Fraunhofer IMS and Arduino released an AI framework for Arduino.
Arduino is one of the widely used prototyping platforms. Fraunhofer IMS and Arduino have recently released a stand-alone C-programmed AI framework for Arduino that can be directly processed on the device. The training data can be captured directly on the device and used for training. This allows creation of battery-powered AI hardware without any link to the cloud.
The framework is known as AIfES, and it allows 8-bit microcontroller-based hardware like Arduino UNO to implement an artificial neural network that can be trained in moderate time. According to arduino.cc, this enables the creation of customizable devices that can adapt to the task at hand by means of training without using an external computer. Moreover, the framework directly integrates into the Arduino IDEs through the Arduino library manager.
The AI framework has been tested by Fraunhofer IMS, and it has been a proven effective development tool for customer-specific AI solutions. The demonstrations include handwriting recognition, gesture recognition and a wireless current sensor.
“AIfES is very similar to and compatible to Python ML frameworks such as TensorFlow, Keras or PyTorch, but its functionality is significantly reduced,” according to the Fraunhofer. “In the current version, feed-forward neural networks are supported, which can be configured completely freely. Also the popular activation functions like ReLU, Sigmoid or Softmax are already integrated. Model development is oriented to the Python frameworks. The common algorithms for training like the gradient descent optimiser or the Adam optimiser are also included.”
More information can be found at arduino.cc.