IoT Edge Inferencing and Learning
Whether your needs require edge algorithm execution or edge adaptive learning models, SensiML Knowledge Packs can accommodate your application.
For applications where a defined edge algorithm meets the need, Knowledge Packs can be easily constructed and tested in the cloud and deployed to the edge device. Developers may implement any mechanism to associate or update a device with a given Knowledge Pack based on contextual information or user preference for that device. Model selection can utilize universal models or be more narrowly defined based on metadata that links to Knowledge Packs trained on specific subsets of data.
For those applications that demand true per-instance customization, this can also be achieved using adaptive edge model tuning. This more advanced feature is an available option for users to implement personalized model parameters from true on-device tuning using the SensiML API to adjust model weights and parameters locally.
Using the SensiML Analytics Studio users can optimize their algorithm either through AutoML or through an expert user interface of plug and play building blocks using SensiML Analytics Studio Notebook and our rich library of device optimized functions.
Knowledge Pack Classification Methods
- Pattern Matching with KNN
- Neuron activation with RBF
- Ensemble of Decision Trees
- Hierarchal Modeling with Multiple Classifiers
- Anomaly Detection with RBF
- Deep Inference with Quantized NN*
*For a complete list, see supporting documentation included with the SensiML Analytics Studio.
Hardware Architecture Support
SensiML supports a range of hardware architectures. Choose your desired architecture and SensiML AutoML will tailor Knowledge Pack code to provide power/performance optimization utilizing the ISA and HW accelerators available on the target system.
The SensiML Endpoint AI Workflow
SensiML covers a broad array of embedded microcontrollers and sensors enabling developers to target the right system for their application needs. From small ultra-low power MCUs possessing tens of kB memory to multi-core x86 client nodes with GBs of SRAM, SensiML provides ML code output to suit the hardware capabilities of your chosen platform.
Whether you are an experimenter, startup, mid-sized manufacturer, or large enterprise, SensiML has a plan tailored to suit your requirements. Compare our different plan features or get started with our "Free Community Edition" to determine what is best for your own IoT project. As such, you can fully explore the capabilities of the toolkit, collect and label your own data, and build and show real working AI edge models!
Quick Links
