Comments (3)
你好,感谢对我们工作的关注,以下是具体的解答,希望对你有帮助:
(1)left和right参数主要用于之前对可训练的BinarizeLayer的尝试,但后来使用了固定bound的BinarizeLayer,所以你可以忽略left和right参数,直接默认保持None即可。
(2)由于我们用0和1分别表示False和True,所以1-x即为~x,也即NOT x。
(3)这其实就是论文中所说的skip connection。skip connection主要是为了自动跳过不必要的层,从而使层数较多的模型更容易收敛、学到的规则更简单。
(4)是的,estimated_grad这个选项就是对应了我们论文中所讲的这个trick。
(5)是的,这个导数可以通过手动计算交叉熵损失函数的导数得来(因为RRL用了交叉熵损失函数,如果用其他的损失函数,需要手动计算对应导数)。
(6)这主要是由于采用了梯度嫁接法(Gradient Grafting,详见论文),梯度嫁接法优化的loss是离散模型的loss,而连续模型主要用于为离散模型衡量边权的变化对节点值的影响大小。
from rrl.
感谢大佬的回复,基本清楚了,另外:interpretable是否就是体现在整个预测过程是透明的,比如有新样本来了被预测为class_x,我们可以找到该新样本所激活的那些解释规则集。
from rrl.
嗯嗯,是的。普遍认为离散的规则模型由于其形式上的优势,其可解释性要优于神经网络一类的模型。另外RRL还可以控制模型的复杂度,因此可以进一步确保可解释性
from rrl.
Related Issues (14)
- Can RRL be used for regression? HOT 2
- 请教一个关于运行效率的问题。 HOT 2
- 您好,我有一个初级的问题想要请教一些您,希望可以得到回复 HOT 2
- 您好,想咨询您关于更新版本的一个问题,希望得到回复 HOT 4
- 请教比较初级的实验结果的问题 HOT 3
- Cannot run it on windows HOT 5
- How to calculate the weights of the rule and class? HOT 2
- it must be working on cuda or not. HOT 1
- 请教一下一个初级的问题 HOT 3
- 您好,请教关于实验复现的问题 HOT 4
- 参数问题 HOT 6
- 你好!请问能提供一下预处理好的.data和.info文件吗? HOT 1
- 您好!请问文中的fashion的class数量是不是写错了?应该是10类而不是4类吧 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rrl.