CTO Anatoli Gorchetchnikov shared his thoughts on artificial intelligence (AI) with the audience at ESC 2018.
One of the major hassles of Deep Learning is the need to fully retrain the network on the server every time new data becomes available in order to preserve the previous knowledge. This is called “catastrophic forgetting,” and it severely impairs the ability to develop a truly autonomous AI.
This problem is solved by simply training on the fly — learning new objects without having to retrain on the old. Imagine a toy that can learn to recognize and react to its owner, or a drone that can learn and detect objects of interest identified while in flight.
Without catastrophic forgetting, this is all possible. State-of-the-art accuracy, as well as real-time performance suitable for deployment of AI directly on the edge, moves AI out of the server room and into the hands of consumers, allowing for technology that mimics the human brain.
