DeepMind has unveiled a new neural network that opens the door for computing systems to (eventually) intuitively understand the relationships between objects or things in a human-like manner. The Alphabet subsidiary has potentially opened the door for relational reasoning, the intuitive understanding that has so-far been off-limits for machines. The new approach lets DeepMind ask the system complex questions that can’t be answered using the current processes, such as “’what size is the cylinder that is left of the brown metal thing that is left of the big sphere.” Achieving a 95.5% success rate, DeepMind posted results that it says are slightly more accurate than humans – when it comes to understanding the relationships between physical objects and their states.…