Limits...
Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns.

Yu Q, Tang H, Tan KC, Li H - PLoS ONE (2013)

Bottom Line: The PSD rule is further validated on a practical example of an optical character recognition problem.The results again show that it can achieve a good recognition performance with a proper encoding.Finally, a detailed discussion is provided about the PSD rule and several related algorithms including tempotron, SPAN, Chronotron and ReSuMe.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore.

ABSTRACT
A new learning rule (Precise-Spike-Driven (PSD) Synaptic Plasticity) is proposed for processing and memorizing spatiotemporal patterns. PSD is a supervised learning rule that is analytically derived from the traditional Widrow-Hoff rule and can be used to train neurons to associate an input spatiotemporal spike pattern with a desired spike train. Synaptic adaptation is driven by the error between the desired and the actual output spikes, with positive errors causing long-term potentiation and negative errors causing long-term depression. The amount of modification is proportional to an eligibility trace that is triggered by afferent spikes. The PSD rule is both computationally efficient and biologically plausible. The properties of this learning rule are investigated extensively through experimental simulations, including its learning performance, its generality to different neuron models, its robustness against noisy conditions, its memory capacity, and the effects of its learning parameters. Experimental results show that the PSD rule is capable of spatiotemporal pattern classification, and can even outperform a well studied benchmark algorithm with the proposed relative confidence criterion. The PSD rule is further validated on a practical example of an optical character recognition problem. The results again show that it can achieve a good recognition performance with a proper encoding. Finally, a detailed discussion is provided about the PSD rule and several related algorithms including tempotron, SPAN, Chronotron and ReSuMe.

Show MeSH

Related in: MedlinePlus

Effects of  and  on the learning.The neuron is trained in a maximum number of 500 epochs to correctly memorize a set of 10 spike patterns. The average learning epochs are recorded for each pair of  and . The reaching points of 500 epochs are regarded as failure of the learning. The left shows an exhaustive investigation of a wide range of  and , and the data are averaged over 30 runs. A small number of learning parameters are examined in the right figure, and the data are averaged over 100 runs.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3818323&req=5

pone-0078318-g011: Effects of and on the learning.The neuron is trained in a maximum number of 500 epochs to correctly memorize a set of 10 spike patterns. The average learning epochs are recorded for each pair of and . The reaching points of 500 epochs are regarded as failure of the learning. The left shows an exhaustive investigation of a wide range of and , and the data are averaged over 30 runs. A small number of learning parameters are examined in the right figure, and the data are averaged over 100 runs.

Mentions: We further conduct another experiment to evaluate the effects of both and on the learning. In this experiment, a single LIF neuron with afferent neurons is considered. The neuron is trained to correctly memorize a set of 10 spike patterns randomly generated over a time window of . The neuron is trained in a maximum number of 500 epochs to correctly associate all these patterns with a desired spike train of [, , , ] . We denote that a pattern is correctly memorized if the distance between the output spike train and the desired spike train is below . If the number of training epochs exceeds 500, we regard it as a failure. We conduct an exhaustive search over a wide range of and . Fig. 11 shows how and jointly affect the learning performance, which can be used as a guidance to select the learning parameters. With a fixed , a larger results in a faster learning speed (shown in Fig. 11, right panel), but when is increased above a critical value (e.g., 0.1 for in our experiments), the learning will slow down or even fail. For small , a larger leads to a faster learning, however, for large , a larger has the opposite effect. As a consequence, when is set in a suitable range (e.g., [5], [15]), a wide range of can result in a fast learning speed (e.g., below 100 epochs).


Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns.

Yu Q, Tang H, Tan KC, Li H - PLoS ONE (2013)

Effects of  and  on the learning.The neuron is trained in a maximum number of 500 epochs to correctly memorize a set of 10 spike patterns. The average learning epochs are recorded for each pair of  and . The reaching points of 500 epochs are regarded as failure of the learning. The left shows an exhaustive investigation of a wide range of  and , and the data are averaged over 30 runs. A small number of learning parameters are examined in the right figure, and the data are averaged over 100 runs.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3818323&req=5

pone-0078318-g011: Effects of and on the learning.The neuron is trained in a maximum number of 500 epochs to correctly memorize a set of 10 spike patterns. The average learning epochs are recorded for each pair of and . The reaching points of 500 epochs are regarded as failure of the learning. The left shows an exhaustive investigation of a wide range of and , and the data are averaged over 30 runs. A small number of learning parameters are examined in the right figure, and the data are averaged over 100 runs.
Mentions: We further conduct another experiment to evaluate the effects of both and on the learning. In this experiment, a single LIF neuron with afferent neurons is considered. The neuron is trained to correctly memorize a set of 10 spike patterns randomly generated over a time window of . The neuron is trained in a maximum number of 500 epochs to correctly associate all these patterns with a desired spike train of [, , , ] . We denote that a pattern is correctly memorized if the distance between the output spike train and the desired spike train is below . If the number of training epochs exceeds 500, we regard it as a failure. We conduct an exhaustive search over a wide range of and . Fig. 11 shows how and jointly affect the learning performance, which can be used as a guidance to select the learning parameters. With a fixed , a larger results in a faster learning speed (shown in Fig. 11, right panel), but when is increased above a critical value (e.g., 0.1 for in our experiments), the learning will slow down or even fail. For small , a larger leads to a faster learning, however, for large , a larger has the opposite effect. As a consequence, when is set in a suitable range (e.g., [5], [15]), a wide range of can result in a fast learning speed (e.g., below 100 epochs).

Bottom Line: The PSD rule is further validated on a practical example of an optical character recognition problem.The results again show that it can achieve a good recognition performance with a proper encoding.Finally, a detailed discussion is provided about the PSD rule and several related algorithms including tempotron, SPAN, Chronotron and ReSuMe.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore.

ABSTRACT
A new learning rule (Precise-Spike-Driven (PSD) Synaptic Plasticity) is proposed for processing and memorizing spatiotemporal patterns. PSD is a supervised learning rule that is analytically derived from the traditional Widrow-Hoff rule and can be used to train neurons to associate an input spatiotemporal spike pattern with a desired spike train. Synaptic adaptation is driven by the error between the desired and the actual output spikes, with positive errors causing long-term potentiation and negative errors causing long-term depression. The amount of modification is proportional to an eligibility trace that is triggered by afferent spikes. The PSD rule is both computationally efficient and biologically plausible. The properties of this learning rule are investigated extensively through experimental simulations, including its learning performance, its generality to different neuron models, its robustness against noisy conditions, its memory capacity, and the effects of its learning parameters. Experimental results show that the PSD rule is capable of spatiotemporal pattern classification, and can even outperform a well studied benchmark algorithm with the proposed relative confidence criterion. The PSD rule is further validated on a practical example of an optical character recognition problem. The results again show that it can achieve a good recognition performance with a proper encoding. Finally, a detailed discussion is provided about the PSD rule and several related algorithms including tempotron, SPAN, Chronotron and ReSuMe.

Show MeSH
Related in: MedlinePlus