Sequence learning with hidden units in spiking neural networks

45 citations recorded by the source corpus.

How researchers see this paper

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

Towards Transparent AI Systems: Interpreting Visual Question Answering Models (2016, background): “, 2015) machine translation (Brea et al., 2011; Sutskever et al., 2014) and speech recognition (Hinton et al.”
Bayesian Computation Emerges in Generic Cortical Microcircuits through Spike-Timing-Dependent Plasticity (2013, methodology): “An alternative approach to implement the learning of generative probabilistic models in spiking neuronal networks is given in [93,94].”
Stochastic variational learning in recurrent spiking networks (2014, methodology): “For instance, the learning rule proposed in Brea et al. (2011) also falls into this category.”
Matching Recall and Storage in Sequence Learning with Spiking Neural Networks (2013, methodology): “This stands in contrast to our previous work (Brea et al., 2011), where the learning rule is identical for both types of synapses. In the absence of hidden neurons the learning rule is identical to the one proposed in Pfister et al. (2006) for feedforward networks.”
Neuromodulated Spike-Timing-Dependent Plasticity, and Theory of Three-Factor Learning Rules (2016, background): “…plasticity rules that could potentially implement learning in neural circuits so that a formal neural network memorizes novel stimuli or sequences, (Brea et al., 2011; Rezende et al., 2011; Brea et al., 2013; Rezende and Gerstner, 2014) or learns rewarding skills (Xie and Seung, 2004; Pfister et…”