Learning in neural networks by reinforcement of irregular spiking.

By Xiaohui S. Xie, H. Sebastian Seung. 2004

166 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Short-term plasticity as cause–effect hypothesis testing in distal reward learning (2014, background): “The maximization of reward functions was also implemented in a variety of neural network models (Lin, 1993; Pennartz, 1997; Schultz et al, 1997; Bosman et al, 2004; Xie and Seung, 2004; Florian, 2007; Farries and Fairhall, 2007; Baras and Meir, 2007; Legenstein et al, 2010; Frémaux et al, 2010; Frie”
Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity (2007, methodology): “This problem was also approached using other reinforcement learning methods for generic spiking neural networks (Seung, 2003; Xie & Seung, 2004).”
Computational models of reinforcement learning: the role of dopamine as a reward signal (2010, unknown): “As an alternative to STDP, Xie and Seung (2004) proposed a different learning rule based on the irregular nature of neural spiking and a reward-dependent eligibility trace.”
Neuromodulated Spike-Timing-Dependent Plasticity, and Theory of Three-Factor Learning Rules (2016, background): “With a combination of agonists for both Frontiers in Neural Circuits | www.frontiersin.org 6 January 2016 | Volume 9 | Article 85 TABLE 1 | Selection of experimental results addressing the interaction of neuromodulation and STDP. Interaction type Quantitative neuromodulation Neuromodulator timing…”
A Spiking Neural Model for Stable Reinforcement of Synapses Based on Multiple Distal Rewards (2013, methodology): “…that R-STDP can be extended to learn multiple distal rewards, using the novel ARG-STDP with STP. Fr´emaux et al. (2010) describe the R-Max plasticity rule (Xie & Seung, 2004; Pﬁster, Toyoizumi, Barber, & Gerstner, 2006; Florian, 2007), which is derived using the principle of reward maximization.”
Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of NeoHebbian Three-Factor Learning Rules (2018, background): “Theoreticians refer to such a plasticity model as a three-factor learning rule (Xie and Seung, 2004; Legenstein et al., 2008; Vasilaki et al., 2009; Frémaux et al., 2013; Frémaux and Gerstner, 2016).”
Functional Requirements for Reward-Modulated Spike-Timing-Dependent Plasticity (2010, methodology): “…by simulating two different learning rules: the R-max rule, which was theoretically designed to increase the amount of reward during learning (Xie and Seung, 2004; Pfister et al., 2006; Baras and Meir, 2007; Florian, 2007); and the R-STDP rule, which is a simple STDP rule with amplitude and…”
Frontiers in Synaptic Neuroscience Synaptic Neuroscience (unknown): “In addition to the third factor requirement, other possible solutions for plasticity induction in vivo have been proposed that are not covered in the present review (Gerstner et al., 1996; Kempter et al., 1999; Beggs, 2001; Seung, 2003; Xie and Seung, 2004).”
Motor learning with unstable neural representations. (2007, background): “Recent studies suggest how reinforcement learning algorithms can be implemented in biophysically realistic, spiking neural circuits (Fiete and Seung, 2006; Seung, 2003; Xie and Seung, 2004).”
Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot Experiment (2008, result): “Similar results could be obtained using a different learning algorithm, such as for example the biologically plausible algorithm proposed by Seung’s group [46,47], a kind of reinforcement learning.”