In a new study, researchers Bojian Yin and Sander Bohté from the Dutch National Research Institute for Mathematics and Computer Science (CWI) have demonstrated a significant step towards artificial intelligence that can be used in local devices like smartphones and in VR-like applications, while protecting privacy. They show how brain-like neurons combined with novel learning methods enable the training of fast and energy-efficient spiking neural networks on a large scale. Potential applications range from wearable AI to speech recognition and Augmented Reality. The algorithms needed for this require a lot of computer memory, limiting the training of larger network models for more complex tasks. This research holds the promise of bringing AI programmes closer to users – on their own devices.
