The NeoPulse® Product Suite
The NeoPulse Framework enables organizations to manage their entire AI workflow and infrastructure from one place. This means that DevOps, data engineers and ML engineers work from one interface instead
of using separate applications. Using NeoPulse, a data engineer can assemble training data sets. The machine learning engineer can create AI models. The DevOps engineer can deploy and manage the solution without ever leaving the NeoPulse environment.
NeoPulse® Studio: AI to build AI
Server application with a powerful AI called “the oracle” that is capable of automating the process of creating sophisticated AI models
NeoPulse® Manager
Manages your AI infrastructure and orchestrates workflows to automate AI generation activities
NeoPulse® Runtime
A program that is licensed by the organization to allow any application in the enterprise to access the AI model using a web-based (REST) API*
NeoPulse® Features
NeoPulse is an end-to-end automated AI platform that enables organizations to streamline the entire machine learning process, while offering them the ability to manage data sets, control AI assets such as AI models, and automate the retraining or redeployment of AI models.
Data Engineering
- Prepare training data sets
- Annotate data
- Identify anomalies
- Integrate with AI development – keep track of what data sets were used to train what model
AI Development & Engineering
- Low code/no code ML model development
- Integrate third party AI models
- Automate retraining
- Visual interface
- AI model performance baselining
AI Deployment & Management
- Organize machines, devices, data sets, applications, and models
- Drag-and-drop deployment
- Production monitoring and A/B testing
- Role-based control of assets and resources
- Deployment to the edge, on-premise, to the cloud or hybrid environments
AI Governance
- Digital Rights Management
- Provenance
- Data source integrity
Scaling
-
Deploy models across hundreds of systems
NeoPulse® Automates AI Generation for Most Data Types
The NeoPulse Framework can create machine learning models based on a variety of data types. It supports both supervised (such as classification and regression) and some unsupervised learning (such as GANs and autoencoders).
image classification
Object recognition
Acoustic/Audio Analysis
DICOM & 3D Imaging
Text analysis
Video analysis
Regression/Time series
Biochemistry/genomics/ proteomics
NeoPulse AI Studio
Use the Power of AI to Build Custom Solutions in Days Instead of Months
WATCH VIDEO
8 Steps to Intelligent Applications
NeoPulse enables enterprises to create and deploy AI models quickly and at scale using NeoPulse Studio to create AI models and NeoPulse Runtime to execute the models. Because of the enterprise features, the NeoPulse Framework can produce significant cost and time savings. A company can train and deploy an AI model in minutes!
1. Curate the Training Data & Construct a .csv File
The first step is to prepare the training data using a CSV file.
If you have high quality properly formatted images, a simple script can construct the .csv file in about 20 minutes.
The NML (NeoPulse Modeling Language) file and the CSV data are compiled and model training is initiated. NeoPulse employs a queuing mechanism so that training jobs can be submitted even if the NeoPulse Studio is busy.
Tip: Copy one of the examples listed on our GitHub page and modify it for your needs – 15 minutes.
Compiling the NML code (assuming no syntax errors) is immediate – seconds.
NeoPulse chooses from over 700,000 possible algorithms to determine the most optimal algorithm.
Training can take time depending on the volume of data and the compute resources available. There’s nothing for you to do but the machine will be busy for a couple of days or more for a decent model.
Fortunately, NeoPulse Studio employs a queuing model – so it doesn’t stop you from starting the next project.
5. Evaluate & Visualize the Model
NeoPulse Studio offers powerful tools to evaluate your model including validation accuracy, validation loss, seeing the hyperparameter choices and visualizing the model generated by NeoPulse Studio
Once the validation is complete, the model can be exported.
Exporting a PIM file is simple – choose from a set of models based on accuracy, for example, and simply export in a single call.
Once the model has been exported, the resulting PIM file can be moved to any target environment that is hosting NPR (NeoPulse Runtime). The PIM file can be imported into NPR and NPR will automatically generate a REST interface that can be queried
Importing the model into the Runtime is a simple command – takes just a couple of seconds.
Finally, an application can be written that makes a call to the NPR that is hosting the PIM file.
8. Call the model via a REST API from the application
After importing the model, NeoPulse Runtime automatically generates a RESTful API that allows applications to query the model directly. You don’t need to build any custom APIs to call your model.
View Use Cases
Download White Paper