Phys.org August 15, 2024
Artificial intelligence systems and neural network models can reduce the intricacy of understanding creative cognition. The Hopfield neural network (HNN) is a simple model known for its biological plausibility in storing and retrieving neuron patterns. Researchers Germany implemented certain modifications to HNN as a step toward the larger framework of creative thinking-based association. The modifications included introducing pattern weights control, which provides a robust representation for content addressable memory and conceptual links in stored data. They identified two mechanisms controlling the transition from analytical to associative-based thinking, namely, the activation threshold of neurons, which acts as an on/off switch for the network and, the inhibition of stored concepts, like an on/off switch that guides the network to search for associative links and when to stop. According to the researchers their findings suggested that neurons step back from the contextual focus and found alternatives when analytical thinking was insufficient. These alternatives were linked to seemingly unrelated ideas, using inhibition as an analogy to the hyperparameters. Using hyperparameters to inhibit the stored patterns, they could control the creation of associative links… read more. Open Access TECHNICAL ARTICLEÂ
Crosstalk encountered by neurons at each update of the second scenario of the matrix (M = 4). Credit: Journal of Creative Behavior, 02 August 2024