TinyML platform builds AI models in minutes

New Products |
By Nick Flaherty

Imagimob, based in Stockholm, has added embedded starter projects to the latest release of its TinyML AI platform to save time for developers.

The AutoML function in the Imagaimob AI platform has been enhanced, taking labelled datasets, preprocessing blocks, the neural network architectures and giving the developer a list of good candidate model architectures. The model architectures are then trained in the cloud training service, and the developer can focus on evaluating and finding the best model.

The starter projects increase the quality of the AI application and reduces time needed to get up and running. A developer can select a starter project from a list of pre-defined projects, and build deep learning AI models in minutes. The starter project includes labelled datasets, pre-processing blocks and a pre-trained AI model. Everything that is needed to get started is included, and all the content is quality assured by Imagimob.

Related articles

The starter projects include and Acconeer Radar Gesture Project using the Acconeer A1 sensor and a Texas Instruments Radar Gesture Project using the Texas Instruments mmWave Radar Sensor IWR6843AOP. There is also an audio Keyword Spotter Project that uses data from a microphone and a Human Activity Recognition Project using data from a 3-axis accelerometer. An Indoor/outdoor Detection project uses environmental data from the Nordic Thingy:91 board.

Comparing numbers when selecting a model is easy to do but lacks the in-depth understanding needed to really know if a model is production-ready or not. In this latest release, improvements have been made in how developers are able to visualize their model output alongside their data. This gives a thorough understanding of the model’s reaction to different events within the datasets and allows the developer to understand the strengths and weaknesses of different models.

The new release is available from today and can be downloaded from the Imagimob website.

Other articles on eeNews Europe



Linked Articles
eeNews Europe