Gustavo Bondoni

Frances Pauli

Willow Croft

Louis Evans

Mary E. Lowd

S. Park

Daniel Lowd

James L. Steele

Jude-Marie Green

Huskyteer

Mark Slauter

Daniel R. Robichaud

Su Haddrell

K.C. Shaw

Kittara Foxworthy

Nenekiri Bookwyrm

Kary M. Jomb

Koji A. Dae

Allison Thai

The ocean is vast and mostly uncharted. In these nineteen stories, authors imagined some of what might be happening under the surface of the waves. Or in some cases, on dry land when water-dwelling creatures pull themselves out of the ocean into a world of furry and feathered animals that they struggle to relate to. Dance in a cuttlefish rave. Join a shark as she attempts to build an airship. Attend an underwater ball thrown by crab-aliens. Watch the last Asian dragon perform in a whale and dolphin circus. Listen to a ballad sung by lobsters and whelks. Hunt for a killer shark with two waring ocean races under a tense truce. Ride squid with the Hell’s Anglerfish seal gang. But above all, don’t forget to bring a wet suit! Featuring stories by Louis Evans, Allison Thai, Koji A. Dae, Gustavo Bondoni, Nenekiri Bookwyrm, Kary M. Jomb, Huskyteer, Kittara Foxworthy, Daniel Lowd, K.C. Shaw, Willow Croft, Mary E. Lowd, James L. Steele, Su Haddrell, Daniel R. Robichaud, Frances Pauli, Mark Slauter, Jude-Marie Green, and S. Park. Scroll up and grab a copy today!

An Ocean Anthology

Shark Week

Pedro Domingos

Most subfields of computer science have an interface layer via which applications communicate with the infrastructure, and this is key to their success (e.g., the Internet in networking, the relational model in databases, etc.). So far this interface layer has been missing in AI. First-order logic and probabilistic graphical models each have some of the necessary features, but a viable interface layer requires combining both. Markov logic is a powerful new language that accomplishes this by attaching weights to first-order formulas and treating them as templates for features of Markov random fields. Most statistical models in wide use are special cases of Markov logic, and first-order logic is its infinite-weight limit. Inference algorithms for Markov logic combine ideas from satisfiability, Markov chain Monte Carlo, belief propagation, and resolution. Learning algorithms make use of conditional likelihood, convex optimization, and inductive logic programming. Markov logic has been successfully applied to problems in information extraction and integration, natural language processing, robot mapping, social networks, computational biology, and others, and is the basis of the open-source Alchemy system. Table of Contents: Introduction / Markov Logic / Inference / Learning / Extensions / Applications / Conclusion

An Interface Layer for Artificial Intelligence

Markov Logic

Daniel Lowd

About

Books

Join the club