Although deep neural networks (DNNs) have demonstrated impressive results during the last decade, they remain highly specialized tools, which are trained -often from scratch -to solve each particular task. The human brain, in contrast, significantly re-uses existing capacities when learning to solve new tasks. In the current study we explore a block-modular architecture for DNNs, which allows parts of the existing network to be re-used to solve a new task without a decrease in performance when solving the original task. We show that networks with such architectures can outperform networks trained from scratch, or perform comparably, while having to learn nearly 10 times fewer weights than the networks trained from scratch.
Birdsong learning has been consolidated as the model system of choice for exploring the biological substrates of vocal learning. In the Zebra Finch (Taeniopygia guttata), only males sing and they develop their song during a sensitive period in early life. Different experimental procedures have been used in the laboratory to train a young finch to learn a song. So far, the best method to get a faithful imitation is to keep a young bird singly with an adult male. Here we present the different characteristics of a robotic zebra finch that was developed with the goal to be used as a song tutor. The robot is morphologically similar to a real-size finch: it can produce movements and sounds contingently to the behaviours of a live bird. We present preliminary results on song imitation, and other possible applications beyond the scope of developmental song learning.
Distributed and hierarchical models of control are nowadays popular in computational modeling and robotics. In the artificial neural network literature, complex behaviors can be produced by composing elementary building blocks or motor primitives, possibly organized in a layered structure. However, it is still unknown how the brain learns and encodes multiple motor primitives, and how it rapidly reassembles, sequences and switches them by exerting cognitive control. In this paper we advance a novel proposal, a hierarchical programmable neural network architecture, based on the notion of programmability and an interpreter-programmer computational scheme. In this approach, complex (and novel) behaviors can be acquired by embedding multiple modules (motor primitives) in a single, multi-purpose neural network. This is supported by recent theories of brain functioning in which skilled behaviors can be generated by combining functional different primitives embedded in ''reusable'' areas of ''recycled'' neurons. Such neuronal substrate supports flexible cognitive control, too. Modules are seen as interpreters of behaviors having controlling input parameters, or programs that encode structures of networks to be interpreted. Flexible cognitive control can be exerted by a programmer module feeding the interpreters with appropriate input parameters, without modifying connectivity. Our results in a multiple Tmaze robotic scenario show how this computational framework provides a robust, scalable and flexible scheme that can be iterated at different hierarchical layers permitting to learn, encode and control multiple qualitatively different behaviors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.