Comments (1)
Iris is a very tiny data set, some 150 examples. It's not really intended as a proper example of good performance, more of a "here's what a network configuration and evaluation looks like"
At any rate, the seed impacts weight initialization, and consequently during learning the network may end up in a different local minima.
To get better performance, of course it would be possible to tune the network (i.e., find better settings of hyperparameters). However without splitting the data into train and test sets, this wouldn't actually tell us much (it's very easy to overfit on such a small data set).
from deeplearning4j-examples.
Related Issues (20)
- Fix links to examples in documentation HOT 1
- 'NoAvailableBackendException' occur when running project on the android studio emulator HOT 1
- Android Example fails due to MainActivity's ClassNotFoundException HOT 3
- Hyperparameter tuning example missing HOT 3
- IndexOutOfBoundsException when importing onnx model
- DL4J uses SharedTrainingMaster on spark and reports "ERROR - publicationUnblockTimeoutNs=15000000000 <= clientLivenessTimeoutNs=30000000000" HOT 6
- Make a Moudle compiler HOT 1
- YOLO HOT 1
- Issue executing GenerateTxtCharCompGraphModel.java HOT 6
- dl4j-examples - clean build failure HOT 1
- load keras saved .pb file model throw exception HOT 1
- UnsupportedClassVersionError HOT 1
- Potential Cuda issue with 4070 cards HOT 4
- org.nd4j:nd4j-cuda-10.2-platform:jar:1.0.0-M2.1 was not found in https://repo.maven.apache.org/maven2 during a previous attempt.
- The provided RNNEmbedding Example does not work, on 1.0.0-M2.1 release HOT 1
- Downloading training data results in 403 HOT 10
- RNNEmbedding IllegalStateException
- NaNs during training when running the TinyYoloHouseNumberDetection example
- rl4j-examples project folder is missing HOT 4
- Request for Scala Tutorials and Jupyter Notebook Formats 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 deeplearning4j-examples.