Synaptic Pruning in Development: A Computational Account

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks (2022, background): “After extensive synaptic pruning during childhood (Chechik et al., 1998), the connection density of the brain stays roughly constant (in healthy adults).”
Fast ConvNets Using Group-Wise Brain Damage (2015, background): “Such process resembles the biological learning processes in mammals, in whose brains the number of synapses peak during early childhood and is then reduced substantially in the process of synaptic pruning [8].”
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression (2017, neutral): “A similar strategy was also explored in [2].”
The brainstem reticular formation is a small-world, not scale-free, network (2006, background): “Assuming that a network could support only a limited number of synapses, Chechik et al. (1998) report that optimal synaptic pruning can be achieved using a minimal-value deletion scheme—removing all connections below a given absolute weighted value.”
Storage capacity diverges with synaptic efficiency in an associative memory model with synaptic delay and pruning (2003, methodology): “In the case of a small loading rate α , if a state close to one or a set of the patterns stored as a sequence is given to the network, the stored sequence of memory patterns is retrieved.”