Claudia Clopath

TL;DR: It is shown that it is possible to overcome the limitation of connectionist models and train networks that can maintain expertise on tasks that they have not experienced for a long time and selectively slowing down learning on the weights important for previous tasks.

TL;DR: In this paper, the authors show that it is possible to train networks that can maintain expertise on tasks that they have not experienced for a long time by selectively slowing down learning on the weights important for those tasks.

TL;DR: An essential role of inhibitory plasticity is suggested in the formation and maintenance of functional cortical circuitry that can accommodate synaptic memories with activity patterns that become indiscernible from the background state but can be reactivated by external stimuli.

TL;DR: It is argued that a deep network is best understood in terms of components used to design it—objective functions, architecture and learning rules—rather than unit-by-unit computation.

TL;DR: A model of spike timing–dependent plasticity (STDP) in which synaptic changes depend on presynaptic spike arrival and the postsynaptic membrane potential, filtered with two different time constants is created and found that the plasticity rule led not only to development of localized receptive fields but also to connectivity patterns that reflect the neural code.