Modeling the Repetition-based Recovering of Acoustic and Visual Sources with Dendritic Neurons
This work addresses blind source separation for auditory and visual processing, offering a neuro-inspired model that could inform neuroscience and machine learning, but it appears incremental as it builds on known biological principles without claiming major breakthroughs.
The authors tackled the problem of blind source separation in acoustic and visual signals by proposing a biologically inspired computational model using somatodendritic neurons with Hebbian-like learning. They showed that the model's segregation capabilities mimic human performance in experimental settings with synthesized sounds and extended it to natural sounds and images.
In natural auditory environments, acoustic signals originate from the temporal superimposition of different sound sources. The problem of inferring individual sources from ambiguous mixtures of sounds is known as blind source decomposition. Experiments on humans have demonstrated that the auditory system can identify sound sources as repeating patterns embedded in the acoustic input. Source repetition produces temporal regularities that can be detected and used for segregation. Specifically, listeners can identify sounds occurring more than once across different mixtures, but not sounds heard only in a single mixture. However, whether such a behaviour can be computationally modelled has not yet been explored. Here, we propose a biologically inspired computational model to perform blind source separation on sequences of mixtures of acoustic stimuli. Our method relies on a somatodendritic neuron model trained with a Hebbian-like learning rule which can detect spatio-temporal patterns recurring in synaptic inputs. We show that the segregation capabilities of our model are reminiscent of the features of human performance in a variety of experimental settings involving synthesized sounds with naturalistic properties. Furthermore, we extend the study to investigate the properties of segregation on task settings not yet explored with human subjects, namely natural sounds and images. Overall, our work suggests that somatodendritic neuron models offer a promising neuro-inspired learning strategy to account for the characteristics of the brain segregation capabilities as well as to make predictions on yet untested experimental settings.