Supervised Learning in Spiking Neural Networks
In supervised learning, the learner is presented, for a set of inputs, the desired (target) outputs corresponding to the given inputs. The learner should then learn to predict the correct output for any valid input. Spiking neural networks are neural models, where neurons transmit information through each other by firing action potentials, or spikes, as real neurons do. Supervised learning in spiking neural networks refers to how spiking neurons modify their parameters in order to be able to reproduce and generalize the input–output associations that they were taught in the past.
Humans and animals learn through coordinated changes in the properties of their neural systems. In neural models, this is simulated by changes of the parameters of these models, such as synaptic efficacies. The study of learning in artificial neural networksfocuses on the rules that govern these changes such that they...
- Bohte, S. M., Poutré, H. L., & Kok, J. N. (2002). SpikeProp: error-backpropagation for networks of spiking neurons. Neurocomputing, 48, 17–37.Google Scholar
- Florian, R. V. (2011). The chronotron: a neuron that learns to fire temporally-precise spike patterns. Nature Precedings. http://precedings.nature.com/documents/5190/version/3.
- Gütig, R., & Sompolinsky, H. (2006). The tempotron: a neuron that learns spike timing-based decisions. Nature Neuroscience, 9(3), 420–428.Google Scholar
- Kasiński, A., & Ponulak, F. (2006). Comparison of supervised learning methods for spike time coding in spiking neural networks. International Journal of Applied Mathematics and Computer Science, 16(1), 101–113.Google Scholar
- Pfister, J.-P., Toyoizumi, T., Barber, D., & Gerstner, W. (2006). Optimal spike timing-dependent plasticity for precise action potential firing in supervised learning. Neural Computation, 18(6), 1318–1348.Google Scholar
- Ponulak, F., & Kasiński, A. (2010). Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural Computation, 22(2), 467–510.Google Scholar