Abstract
Large pre-trained deep networks are the standard building blocks of modern AI applications. This raises fundamental questions about how to control their behaviour and how to make them efficiently interact with each other. The field of deep net emergent communication tackles these challenges by studying how to induce communication protocols between neural network agents, and how to include humans in the communication loop. Traditionally, this research had focussed on relatively small-scale experiments where two networks have to develop a discrete code from scratch for referential communication. However, with the rise of large pre-trained language models that can work well on many tasks, the emphasis is now shifting on how to let these models interact through a language-like channel in order to engage in more complex behaviors.
In this talk, I'll present an overview of deep emergent communication, covering various central topics from the present and recent past, as well as discussing current shortcomings and suggest future directions. The talks tries to bridge the gap between researchers wanting to develop more flexible AI systems, but also to cognitive scientists and linguists interested in the evolution of communication systems.