SensiML combines popular hardware evaluation tools for AI-based applications
For engineers developing AI-based consumer wearable or industrial IoT products, SensiML’s Analytics Toolkit is an end-to-end AI development platform spanning data collection, labelling, algorithm and firmware auto-generation, and testing.
Developers can use it to quickly generate application-specific pattern recognition code that transforms sensors into smart, actionable event detectors, explains SensiML.
It has been developed for engineers evaluating software tools to help implement AI, from cloud-based analytics which offers nearly limitless computing resources but introduces communication issues such as latency, bandwidth constraints, fault tolerance, and security – to local embedded development tools which rely upon data scientists and firmware engineers to hand-code algorithms at significant cost and development time.
The SensiML Analytics Toolkit includes tools to create optimised AI code without the user having to have data science expertise. Other tools generate code that can run on microcontrollers rather than central processing units (CPUs) and tools to make designs flexible and easily extensible, support an end-to-end workflow and deliver production-grade capabilities such as multi-user, multi-project, and dataset management. There are also tools to gain “significant” time-to-market – up to five times faster than AI expert hand coding, says the company.
The toolkit has been designed to support multiple hardware evaluation platforms including the QuickLogic Merced and Chilkat platforms, Raspberry Pi, the ST Sensor Tile and the Nordic Thingy.
To further lower the barriers to entry, at SensiML is offering a trial version free of charge. The trial Analytics Toolkit includes data collection and labelling (using sample datasets), automated machine learning (ML) algorithm creation, algorithm performance visualisation, auto-generation of optimised device code, embedded binary executable output (limited number of classification results per device power cycle) and device test/validation.
This trail toolkit allows users to explore the design flow used to quickly create AI-based IoT applications and gain a deeper understanding of how the SensiML Analytics Toolkit can help an application development.