no code implementations • 20 Jun 2017 • Kazuyuki Hara, Kentaro Katahira, Masato Okada
The value of the objective function for an unperturbed output is called a baseline.
no code implementations • NeurIPS 2010 • Kentaro Katahira, Kazuo Okanoya, Masato Okada
Loewenstein & Seung (2006) demonstrated that matching behavior is a steady state of learning in neural networks if the synaptic weights change proportionally to the covariance between reward and neural activities.