Encoding and Decoding Dynamic Sensory Signals with Recurrent Neural Networks: An Application of Conceptors to Birdsongs

  title={Encoding and Decoding Dynamic Sensory Signals with Recurrent Neural Networks: An Application of Conceptors to Birdsongs},
  author={Richard Gast and Patrick Faion and K. Standvoss and Andrea Suckro and B. Lewis and G. Pipa},
In a constantly changing environment the brain has to make sense of dynamic patterns of sensory input. These patterns can refer to stimuli with a complex and hierarchical structure which has to be inferred from the neural activity of sensory areas in the brain. Such areas were found to be locally recurrently structured as well as hierarchically organized within a given sensory domain. While there is a great body of work identifying neural representations of various sensory stimuli at different… Expand
Transfer between long-term and short-term memory using Conceptors
A recurrent neural network model of working memory combining short-term and long-term components is introduced and it is shown how standard operations on conceptors allow to combine long- term memories and describe their effect on short- term memory. Expand
Controlling Recurrent Neural Networks by Diagonal Conceptors
Sample-level sound synthesis with recurrent neural networks and conceptors
The techniques presented here represent an initial exploration of the sound synthesis potential of conceptors, demonstrating possible creative applications in sound design and Limitations of conceptor models are revealed with regards to reproduction quality and pragmatic limitations are shown. Expand


A Hierarchical Neuronal Model for Generation and Online Recognition of Birdsongs
The results indicate that the specific way birdsong is generated enables a listening bird to robustly and rapidly perceive embedded information at multiple time scales of a song. Expand
Controlling Recurrent Neural Networks by Conceptors
A mechanism of neurodynamical organization, called conceptors, is proposed, which unites nonlinear dynamics with basic principles of conceptual abstraction and logic, and helps explain how conceptual-level information processing emerges naturally and robustly in neural systems. Expand
Learning and inference in the brain
Hierarchy generative models enable the learning of empirical priors and eschew prior assumptions about the causes of sensory input that are inherent in non-hierarchical models, but are not necessary in a hierarchical context. Expand
A Hierarchy of Time-Scales and the Brain
It is suggested that cortical anatomy recapitulates the temporal hierarchy that is inherent in the dynamics of environmental states, and this anatomic-temporal hierarchy provides a comprehensive framework for understanding cortical function. Expand
They’re Playing Our Song Gene Expression and Birdsong Perception
The recent findings in the neuroethology of song perception discussed here point to important ways in which approaching the question of neural representation in songbirds has led to advances in ourExpand
Two neural streams, one voice: Pathways for theme and variation in the songbird brain
This work focuses on the central control of birdsong and review the recent discovery that zebra finch song is under dual premotor control, meaning that anatomical, physiological, and computational approaches are poised to reveal the neural mechanisms used by the brain to compose the songs of birds. Expand
The Bayesian brain: the role of uncertainty in neural coding and computation
A major challenge for neuroscientists is to test ideas for how this might be achieved in populations of neurons experimentally, and so determine whether and how neurons code information about sensory uncertainty. Expand
Birdsong and human speech: common themes and mechanisms.
Human speech and birdsong have numerous parallels, with striking similarities in how sensory experience is internalized and used to shape vocal outputs, and how learning is enhanced during a critical period of development. Expand
Birdsong Memory: A Neural Dissociation between Song Recognition and Production
The results show that tutor-song memory and a motor program for the bird's own song have separate neural representations in the songbird brain, which demonstrates that the cognitive systems of vocal production and auditory recognition memory are subserved by distinct brain regions. Expand
Distributed representation of objects in the human ventral visual pathway.
It is proposed that the functional architecture of the ventral visual pathway is not a mosaic of category-specific modules but instead is a continuous representation of information about object form that has a highly consistent and orderly topological arrangement. Expand