✦ LIBER ✦

Learning and structure of neuronal networks

✍ Scribed by KIRAN M KOLWANKAR; QUANSHENG REN; AREEJIT SAMAL; JÜRGEN JOST

Book ID: 107589070
Publisher: Springer-Verlag
Year: 2011
Tongue: English
Weight: 260 KB
Volume: 77
Category: Article
ISSN: 0304-4289
DOI: 10.1007/s12043-011-0192-2

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Effects of Hebbian learning on the dynam

Effects of Hebbian learning on the dynamics and structure of random networks with inhibitory and excitatory neurons

✍ Benoît Siri; Mathias Quoy; Bruno Delord; Bruno Cessac; Hugues Berry 📂 Article 📅 2007 🏛 Elsevier Science 🌐 English ⚖ 326 KB

Mathematical learning models and neurona

Mathematical learning models and neuronal networks

✍ E. Pfaffelhuber 📂 Article 📅 1973 🏛 Elsevier Science 🌐 English ⚖ 801 KB

Neuronal state feedback learning of Cohe

Neuronal state feedback learning of Cohen-Grossberg networks

✍ Apostolou, N.; King, R. E. 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 113 KB 👁 2 views

This paper proposes a direct synaptic weight training technique for a class of additive dynamic auto-associative neural networks based on the Cohen}Grossberg neuronal activation model. The proposed technique is based on the Jurdjevic}Quinn stabilization method for control a$ne systems. Asymptotic st

Neuronal codes: reading them and learnin

Neuronal codes: reading them and learning how their structure influences network organization

✍ Barry J. Richmond; Timothy J. Gawne; Guo-Xiong Jin 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 745 KB

Simulation of learning processes in neur

Simulation of learning processes in neuronal networks of the cerebellum

✍ D. S. Melkonian; H. H. Mkrtchian; V. V. Fanardjian 📂 Article 📅 1982 🏛 Springer-Verlag 🌐 English ⚖ 900 KB

Learning of modular structured networks

✍ Masumi Ishikawa 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 755 KB

Learning of large-scale neural networks suffers from computational cost and the local minima problem. One solution to these difficulties is the use of modular structured networks. Proposed here is the learning of modular networks using structural learning with forgetting. It enables the formation of