Someone said to an editor: "why not have a regular lighthearted column on AI topics?" The editor said: "what an excellent idea, and when will we get the first manuscript?" We go to press next week." While looking for something to give him, we stumbled on this old manuscript, written years ago (with our esteemed colleague Neil Agnew, the Duke of York). Ever had an old sock that you try to throw away, but keep finding in the bottom of a drawer?

Between Walking Dead and its spinoff, Fear the Walking Dead, AMC currently has a cable ratings juggernaut on its hands. But before the network put all its eggs in the zombie basket, it was committed to developing critical darling successors to shows like Mad Men and Breaking Bad. The would-be fill-in for the latter, Low Winter Sun, got cancelled after a single botched season. But Halt and Catch Fire, a darkly lit drama following Joe MacMillan (Lee Pace), a tortured genius businessman in the fledgling world of personal computers in 1980s Texas, rebounded from anemic early ratings to earn increasingly improbable renewals for a second and then third season. And that's when the show did something pretty remarkable: It got even better.

We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and written to, with the goal of using it for prediction. We investigate these models in the context of question answering (QA) where the long-term memory effectively acts as a (dynamic) knowledge base, and the output is a textual response. We evaluate them on a large-scale QA task, and a smaller, but more complex, toy task generated from a simulated world. In the latter, we show the reasoning power of such models by chaining multiple supporting sentences to answer questions that require understanding the intension of verbs.

In this challenge paper, we consider the importance of preferences in smart homes and assistive environments and discuss the potential application of models and algorithms developed within the computational preferences community. We suggest the value of future research collaborations.

Sparse data models, where data is assumed to be well represented as a linear combination of a few elements from a dictionary, have gained considerable attention in recent years, and their use has led to state-of-the-art results in many signal and image processing tasks. It is now well understood that the choice of the sparsity regularization term is critical in the success of such models. Based on a codelength minimization interpretation of sparse coding, and using tools from universal coding theory, we propose a framework for designing sparsity regularization terms which have theoretical and practical advantages when compared to the more standard l0 or l1 ones. The presentation of the framework and theoretical foundations is complemented with examples that show its practical advantages in image denoising, zooming and classification.

This column, like many strange things in the modern world, was conceived in an email exchange. Someone said to an editor: "why not have a regular lighthearted column on AI topics?" The editor said: "what an excellent idea, and when will we get the first manuscript?" and the first person said: "oh but I didn't volunteer;" and the editor said: "listen, buddy, I can make your life very uncomfortable if I don't get some cooperation. We go to press next week." While looking for something to give him, we stumbled on this old manuscript, written years ago (with our esteemed colleague Neil Agnew, the Duke of York). Ever had an old sock that you try to throw away, but keep finding in the bottom of a drawer? This is a bit like that. Come to think of it, so is the frame problem. Anyway, you can't make an omelette without breaking eggs, so here is our first reflection. It's a variation on an old, old story ....