[其他] 计算视觉Wide Feedforward or Recurrent Neural Networks of Any Architecture are G ... [推广有奖]

0关注
22粉丝

已卖：1969份资源

大师

21%

还不是VIP/贵宾

威望: 1 级
论坛币: 546 个
通用积分: 575.4231
学术水平: 66 点
热心指数: 130 点
信用等级: 37 点
经验: 114033 点
帖子: 6755
精华: 0
在线时间: 2956 小时
注册时间: 2022-8-18
最后登录: 2026-1-19

楼主

2023Hua

发表于 2025-8-11 10:47:50 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Tensor Programs I: Wide Feedforward or Recurrent
Neural Networks of Any Architecture are Gaussian
         Processes

                  Greg Yang
                  Microsoft Research AI
               gregyang@microsoft.com

                     Abstract
   Wide neural networks with random weights and biases are Gaussian processes,
   as observed by Neal (1995) for shallow networks, and more recently by Lee et
   al. (2018) and Matthews et al. (2018) for deep fully-connected ...