A new method reveals how neural networks work.

A New Method Explains Artificial Intelligence

Researchers at Los Alamos National Laboratory have developed a new method of comparing neural networks. This method looks inside the \”black box\”, or artificial intelligence, to help researchers understand neural network behavior. The neural networks are used to identify patterns within datasets. They can be found in applications such as virtual assistants or facial recognition systems.

Haydn Jones is a Los Alamos researcher in the Advanced Research in Cyber Systems Group. \”The artificial Intelligence research community does not necessarily have a full understanding of what neural network do. They give us good results but we don’t understand how or why,\” he said. \”Our new approach does a much better job of comparing the neural networks. This is an important step towards better understanding AI’s mathematics.\”

Source:

New Method Exposes How Artificial Intelligence Works