Tag: Convolutions
Understanding neural networks with neural-symbolic integration
Dr Joe Townsend, Dr Theodoros Kasioumis, and Dr Hiroya Inakoshi, from the Artificial Intelligence Research Division at Fujitsu Research of Europe Ltd, used Neural-Symbolic Integration to better understand the reasoning of Artificial Intelligence (AI). They developed two solutions. The first solution – ERIC: Extracting Relations Inferred from Convolutions – opens the so-called ‘black box’ of AI and attempts to translate […]
Read More… from Understanding neural networks with neural-symbolic integration