Transfer Functions in Artificial Neural Networks - A Simulation-Based Tutorial

Artificial neural networks are based on computational units that resemble basic information processing properties of biological neurons in an abstract and simplified manner. Generally, these formal neurons model an input-output behaviour as it is also often used to characterize biological neurons. The neuron is treated as a black box; spatial extension and temporal dynamics present in biological neurons are most often neglected. Even though artificial neurons are simplified, they can show a variety of input-output relations, depending on the transfer functions they apply. This unit on transfer functions provides an overview of different transfer functions and offers a simulation that visualizes the input-output behaviour of an artificial neuron depending on the specific combination of transfer functions.

Particle placement and the case for “allostructions”

As a reaction against derivational frameworks, Construction Grammar accords no place to regular alternations between two surface patterns. This paper argues for a more tolerant position towards alternations. With respect to the well-known placement variability of verbal particles (pick up the book / pick the book up), the author grants that there is little reason for analysing one ordering as underlying the other but goes on to show that it is equally problematic to claim that the two orderings code two different meanings (or serve two different functions) and therefore cannot be linked in the grammar as variants of a single category. The alternative offered here is to consider the two orderings as two “allostructions” of a more general transitive verb-particle construction underspecified for word order.