Simulated Language Acquisition in a Biologically Realistic Model of the Brain
This work addresses the fundamental gap in neuroscience for explaining cognition, though it is incremental as it builds on established principles to simulate language learning.
The authors tackled the problem of understanding how neural spiking leads to high-level cognition by developing a biologically realistic model based on six neuroscience principles, which achieved basic language acquisition from scratch, learning semantics, syntax, and word order to generate novel sentences with modest data.
Despite tremendous progress in neuroscience, we do not have a compelling narrative for the precise way whereby the spiking of neurons in our brain results in high-level cognitive phenomena such as planning and language. We introduce a simple mathematical formulation of six basic and broadly accepted principles of neuroscience: excitatory neurons, brain areas, random synapses, Hebbian plasticity, local inhibition, and inter-area inhibition. We implement a simulated neuromorphic system based on this formalism, which is capable of basic language acquisition: Starting from a tabula rasa, the system learns, in any language, the semantics of words, their syntactic role (verb versus noun), and the word order of the language, including the ability to generate novel sentences, through the exposure to a modest number of grounded sentences in the same language. We discuss several possible extensions and implications of this result.