✦ LIBER ✦

Improving reinforcement learning in stochastic RAM-based neural networks

✍ Scribed by Alistair Ferguson; Hamid Bolouri

Publisher: Springer US
Year: 1996
Tongue: English
Weight: 250 KB
Volume: 3
Category: Article
ISSN: 1370-4621
DOI: 10.1007/bf00417784

No coin nor oath required. For personal study only.

✦ Synopsis

RAM-based neural networks are designed to be efficiently implemented in hardware. The desire to retain this property influences the training algorithms used, and has led to the use of reinforcement (reward-penalty) learning. An analysis of the reinforcement algorithm applied to RAM-based nodes has shown the ease with which unlearning can occur. An amended algorithm is proposed which demonstrates improved learning performance compared to previously published reinforcement regimes.

📜 SIMILAR VOLUMES

Reinforcement learning in random neural

Reinforcement learning in random neural networks for cascaded decisions

✍ Ugur Halici 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 771 KB

Spiking neural network model of free-ene

Spiking neural network model of free-energy-based reinforcement learning

✍ Takashi Nakano; Makoto Otsuka 📂 Article 📅 2011 🏛 BioMed Central 🌐 English ⚖ 289 KB

Figure 1 Performance of the spiking neural network. A. The free-energies estimated by both the spiking neural network and the original RBM. They are highly correlated (correlation coefficient, r = 0.9485) B. The hidden neurons activation on the two principal components. The hidden activation pattern

Learning in feed-forward neural networks

Learning in feed-forward neural networks by improving the performance

✍ Mirta B. Gordon; Pierre Pereto; Miguel Rodriguez-Girones 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 390 KB

A reinforcement learning approach based

A reinforcement learning approach based on the fuzzy min-max neural network

✍ Aristidis Likas; Kostas Blekas 📂 Article 📅 1996 🏛 Springer US 🌐 English ⚖ 374 KB

The fuzzy min-max neural network constitutes a neural architecture that is based on hyperbox fuzzy sets and can be incrementally trained by appropriately adjusting the number of hyperboxes and their corresponding volumes. Two versions have been proposed: for supervised and unsupervised learning. In

Reinforcement Learning Enhanced Iterativ

Reinforcement Learning Enhanced Iterative Power Allocation in Stochastic Cognitive Wireless Mesh Networks

✍ Xianfu Chen; Zhifeng Zhao; Honggang Zhang; Tao Chen 📂 Article 📅 2010 🏛 Springer US 🌐 English ⚖ 759 KB

Back-propagation learning in improving t

Back-propagation learning in improving the accuracy of neural network-based tourism demand forecasting

✍ Rob Law 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 184 KB

Traditional tourism demand forecasting techniques concentrate predominantly on multivariate regression models and univariate time-series models. These single mathematical function-based forecasting techniques, although they have achieved a certain degree of success in tourism forecasting, are unable