al. On Exact Computation with an Infinitely Wide Neural Net , 2019, NeurIPS.
[7] Lior Wolf,et al. On the Optimization Dynamics of Wide Hypernetworks , 2020, ArXiv.
[8] Greg Yang,et al. Tensor Programs II: Neural Tangent Kernel for Any Architecture , 2020, ArXiv.
[9] Etai Littwin,et al. Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics , 2021, ICML.
[10] Alex Krizhevsky,et al. Learning Multiple Layers of Features from Tiny Images , 2009 .
[11] Yoram Singer,et al. Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity , 2016, NIPS.
[12] Lawrence D. Jackel,et al. Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.
[13] Geoffrey E. Hinton,et al. Bayesian Learning for Neural Networks , 1995 .
[14] Greg Yang,et al. Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes , 2019, NeurIPS.
[15] 俊一 甘利. 5分で分かる!? 有名論文ナナメ読み:Jacot, Arthor, Gabriel, Franck and Hongler, Clement : Neural Tangent Kernel : Convergence and Generalization in Neural Networks , 2020 .
[16] Lior Wolf,et al. On random kernels of residual architectures , 2020, UAI.