Role of Delay in Brain Dynamics
This work addresses the inflexibility of brain-like learning architectures for AI researchers, though it appears incremental as it builds on existing delay-based models with specific enhancements.
The study tackled the computational disadvantage of asynchronous brain dynamics due to neuronal delays by proposing the RoDiB model, which converts delays into an advantage using a network with multiple delays to generate polynomial time-series outputs, achieving accuracies comparable to tunable single-delay architectures and enhanced performance when output labels exceed input size.
Significant variations of delays among connecting neurons cause an inevitable disadvantage of asynchronous brain dynamics compared to synchronous deep learning. However, this study demonstrates that this disadvantage can be converted into a computational advantage using a network with a single output and M multiple delays between successive layers, thereby generating a polynomial time-series outputs with M. The proposed role of delay in brain dynamics (RoDiB) model, is capable of learning increasing number of classified labels using a fixed architecture, and overcomes the inflexibility of the brain to update the learning architecture using additional neurons and connections. Moreover, the achievable accuracies of the RoDiB system are comparable with those of its counterpart tunable single delay architectures with M outputs. Further, the accuracies are significantly enhanced when the number of output labels exceeds its fully connected input size. The results are mainly obtained using simulations of VGG-6 on CIFAR datasets and also include multiple label inputs. However, currently only a small fraction of the abundant number of RoDiB outputs is utilized, thereby suggesting its potential for advanced computational power yet to be discovered.