All Projects → nemo → Natural Synaptic

nemo / Natural Synaptic

Licence: mit
Javascript Natural Language Classifier

Programming Languages

javascript
184084 projects - #8 most used programming language

Projects that are alternatives of or similar to Natural Synaptic

Lossfunctions.jl
Julia package of loss functions for machine learning.
Stars: ✭ 89 (-19.09%)
Mutual labels:  classification
Augmentedgaussianprocesses.jl
Gaussian Process package based on data augmentation, sparsity and natural gradients
Stars: ✭ 99 (-10%)
Mutual labels:  classification
Onenotetaggingkit
OneNote (desktop) add-in to manage OneNote pages by page tags
Stars: ✭ 106 (-3.64%)
Mutual labels:  classification
Tabi
BGP Hijack Detection
Stars: ✭ 90 (-18.18%)
Mutual labels:  classification
Dataset
Crop/Weed Field Image Dataset
Stars: ✭ 98 (-10.91%)
Mutual labels:  classification
Fastrtext
R wrapper for fastText
Stars: ✭ 103 (-6.36%)
Mutual labels:  classification
Nlp Journey
Documents, papers and codes related to Natural Language Processing, including Topic Model, Word Embedding, Named Entity Recognition, Text Classificatin, Text Generation, Text Similarity, Machine Translation),etc. All codes are implemented intensorflow 2.0.
Stars: ✭ 1,290 (+1072.73%)
Mutual labels:  classification
Selfdrivingcar
A collection of all projects pertaining to different layers in the SDC software stack
Stars: ✭ 107 (-2.73%)
Mutual labels:  classification
Universal Data Tool
Collaborate & label any type of data, images, text, or documents, in an easy web interface or desktop app.
Stars: ✭ 1,356 (+1132.73%)
Mutual labels:  classification
Neuroflow
Artificial Neural Networks for Scala
Stars: ✭ 105 (-4.55%)
Mutual labels:  classification
Machine Learning Algorithms
A curated list of almost all machine learning algorithms and deep learning algorithms grouped by category.
Stars: ✭ 92 (-16.36%)
Mutual labels:  classification
Happy Transformer
A package built on top of Hugging Face's transformer library that makes it easy to utilize state-of-the-art NLP models
Stars: ✭ 97 (-11.82%)
Mutual labels:  classification
Fine grained classification
Fined grained classification On Car dataset
Stars: ✭ 103 (-6.36%)
Mutual labels:  classification
Uer Py
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
Stars: ✭ 1,295 (+1077.27%)
Mutual labels:  classification
Gpstuff
GPstuff - Gaussian process models for Bayesian analysis
Stars: ✭ 106 (-3.64%)
Mutual labels:  classification
Pytorch Sentiment Classification
LSTM and CNN sentiment analysis
Stars: ✭ 89 (-19.09%)
Mutual labels:  classification
Segmentation
Tensorflow implementation : U-net and FCN with global convolution
Stars: ✭ 101 (-8.18%)
Mutual labels:  classification
Pointnet Keras
Keras implementation for Pointnet
Stars: ✭ 110 (+0%)
Mutual labels:  classification
Edafa
Test Time Augmentation (TTA) wrapper for computer vision tasks: segmentation, classification, super-resolution, ... etc.
Stars: ✭ 107 (-2.73%)
Mutual labels:  classification
Bert Relation Classification
A pytorch implementation of BERT-based relation classification
Stars: ✭ 103 (-6.36%)
Mutual labels:  classification

natural-synaptic

Circle CI

A natural language classifier for Node Natural using a Synaptic neural network.

This project was inspired by Natural Brain, which is based on a BrainJS neural network. The reason for the re-write is that BrainJS is currently unmaintained (see issue).

Note: This classifier passes the same tests as the Node Natural Bayes classifier.

Usage

Installing

You can either clone this repo or install it from npm:

npm install natural-synaptic --save

Training and Classifying

var NaturalSynaptic = require('natural-synaptic');
var classifier = new NaturalSynaptic();

classifier.addDocument('my unit-tests failed.', 'software');
classifier.addDocument('tried the program, but it was buggy.', 'software');
classifier.addDocument('tomorrow we will do standup.', 'meeting');
classifier.addDocument('the drive has a 2TB capacity.', 'hardware');
classifier.addDocument('i need a new power supply.', 'hardware');
classifier.addDocument('can you play some new music?', 'music');

classifier.train();

console.log(classifier.classify('did the tests pass?')); // -> software
console.log(classifier.classify('did you buy a new drive?')); // -> hardware
console.log(classifier.classify('What is the capacity?')); // -> hardware
console.log(classifier.classify('Lets meet tomorrow?')); // -> meeting
console.log(classifier.classify('Can you play some stuff?')); // -> music

Load/Reload from file

var NaturalSynaptic = require('natural-synaptic');
var classifier = new NaturalSynaptic();

classifier.addDocument('my unit-tests failed.', 'software');
classifier.addDocument('tried the program, but it was buggy.', 'software');
classifier.addDocument('tomorrow we will do standup.', 'meeting');
classifier.addDocument('the drive has a 2TB capacity.', 'hardware');
classifier.addDocument('i need a new power supply.', 'hardware');
classifier.addDocument('can you play some new music?', 'music');

classifier.train();

classifier.save("file_to_save.json", function(err) {
    NaturalSynaptic.load("file_to_save.json", function(err, newClassifier) {
        console.log(newClassifier.classify('did the tests pass?')); // -> software
        console.log(newClassifier.classify('did you buy a new drive?')); // -> hardware
        console.log(newClassifier.classify('What is the capacity?')); // -> hardware
        console.log(newClassifier.classify('Lets meet tomorrow?')); // -> meeting
        console.log(newClassifier.classify('Can you play some stuff?')); // -> music
    });
});
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].