Large-scale brain-like neural network implementation available for AI

In a new study recently published in the journal Nature Machine Intelligence, scientists at the National Institute for Mathematics and Computer Science (CWI) in the Netherlands showed how brain-like neurons can be combined with novel learning methods to enable large-scale training of fast and energy-efficient spiking neural networks. Potential applications include wearable artificial intelligence (AI), speech recognition, augmented reality, and many other areas. Such spiking neural networks, which can be implemented in chips called neuromorphic hardware, are expected to bring AI programs closer to the user. This solution facilitates privacy protection, robustness and responsiveness, with applications ranging from voice recognition in appliances, healthcare monitoring, drone navigation, to local surveillance devices.