𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Simulation of cortex-like neural networks on a CNAPS SIMD neurocomputer

✍ Scribed by Ralf Möller; Peter Paschke

Book ID
104768800
Publisher
Springer US
Year
1996
Tongue
English
Weight
510 KB
Volume
4
Category
Article
ISSN
1370-4621

No coin nor oath required. For personal study only.

✦ Synopsis

Neurons of the cortical tissue in a mammalian brain are connected in an extremely sparse and random fashion. The paper presents efficient methods for a parallel simulation of neural networks modeling this connection scheme on a CNAPS SIMD neurocomputer. Appropriate algorithms and data structures are introduced that allow for a minimal loss of parallelism during the computation of input scalar products. A 'greedy' optimization procedure applied to the neuron-processor assignment is shown to gain a further reduction of computation time getting close to the lower bound. Using these methods, a considerable speedup in comparison to sequential computation is achieved.

📜 SIMILAR VOLUMES

Extended Kalman Filter Training of Neura
Extended Kalman Filter Training of Neural Networks on a SIMD Parallel Machine
✍ Shuhui Li; Donald C. Wunsch; Edgar O'Hair; Michael G. Giesselmann 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 260 KB

The extended Kalman filter (EKF) algorithm has been shown to be advantageous for neural network trainings. However, unlike the backpropagation (BP), many matrix operations are needed for the EKF algorithm and therefore greatly increase the computational complexity. This paper presents a method to do

[Lecture Notes in Computer Science] Arti
[Lecture Notes in Computer Science] Artificial Neural Networks – ICANN 2010 Volume 6353 || A Neurocomputational Model of Nicotine Addiction Based on Reinforcement Learning
✍ Diamantaras, Konstantinos; Duch, Wlodek; Iliadis, Lazaros S. 📂 Article 📅 2010 🏛 Springer Berlin Heidelberg 🌐 English ⚖ 189 KB

th This volume is part of the three-volume proceedings of the 20 International Conference on Arti?cial Neural Networks (ICANN 2010) that was held in Th- saloniki, Greece during September 15–18, 2010. ICANN is an annual meeting sponsored by the European Neural Network Society (ENNS) in cooperation wi