Integrating Connectionism News Today : Breaking News, Live Updates & Top Stories | Vimarsana

The power of human language and thought arises from systematic compositionality—the algebraic ability to understand and produce novel combinations from known components. Fodor and Pylyshyn1 famously argued that artificial neural networks lack this capacity and are therefore not viable models of the mind. Neural networks have advanced considerably in the years since, yet the systematicity challenge persists. Here we successfully address Fodor and Pylyshyn’s challenge by providing evidence that neural networks can achieve human-like systematicity when optimized for their compositional skills. To do so, we introduce the meta-learning for compositionality (MLC) approach for guiding training through a dynamic stream of compositional tasks. To compare humans and machines, we conducted human behavioural experiments using an instruction learning paradigm. After considering seven different models, we found that, in contrast to perfectly systematic but rigid probabilistic sy

Conference of the cognitive science societyInternational conference on learning representationsInternational joint conference on natural language processingCurran associatesInternational conference on computational linguisticsProc international conference on machine learningMeeting of the association for computational linguisticsCognitive science societyAssociation for computational linguisticsMeeting of the cognitive science societyInternational conference on machine learningAlgebraic mindIntegrating connectionismCognitive scienceRethinking fodorSystematicity challenge