Brain inspired neuronal silencing mechanism to enable reliable sequence identification
This addresses the challenge of sequence identification for applications like event recognition and authentication, offering a novel approach that could impact ANN algorithms, though it appears incremental in its application to specific domains.
The paper tackles the problem of real-time sequence identification in artificial neural networks by introducing a neuronal silencing mechanism that enables feedforward networks to reliably identify sequences without feedback loops, achieving high classification performance for sequences of 10 handwritten digits with limited training examples.
Real-time sequence identification is a core use-case of artificial neural networks (ANNs), ranging from recognizing temporal events to identifying verification codes. Existing methods apply recurrent neural networks, which suffer from training difficulties; however, performing this function without feedback loops remains a challenge. Here, we present an experimental neuronal long-term plasticity mechanism for high-precision feedforward sequence identification networks (ID-nets) without feedback loops, wherein input objects have a given order and timing. This mechanism temporarily silences neurons following their recent spiking activity. Therefore, transitory objects act on different dynamically created feedforward sub-networks. ID-nets are demonstrated to reliably identify 10 handwritten digit sequences, and are generalized to deep convolutional ANNs with continuous activation nodes trained on image sequences. Counterintuitively, their classification performance, even with a limited number of training examples, is high for sequences but low for individual objects. ID-nets are also implemented for writer-dependent recognition, and suggested as a cryptographic tool for encrypted authentication. The presented mechanism opens new horizons for advanced ANN algorithms.