Sign in to see all reviews and comparisons. It's Free!
By clicking Sign In with Social Media, you agree to let PAT RESEARCH store, use and/or disclose your Social Media profile and email address in accordance with the PAT RESEARCH
Privacy Policy
and agree to the
Terms of Use.
NeuralN is a C++ Neural Network library for Node.js with multiple advantages compared to existing solutions Works with extra large datasets (>1Go allowed by nodejs) and Multi-Threaded training available.
Category
Artificial Neural Network Software
Features
•Large datasets
•Multi-Threaded
License
Proprietary Software
Pricing
Subscription
Free Trial
Available
Users Size
Small (<50 employees), medium (50 to 1000 enterprise (>1001 employees)
Company
NeuralN
What is best?
•Large datasets
•Multi-Threaded
PAT Rating™
Editor Rating
Aggregated User Rating
Rate Here
Ease of use
8.6
6.1
Features & Functionality
8.6
—
Advanced Features
8.4
—
Integration
8.4
—
Performance
8.5
—
Customer Support
7.6
—
Implementation
—
Renew & Recommend
—
Bottom Line
With Node.js and the V8, it is not possible to work with large datasets since the maximum allowed memory is around 512MB for 32-bits machines and 1GB for 64-bits machines.With the multi-threaded training method of NeuralN, you can significantly reduce the duration of the learning phase, by training your network simultaneously on different parts of your dataset.
8.4
Editor Rating
6.1
Aggregated User Rating
1 rating
You have rated this
NeuralN is a C++ Neural Network library for Node.js with multiple advantages compared to existing solutions. It works with extra-large datasets (>1Go allowed by nodejs) and Multi-Threaded training available. With Node.js and the V8, it is not possible to work with large datasets since the maximum allowed memory is around 512MB for 32-bits machines and 1GB for 64-bits machines.
When working with datasets of several gigabytes, it quickly becomes difficult to train the network with all the data. NeuralN allows users to use datasets as big as their memory can contain.
Working with large datasets increases the performances of the final network, but the learning phase can sometimes take up to several days or even weeks to obtain good results. With the multi-threaded training method of NeuralN, users can significantly reduce the duration of the learning phase, by training their networks simultaneously on different parts of their dataset. The results of each iteration are then combined.
NeuralN can return a string representation of the network in order to save and reload it later. It can also return a string representation of each neuron of the network. It allows users to understand which entrance neurons most impacted the final result. Moreover, it can return a json representation of the network and the network's state but this is not recommended when the network structure gets big.
NeuralN features a `visu_state` tool that takes as argument the state of a neural network right after classification and generates an html page rendering the classification state using SVG. The `visu_state` command takes a filename as argument containing the neural network state string as returned by the `get_state` method.
We are the movers and shakers of B2B Software & Services. We have been copied by many including the you know who?
Why not get it straight and right from the original source. Join over 66,000+ Executives by subscribing to our newsletter... its FREE ! and get fully confidential personalized recommendations for your software and services search
Privacy Policy: We hate SPAM and promise to keep your email address safe.
By clicking Sign In with Social Media, you agree to let PAT RESEARCH store, use and/or disclose your Social Media profile and email address in accordance with the PAT RESEARCH Privacy Policy and agree to the Terms of Use.