Backpropagation learning algorithm, the workhorse of modern artificial intelligence, is notoriously difficult to implement in physical neural networks. Equilibrium Propagation (EP) is an alternative with comparable efficiency and strong potential for in-situ training. We extend EP learning to both discrete and continuous complex-valued wave systems. In contrast to previous EP implementations, our scheme is valid in the weakly dissipative regime, and readily applicable to a wide range of physical settings, even without well defined nodes, where trainable inter-node connections can be replaced by trainable local potential. We test the method in driven-dissipative exciton-polariton condensates governed by generalized Gross-Pitaevskii dynamics. Numerical studies on standard benchmarks, including a simple logical task and handwritten-digit recognition, demonstrate stable convergence, establishing a practical route to in-situ learning in physical systems in which system control is restricted to local parameters.

I've done a lot of writing and research recently about the bright future of AI: that it'll be able to analyze human emotions, understand social nuances, conduct medical treatments and diagnoses that overshadow the best human physicians, and in general make many human workers redundant and unnecessary. I still stand behind all of these forecasts, but they are meant for the long term – twenty or thirty years into the future. And so, the question that many people want answered is about the situation at the present. Luckily, DARPA has decided to provide an answer to that question. DARPA is one of the most interesting US agencies.

In this chapter we discuss soft concept analysis, a study which identifies an enriched notion of "conceptual scale" as developed in formal concept analysis with an enriched notion of "linguistic variable" as discussed in fuzzy logic. The identification "enriched conceptual scale" = "enriched linguistic variable" was made in a previous paper (Enriched interpretation, Robert E. Kent). In this chapter we offer further arguments for the importance of this identification by discussing the philosophy, spirit, and practical application of conceptual scaling to the discovery, conceptual analysis, interpretation, and categorization of networked information resources. We argue that a linguistic variable, which has been defined at just the right generalization of valuated categories, provides a natural definition for the process of soft conceptual scaling. This enrichment using valuated categories models the relation of indiscernability, a notion of central importance in rough set theory. At a more fundamental level for soft concept analysis, it also models the derivation of formal concepts, a process of central importance in formal concept analysis. Soft concept analysis is synonymous with enriched concept analysis. From one viewpoint, the study of soft concept analysis that is initiated here extends formal concept analysis to soft computational structures. From another viewpoint, soft concept analysis provides a natural foundation for soft computation by unifying and explaining notions from soft computation in terms of suitably generalized notions from formal concept analysis, rough set theory and fuzzy set theory.

Researchers will hold the next wave of artificial intelligences (AI) to the same standard as high school math students everywhere: no credit if you don't show your work. On Friday, Defense Advanced Research Projects Agency (DARPA), a Department of Defense (DoD) agency focused on breakthrough technologies, announced its Artificial Intelligence Exploration (AIE) program. This program will streamline the agency's process for funding AI research and development with a focus on third wave AI technologies -- the kinds that can understand and explain how they arrived at an answer. Most of the AI in use today falls under the category of first wave. These AIs follow clear, logical rules (think: chess-playing AIs).

I've done a lot of writing and research recently about the bright future of AI: that it'll be able to analyze human emotions, understand social nuances, conduct medical treatments and diagnoses that overshadow the best human physicians, and in general make many human workers redundant and unnecessary. I still stand behind all of these forecasts, but they are meant for the long term – twenty or thirty years into the future. And so, the question that many people want answered is about the situation at the present. Luckily, DARPA has decided to provide an answer to that question. DARPA is one of the most interesting US agencies.