A novel variant of the familiar backpropagation-through-time approach to training recurrent networks is described. This algorithm is intended to be used on arbitrary recurrent networks that run continually without ever being reset to an initial state, and it is specifically designed for computationally efficient computer implementation. This algorithm can be viewed as a cross between epochwise backpropagation through time, which is not appropriate for continually running networks, and the widely used on-line gradient approximation technique of truncated backpropagation through time.

Nearest neighbor classi cation assumes locally constant class conditional probabilities. This assumption becomes invalid in high dimensions with nite samples due to the curse of dimensionality. Severe bias can be introduced under these conditions when using the nearest neighbor rule. We propose a locally adaptive nearest neighbor classi cation method to try to minimize bias. We use a Chisquared distance analysis to compute a exible metric for producing neighborhoods that are highly adaptive to query locations. Neighborhoods are elongated along less relevant feature dimensions and constricted along most in uential ones. As a result, the class conditional probabilities tend to be smoother in the modi ed neighborhoods, whereby better classi cation performance can be achieved. The e cacy of our method is validated and compared against other techniques using a variety of simulated and real world data.

Any non-associative reinforcement learning algorithm can be viewed as a method for performing function optimization through (possibly noise-corrupted) sampling of function values. We describe the results of simulations in which the optima of several deterministic functions studied by Ackley were sought using variants of REINFORCE algorithms. Some of the algorithms used here incorporated additional heuristic features resembling certain aspects of some of the algorithms used in Ackley's studies. Differing levels ofperformance were achieved by the various algorithms investigated, but a number of them performed at a level comparable to the best found in Ackley's studies on a number of the tasks, in spite of their simplicity. One of these variants, called REINFORCE/MENT, represents a novel but principled approach to reinforcement learning in nontrivial networks which incorporates an entropy maximization strategy. This was found to perform especially well on more hierarchically organized tasks.

No abstract

No abstract

Abstract. This paper presents a novel incremental algorithm that combines Q-learning, a well-known dynamicprogramming based reinforcement learning method, with the TD(A) return estimation process, which is typically used in actor-critic learning, another well-known dynamic-programming based reinforcement learning method. The parameter A is used to distribute credit throughout sequences of actions, leading to faster learning and also helping to alleviate the non-Markovian effect of coarse state-space quantization. The resulting algorithm, Q(A)-learning, thus combines some of the best features of the Q-learning and actor-critic learning paradigms. The behavior of this algorithm has been demonstrated through computer simulations.

Improving content sharing on social media platforms helps firms enhance the efficacy of their marketing campaigns. The authors study the impact of network overlap—the overlap in network connections between two users—on content sharing in directed social media platforms. The authors propose a hazards model that flexibly captures the impact of three measures of network overlap (i.e., common followees, common followers, and common mutual followers) on content sharing. Using data on content sharing from two directed social media platforms (Twitter and Digg), the authors establish that a receiver is more likely to share content from a sender with whom they share more common followees, common followers, or common mutual followers even after accounting for other measures. In addition, common followers have a higher effect than common mutual followers on the sharing propensity of the receiver. Finally, the effect of common followers and common mutual followers is positive when the content is novel but decreases, and may even become negative, when many others have already shared it. Collectively, these results have a bearing for marketers to more effectively target users for spreading content on social media platforms.

We describe an algorithm for automatic classification of idiomatic and literal expressions. Our starting point is that words in a given text segment, such as a paragraph, that are highranking representatives of a common topic of discussion are less likely to be a part of an idiomatic expression. Our additional hypothesis is that contexts in which idioms occur, typically, are more affective and therefore, we incorporate a simple analysis of the intensity of the emotions expressed by the contexts. We investigate the bag of words topic representation of one to three paragraphs containing an expression that should be classified as idiomatic or literal (a target phrase). We extract topics from paragraphs containing idioms and from paragraphs containing literals using an unsupervised clustering method, Latent Dirichlet Allocation (LDA) (Blei et al., 2003). Since idiomatic expressions exhibit the property of non-compositionality, we assume that they usually present different semantics than the words used in the local topic. We treat idioms as semantic outliers, and the identification of a semantic shift as outlier detection. Thus, this topic representation allows us to differentiate idioms from literals using local semantic contexts. Our results are encouraging.