The receptron is a nonlinear threshold logic gate with intrinsic multi-dimensional selective capabilities for analog inputs
This work addresses the need for simpler, more selective classification devices for edge applications, offering a potential new class of networks without complex training, though it appears incremental as a generalization of existing models.
The authors tackled the limited classification capabilities of linear threshold logic gates by introducing the receptron, a nonlinear generalization with input-dependent weight functions, which significantly enhances classification performance even as a single unit, demonstrating selective activation for analog inputs within cubic domains in 3D space.
Threshold logic gates (TLGs) have been proposed as artificial counterparts of biological neurons with classification capabilities based on a linear predictor function combining a set of weights with the feature vector. The linearity of TLGs limits their classification capabilities requiring the use of networks for the accomplishment of complex tasks. A generalization of the TLG model called receptron, characterized by input-dependent weight functions allows for a significant enhancement of classification performances even with the use of a single unit. Here we formally demonstrate that a receptron, characterized by nonlinear input-dependent weight functions, exhibit intrinsic selective activation properties for analog inputs, when the input vector is within cubic domains in a 3D space. The proposed model can be extended to the n-dimensional case for multidimensional applications. Our results suggest that receptron-based networks can represent a new class of devices capable to manage a large number of analog inputs, for edge applications requiring high selectivity and classification capabilities without the burden of complex training.