Visually Grounded Interaction 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 Society , International Conference On Learning Representations , International Joint Conference On Natural Language Processing , Curran Associates , International Conference On Computational Linguistics , Proc International Conference On Machine Learning , Meeting Of The Association For Computational Linguistics , Cognitive Science Society , Association For Computational Linguistics , Meeting Of The Cognitive Science Society , International Conference On Machine Learning , Algebraic Mind , Integrating Connectionism , Cognitive Science , Rethinking Fodor , Systematicity Challenge , International Conference , Learning Representations , Proc International Conference , Machine Learning , Computational Linguistics , Visually Grounded Interaction , Empirical Methods , Natural Language Processing , Neural Information Processing Systems , Thirty Second Annual Conference ,