Machine Learning for LabVIEW, LabVIEW NXG, Arduino, C, C++, C#, Ardroid, and iOS applications

ANNHUB

ANNHUB Machine Learning Platform

ANNHUB is a machine learning platform that allows machine learning design, train, and validation without any programming. User can develop machine learning models to tackle real-life industrial solutions by merely clicking through the guided steps and utilizing auto-recommended training and validation features. It is ideal for engineers who do not have a profound knowledge of machine learning and programming skills to design a proper neural network. User can effortlessly develop the model in ANNHUB and integrate it into any applications with minimal API calls. Users may even deploy the solution to LabVIEW NXG, C, C++, C#, Android, iOS, Arduino, and Rasberry PI applications.

Equipped with a friendly user interface and auto-recommendation feature, ANNHUB allows users to complete any machine learning design tasks with ease by recommending neural network structures to achieve optimal performance based on the dataset. ANNHUB supports different types of activations functions and cost functions that give users the flexibility to customize any neural network structures. The particular type of Bayesian Neural Network is supported to effectively deals with small dataset applications.

ANNHUB supports advanced training algorithms, including Scaled Conjugate Gradient, Levenberg Marquardt, Quasi-Newton, and Bayesian Regularization that help speeding up training speed and to improve the convergence rate. During the training process, the over-fitting issue will be taken care of by the early stopping technique or Bayesian regularization automatically. To effectively evaluate a trained neural network model, ANNHUB supports various evaluation metrics, including ROC curves, confusion matrix, performance metrics, and regression curves. The performance of the trained model is also can be evaluated with the new dataset.

Features

ANNHUB key features

Easy to use

ANNHUB does not require in-depth machine learning knowledge and programming skills to design a neural network for any applications. Friendly user interface with auto-suggest features allows a user complete AI design task with ease.

Advanced algorithms

Effective Evaluation

ANNHUB supports various evaluation metrics, including ROC curves, confusion matrix, performance metrics, and regression curves to effectively evaluate a trained neural network model. The performance of the trained model can be evaluated with the new dataset.

Flexibility

ANNHUB supports different types of activations functions and cost functions that allow a designer to customize a neural network structure. Bayesian Neural Network is supported to effectively deals with applications with small datasets.

Easy to deploy

Trained neural network model can be easily deployed in real-time applications developed various programming languages such as LabVIEW, LabVIEW NXG, LabWindow CVI, C.C++, C#, iOS, Android and Arduino by using appropriate API provided by ANSCENTER.

Design assitance

Based on dataset loaded by a designer, ANNHUB suggests a neural network structure to achieve optimal performance. During the training process, the over-fitting issue will be taken care of by the early stopping technique or Bayesian regularization automatically.

Design process

How to design a neural network

Load dataset into ANNHUB

ANNHUB supports dataset in comma-separated values (CSV) format, as shown in the above figure. The outputs are identified by keywords "output, target, class." Each row in the csv file is equivalents to 1 data sample.

Configure a neural network structure

ANNHUB supports various activation types for both hidden layer and output layer. Both pre-processing and post-processing methods are provided to normalize dataset inputs and outputs. Designers can use different cost functions in conjunction with training engines to customize a neural network structure that suits their applications. Suggest the neural network structure is also provided based on dataset format.

Train a neural network

ANNHUB separates dataset into a training set, validation set, and test set. During the training process, the training set is used to train a neural network by optimizing its cost function while the validation set is used to prevent the over-fitting issue. If Bayesian Neural Network is used, regularization will help to prevent over-fitting. The training is finished when stopping criteria are met.

Evaluate trained neural network using ROC curve.

ANNHUB supports ROC curve technique to evaluate the performance of the trained neural network on both training set, validation set, and test set. These ROC curves provide essential information that helps the machine learning design process.

Evaluate trained neural network using confusion matrix in ANNHUB

Evaluate the trained neural network using confusion matrix.

ANNHUB supports confusion matrix technique to evaluate the performance of the trained neural network on both training set, validation set, and test set. These confusion matrices also include accuracy, sensitivity, and specificity information that helps the classification design process.

Evaluate trained neural network using regression curve in ANNHUB

Evaluate the trained neural network using regression curve.

ANNHUB supports regression curve technique to evaluate the performance of the trained neural network on both training set, validation set, and test set. These regression curves provide essential information that helps the regression design process.

Evaluate trained neural network with new dataset in ANNHUB

Evaluate the trained neural network with new dataset.

A completely new dataset can be loaded into ANNHUB to evaluate the performance of the trained neural network model. This valuable information helps to verify the trained model before deciding to deploy it into a real-time application.

Export trained a neural network for deployment in ANNHUB

Export trained neural network model for deploymennt

ANNHUB supports exporting trained neural network model into a weight file. This weight file is then can be loaded into different programming environments using Application Programming Interface (API) provided by ANS Center. By using an appropriate programming environment, the trained model can easily be deployed into any real-time applications.

Application Programming Interface

How to deploy a neural network into applications

After the trained neural network has been verified and tested with a new dataset, it is ready to be deployed in a real-time application. ANNHUB allows a user to export this trained model into a file with an "ann" extension. This file contains the trained neural network structure as well as its parameters.

ANNHUB supports different API to allow deploying the trained neural network model into an application developed by different programming languages such as LabVIEW, LabVIEW NXG, LabWindow CVI, C/C++/C#, Android, iOS and Arduino. Please login the ANSCENTER website and download appropriate API from the Customer Portal. Use supported API to import a trained model in “ann” extension text file into a machine learning application developed in a supported programming environment.

The customized application then can be compiled and deployed to an appropriate hardware platform.