Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
Greenplum
Annotated Deep Learning Paper Implementations
提交
591bfc37
A
Annotated Deep Learning Paper Implementations
项目概览
Greenplum
/
Annotated Deep Learning Paper Implementations
11 个月 前同步成功
通知
6
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
DevOps
流水线
流水线任务
计划
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
A
Annotated Deep Learning Paper Implementations
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
DevOps
DevOps
流水线
流水线任务
计划
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
流水线任务
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
591bfc37
编写于
5月 07, 2021
作者:
V
Varuna Jayasiri
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
typosg
上级
cb6f63f2
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
4 addition
and
4 deletion
+4
-4
docs/gan/wasserstein/index.html
docs/gan/wasserstein/index.html
+2
-2
labml_nn/gan/wasserstein/__init__.py
labml_nn/gan/wasserstein/__init__.py
+2
-2
未找到文件。
docs/gan/wasserstein/index.html
浏览文件 @
591bfc37
...
...
@@ -92,8 +92,8 @@ marginal probabilities are $\gamma(x, y)$.</p>
a given joint distribution ($x$ and $y$ are probabilities).
</p>
<p>
So $W(\mathbb{P}_r, \mathbb{P}g)$ is equal to the least earth mover distance for
any joint distribution between the real distribution $\mathbb{P}_r$ and generated distribution $\mathbb{P}_g$.
</p>
<p>
The paper shows that Jensen-Shannon (JS) divergence and other measures for difference between two probability
distributions are not smooth. And therefore if we are doing
a
gradient descent on one of the probability
<p>
The paper shows that Jensen-Shannon (JS) divergence and other measures for
the
difference between two probability
distributions are not smooth. And therefore if we are doing gradient descent on one of the probability
distributions (parameterized) it will not converge.
</p>
<p>
Based on Kantorovich-Rubinstein duality,
<script
type=
"math/tex; mode=display"
>
...
...
labml_nn/gan/wasserstein/__init__.py
浏览文件 @
591bfc37
...
...
@@ -29,8 +29,8 @@ a given joint distribution ($x$ and $y$ are probabilities).
So $W(\mathbb{P}_r, \mathbb{P}g)$ is equal to the least earth mover distance for
any joint distribution between the real distribution $\mathbb{P}_r$ and generated distribution $\mathbb{P}_g$.
The paper shows that Jensen-Shannon (JS) divergence and other measures for difference between two probability
distributions are not smooth. And therefore if we are doing
a
gradient descent on one of the probability
The paper shows that Jensen-Shannon (JS) divergence and other measures for
the
difference between two probability
distributions are not smooth. And therefore if we are doing gradient descent on one of the probability
distributions (parameterized) it will not converge.
Based on Kantorovich-Rubinstein duality,
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录