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

✍ Scribed by Takashi Nakano; Makoto Otsuka

• Publisher: BioMed Central
• Year: 2011
• Tongue: English
• Weight: 289 KB
• Volume: 12
• Category: Article
• ISSN: 1471-2202
• DOI: 10.1186/1471-2202-12-s1-p244

✦ Synopsis

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 patterns are clustered by same optimal action.