Comments (3)
Yes,I try some other models, and some of them reach -0.16 of loss too, but soon get over fitting. Then I add a dropout layer to input layer, and then to hidden layer. Maybe I add too much. I will try remove first dropout layer. Thank you very much. You question means much.
from deeptrade_keras.
I am glad the question helps. To be more specific: the reason why it is not recommended to do dropout on Input layer is that we don't want to lose data; the reason why to apply dropout on hidden layer is to reduce overfitting while not losing data.
from deeptrade_keras.
It helps me a lot. I will do more experiments without input dropout layer. Thank you very much.
from deeptrade_keras.
Related Issues (20)
- some data files are missing? HOT 2
- Ultimate feature and label file HOT 1
- Adapting this for FOREX on 1 Hour Timeframe HOT 8
- Low accuracy HOT 1
- Some questions HOT 1
- which you use keras version? HOT 1
- Could you provide the website code?
- relu_limited and risk_estimation definition HOT 1
- negative loss
- 关于数据的组成的问题
- How to plot 2 images for the loss and accuracy?
- 特征不会用到未来数据吗? HOT 3
- 特征穿越
- add validation set HOT 1
- the best model trained so far? HOT 17
- something wield on visualization site HOT 1
- Design of model skeleton and feature selection? HOT 1
- 关于预测值的处理(why relu_limited not sigmoid?)
- What does value of pred represent? HOT 2
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 deeptrade_keras.