Learning compositional sequences with multiple time scales through a hierarchical network of spiking neurons
نویسندگان
چکیده
منابع مشابه
Multiple time scales of temporal response in pyramidal and fast spiking cortical neurons.
Neural dynamic processes correlated over several time scales are found in vivo, in stimulus-evoked as well as spontaneous activity, and are thought to affect the way sensory stimulation is processed. Despite their potential computational consequences, a systematic description of the presence of multiple time scales in single cortical neurons is lacking. In this study, we injected fast spiking a...
متن کاملFrequency locking and travelling bursts sequences in modular network of inhibitory neurons with differing time-scales
We report the emergent dynamics of a community structured modular network of chaotic Hindmarsh-Rose (HR) neurons with inhibitory synapses. We find the inhibitory coupling between the neuronal modules lead to complete synchronization of neurons in a module, and also pushes modules into interesting sequences of travelling burst patterns. When dynamical time-scales vary for neurons in different mo...
متن کاملHierarchical compositional feature learning
We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images. The building blocks are binary features defined hierarchically as a composition of some of the features in the layer immediately below, arranged in a particular manner. At a high level, HCN is similar to a si...
متن کاملA Hardware Implementation of a Network of Functional Spiking Neurons with Hebbian Learning
Nowadays, networks of artificial spiking neurons might contain thousands of synapses. Although software solutions offer flexibility, their performance decreases while increasing the number of neurons and synapses. Embedded systems very often require real-time execution, which do not allow an unconstrained increasing of the execution time. On the other hand, hardware solutions, given their inher...
متن کاملModel-based reinforcement learning with spiking neurons
Behavioural and neuroscientific data on reward-based decision making point to a fundamental distinction between habitual and goal-directed action selection. An increasingly explicit set of neuroscientific ideas has been established for habit formation, whereas goal-directed control has only recently started to attract researchers’ attention. While using functional magnetic resonance imaging to ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: PLOS Computational Biology
سال: 2021
ISSN: 1553-7358
DOI: 10.1371/journal.pcbi.1008866