Adaptive Feedback Inhibition Improves Pattern Discrimination Learning

Abstract

Neural network models for unsupervised pattern recognition learning are challenged when the difference between the patterns of the training set is small. The standard neural network architecture for pattern recognition learning consists of adaptive forward connections and lateral inhibition, which provides competition between output neurons. We propose an additional adaptive inhibitory feedback mechanism, to emphasize the difference between training patterns and improve learning. We present an implementation of adaptive feedback inhibition for spiking neural network models, based on spike timing dependent plasticity (STDP). When the inhibitory feedback connections are adjusted using an anti-Hebbian learning rule, feedback inhibition suppresses the redundant activity of input units which code the overlap between similar stimuli. We show, that learning speed and pattern discriminatability can be increased by adding this mechanism to the standard architecture.

Using Spatiotemporal Correlations to Learn Topographic Maps for Invariant Object Recognition

“…We used a Hebbian learning rule similar to that proposed by Gerstner et al (1996), Saam and Eckhorn (2000), and Michler et al (2006). The synaptic weights w m, n of the forward connections from layer E0 to E1 are adapted according to the following equations…”