artificial-neural-networks | simple neural network using sigmoid function | Machine Learning library
kandi X-RAY | artificial-neural-networks Summary
kandi X-RAY | artificial-neural-networks Summary
simple neural network using sigmoid function
Support
Quality
Security
License
Reuse
Top functions reviewed by kandi - BETA
- Activate the model
- Calculate the dot product of inputs
artificial-neural-networks Key Features
artificial-neural-networks Examples and Code Snippets
Community Discussions
Trending Discussions on artificial-neural-networks
QUESTION
i have start learn ML from online curses and find it very exciting.
the examples are pretty easy to understand (written in python) and the results are amazing , but all the examples are pretty simple and don't explain how to decide how many hidden layers and neurons needed in the hidden layers , so i searched in google.
most of the results say its art and experience, i found one article that show how beginners-ask-how-many-hidden-layers-neurons-to-use-in-artificial-neural-networks but for large data sets with a lot of parameters i cant rely draw boundaries , is there a way to do it programmable or a better way to know how many hidden layers and neurons i need?
...ANSWER
Answered 2019-Apr-19 at 22:43No, this is a matter of experimentation to find what solves your problem. As your reference shows, the layer complexity is driven by the inherent complexity of your data and the classifications you're trying to do.
As a general principle, note that a hidden layer is a minimal convenience: a linear combination of linear combinations does not produce any additional learning capability: it's still a linear combination. Thus, you need only one hidden layer -- although for some problems, using two or three hidden layers will slightly reduce the quantity of neurons needed to train at the same rate.
When I need to do such design, I attack it simply: start with a hidden layer with my best guess at the quantity of neurons I'll need. Train the model; if it fails to converge, look at the loss function to see how badly it failed. Based on that, increase the neurons (double, 10x, ...) and try again.
Once it succeeds, then I gradually reduce the neuron count until I find the "sweet spot" for accuracy vs training time.
Some problems don't solve readily through a simple NN. Depending on the application, you may need something from the Deep Learning world, such as a simple CNN (Convolutional NN).
If your data set is complex enough, you may also want to apply PCA (Principal Component Analysis) to find the significant input parameters. You can then reduce the input data, greatly reducing the size of the NN and the training time required to converge.
Community Discussions, Code Snippets contain sources that include Stack Exchange Network
Vulnerabilities
No vulnerabilities reported
Install artificial-neural-networks
You can use artificial-neural-networks like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.
Support
Reuse Trending Solutions
Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items
Find more librariesStay Updated
Subscribe to our newsletter for trending solutions and developer bootcamps
Share this Page