Feedforward Inhibition Allows Input Summation to Vary in Recurrent Cortical Networks
نویسندگان
چکیده
منابع مشابه
An evolutionary approach to training feedforward and recurrent neural networks
This paper describes a method of utilising genetic algorithms to train fixed architecture feed-forward and recurrent neural networks. The technique described uses the genetic algorithm to evolve changes to the weights and biases of the network rather than the weights and biases themselves. Results achieved by this technique indicate that for many problems it compares very favourably with the mo...
متن کاملConnected Cortical Recurrent Networks
A model of an associative memory composed of many mod ules working as attractor neural networks with features of biological re alism is proposed and analyzed using standard statistical physics tech niques The memories of the system are stored in the synapses between neurons in the same module and the synapses between neurons in di er ent modules provide the associations between these memories A...
متن کاملDivisive inhibition in recurrent networks.
Models of visual cortex suggest that response selectivity can arise from recurrent networks operating at high gain. However, such networks have a number of problematic features: (i) they operate perilously close to a point of instability, (ii) small changes in synaptic strength can dramatically modify the degree of amplification, and (iii) they respond slowly to rapidly changing stimuli. Divisi...
متن کاملStability of Learning in Classes of Recurrent and Feedforward Networks
Stability of Learning in Classes of The relationship to work by Mozer, [5], on induction of temporal structure, is briefly described in [13]. Recurrent and Feedforward Networks In the research reported here, the task is similar to Elman’s: predicting the next letter in a word (or the end of William H. Wilson the word) from the current letter and the representation of past letters held in the st...
متن کاملEnforcing balance allows local supervised learning in spiking recurrent networks
To predict sensory inputs or control motor trajectories, the brain must constantly learn temporal dynamics based on error feedback. However, it remains unclear how such supervised learning is implemented in biological neural networks. Learning in recurrent spiking networks is notoriously difficult because local changes in connectivity may have an unpredictable effect on the global dynamics. The...
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: eneuro
سال: 2018
ISSN: 2373-2822
DOI: 10.1523/eneuro.0356-17.2018