- 150+ special inbuilt math functions(like integration, limit-continuity, Differentiation, Data analysis, etc.)
- 35+ probability distributions(for handling probabilistic data)
- 50+ sample dataset for doing testing and development etc.
Binary classification via Stochastic gradient descent
For ex: @stdlib/ml/online-binary-classification
Natural language processing
For ex: @stdlib/nlp and many othere features.
KerasJS is another trending open source available framework that allows you to run machine learning models in the browser and helps you to easily run Keras models in the browser with support of GPU via WebGL. These models also work in Node.js if CPU mode is allowed. Keras.js also extends its support for model training using any backend framework, such as the Microsoft Cognitive Toolkit (CNTK), Next.js, Meteor.js. Some Keras models that can be deployed on the client-side browser includes Inception v3 (trained on ImageNet), 50-layer Residual Network (trained on ImageNet), and Convolutional variational auto-encoder (trained on MNIST).
Below are some Keras models that can be run in the browser:
- DenseNet-121, trained on ImageNet
- Inception v3, trained on ImageNet
- Convolutional variational autoencoder, trained on MNIST etc.
To set up Brain.js, use the following code:
npm install brain.js
You can also include the library in the browser using the code given below
However, to install the Naive Bayesian classifier, use the following code
npm install classifier
To install the ConvNetJS classifier, use the following code
npm i convnetjs
One of the disadvantages of using this library is that it is difficult to manage and it is also complex for beginners who want to use it. To use this library you must have appropriate common knowledge of this field. We can also disfavor it because the processing sometimes becomes slower than in other tools equivalent to this.
ML.JS gives machine learning tools for working with NodeJS and browsers. The main motive of ML.js is to make machine learning approachable for large geographical users, well-skilled coders, and students. This library has included almost all the possible algorithms that one must need to build a good machine learning models. ML.js gives us the ability to take machine learning at another level. ML Hub-Team likes to work with new technologies and such great implementations of it.
You can set up the ML.js tool using the following code
ML.js supports the following machine learning algorithms…
- K-Nearest Neighbor (KNN)
- Naive Bayes
- Partial least squares (PLS)
- Simple linear regression
- Random forest
- Logistic regression
- Decision tree: CART
- Multi-variate linear regression
- Support vector machines (SVM)
- K-means clustering
- Principal component analysis (PCA)