Comments (4)
I suspect that the training data is different in each file, ultimately that means that the network needs to change size.
from brain.js.
Differed only output. For example
- for file data1.json output for all inputs is {"id123": 1}
- for file data2.json output for all inputs is {"id124": 1}
etc.
So I need set size at initialization of nn?
from brain.js.
If you were to use brain.NeuralNetwork
which is the feed forward neural net, iterate through your training data, and find all the different input and output keys. When you input or output of your sample data has a property, give the training data that value. When it does not, give it a zero for the missing data.
net.train([{
input: {
value1: 1,
value2: 0
},
output: {
id123: 1,
id124: 0
},
input: {
value1: 0,
value2: 1
},
output: {
id123: 0,
id124: 1
}
]);
Ultimately, I think you found something we can try and improve though. Very cool, and very common looking, use case.
from brain.js.
I think the current answer to this, in the way that you are defining networks, it is like asking how to restructure a neural network, after it has already been structured to train it further. Currently this isn't implemented.
from brain.js.
Related Issues (20)
- Deno Support?
- The Recurrent class will not function without a GPU HOT 1
- Unable to install Brain.js on PopOS HOT 22
- GPU powered AI demo is a 404 HOT 2
- "Forecasting" demo is a 404 HOT 2
- tree process
- Freezing when training NeuralNetworkGPU (async).
- Train with NeuralNetworkGPU more slower than CPU HOT 3
- Always the same output data on NeuralNetwork HOT 1
- Unable to install on MacOS Ventura HOT 1
- Did you try the built in distance calc?
- need to update URL for example
- MacOS node 20.10.0 build failing HOT 2
- Fatal error while installing via NPM package HOT 1
- Most example links are broken HOT 4
- Summary()
- Type 'InputType' is not assignable to type 'Partial<INumberHash>'... and many others
- stream-example.js page not found error HOT 1
- Npm i brain.js || node-gyp error
- Brain.js to detect bad words 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 brain.js.