May 6, 2019

2786 words 14 mins read

Paper Group ANR 367

Simulating user learning in authoritative technology adoption: An agent based model for council-led smart meter deployment planning in the UK. Real-Time Video Highlights for Yahoo Esports. Boosting as a kernel-based method. Learning Operations on a Stack with Neural Turing Machines. Instance-aware Image and Sentence Matching with Selective Multimod …

Simulating user learning in authoritative technology adoption: An agent based model for council-led smart meter deployment planning in the UK


Title	Simulating user learning in authoritative technology adoption: An agent based model for council-led smart meter deployment planning in the UK
Authors	Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin
Abstract	How do technology users effectively transit from having zero knowledge about a technology to making the best use of it after an authoritative technology adoption? This post-adoption user learning has received little research attention in technology management literature. In this paper we investigate user learning in authoritative technology adoption by developing an agent-based model using the case of council-led smart meter deployment in the UK City of Leeds. Energy consumers gain experience of using smart meters based on the learning curve in behavioural learning. With the agent-based model we carry out experiments to validate the model and test different energy interventions that local authorities can use to facilitate energy consumers’ learning and maintain their continuous use of the technology. Our results show that the easier energy consumers become experienced, the more energy-efficient they are and the more energy saving they can achieve; encouraging energy consumers’ contacts via various informational means can facilitate their learning; and developing and maintaining their positive attitude toward smart metering can enable them to use the technology continuously. Contributions and energy policy/intervention implications are discussed in this paper.
Tasks
Published	2016-07-20
URL	http://arxiv.org/abs/1607.05912v1
PDF	http://arxiv.org/pdf/1607.05912v1.pdf
PWC	https://paperswithcode.com/paper/simulating-user-learning-in-authoritative
Repo
Framework

Real-Time Video Highlights for Yahoo Esports


Title	Real-Time Video Highlights for Yahoo Esports
Authors	Yale Song
Abstract	Esports has gained global popularity in recent years and several companies have started offering live streaming videos of esports games and events. This creates opportunities to develop large scale video understanding systems for new product features and services. We present a technique for detecting highlights from live streaming videos of esports game matches. Most video games use pronounced visual effects to emphasize highlight moments; we use CNNs to learn convolution filters of those visual effects for detecting highlights. We propose a cascaded prediction approach that allows us to deal with several challenges arise in a production environment. We demonstrate our technique on our new dataset of three popular game titles, Heroes of the Storm, League of Legends, and Dota 2. Our technique achieves 18 FPS on a single CPU with an average precision of up to 83.18%. Part of our technique is currently deployed in production on Yahoo Esports.
Tasks	Dota 2, League of Legends, Video Understanding
Published	2016-11-27
URL	http://arxiv.org/abs/1611.08780v1
PDF	http://arxiv.org/pdf/1611.08780v1.pdf
PWC	https://paperswithcode.com/paper/real-time-video-highlights-for-yahoo-esports
Repo
Framework

Boosting as a kernel-based method


Title	Boosting as a kernel-based method
Authors	Aleksandr Y. Aravkin, Giulio Bottegal, Gianluigi Pillonetto
Abstract	Boosting combines weak (biased) learners to obtain effective learning algorithms for classification and prediction. In this paper, we show a connection between boosting and kernel-based methods, highlighting both theoretical and practical applications. In the context of $\ell_2$ boosting, we start with a weak linear learner defined by a kernel $K$. We show that boosting with this learner is equivalent to estimation with a special {\it boosting kernel} that depends on $K$, as well as on the regression matrix, noise variance, and hyperparameters. The number of boosting iterations is modeled as a continuous hyperparameter, and fit along with other parameters using standard techniques. We then generalize the boosting kernel to a broad new class of boosting approaches for more general weak learners, including those based on the $\ell_1$, hinge and Vapnik losses. The approach allows fast hyperparameter tuning for this general class, and has a wide range of applications, including robust regression and classification. We illustrate some of these applications with numerical examples on synthetic and real data.
Tasks
Published	2016-08-08
URL	http://arxiv.org/abs/1608.02485v2
PDF	http://arxiv.org/pdf/1608.02485v2.pdf
PWC	https://paperswithcode.com/paper/boosting-as-a-kernel-based-method
Repo
Framework

Learning Operations on a Stack with Neural Turing Machines


Title	Learning Operations on a Stack with Neural Turing Machines
Authors	Tristan Deleu, Joseph Dureau
Abstract	Multiple extensions of Recurrent Neural Networks (RNNs) have been proposed recently to address the difficulty of storing information over long time periods. In this paper, we experiment with the capacity of Neural Turing Machines (NTMs) to deal with these long-term dependencies on well-balanced strings of parentheses. We show that not only does the NTM emulate a stack with its heads and learn an algorithm to recognize such words, but it is also capable of strongly generalizing to much longer sequences.
Tasks
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00827v1
PDF	http://arxiv.org/pdf/1612.00827v1.pdf
PWC	https://paperswithcode.com/paper/learning-operations-on-a-stack-with-neural
Repo
Framework

Instance-aware Image and Sentence Matching with Selective Multimodal LSTM


Title	Instance-aware Image and Sentence Matching with Selective Multimodal LSTM
Authors	Yan Huang, Wei Wang, Liang Wang
Abstract	Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between pairwise instances of image (objects) and sentence (words), we propose a selective multimodal Long Short-Term Memory network (sm-LSTM) for instance-aware image and sentence matching. The sm-LSTM includes a multimodal context-modulated attention scheme at each timestep that can selectively attend to a pair of instances of image and sentence, by predicting pairwise instance-aware saliency maps for image and sentence. For selected pairwise instances, their representations are obtained based on the predicted saliency maps, and then compared to measure their local similarity. By similarly measuring multiple local similarities within a few timesteps, the sm-LSTM sequentially aggregates them with hidden states to obtain a final matching score as the desired global similarity. Extensive experiments show that our model can well match image and sentence with complex content, and achieve the state-of-the-art results on two public benchmark datasets.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2016-11-17
URL	http://arxiv.org/abs/1611.05588v1
PDF	http://arxiv.org/pdf/1611.05588v1.pdf
PWC	https://paperswithcode.com/paper/instance-aware-image-and-sentence-matching
Repo
Framework

AttSum: Joint Learning of Focusing and Summarization with Neural Attention


Title	AttSum: Joint Learning of Focusing and Summarization with Neural Attention
Authors	Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei, Yanran Li
Abstract	Query relevance ranking and sentence saliency ranking are the two main tasks in extractive query-focused summarization. Previous supervised summarization systems often perform the two tasks in isolation. However, since reference summaries are the trade-off between relevance and saliency, using them as supervision, neither of the two rankers could be trained well. This paper proposes a novel summarization system called AttSum, which tackles the two tasks jointly. It automatically learns distributed representations for sentences as well as the document cluster. Meanwhile, it applies the attention mechanism to simulate the attentive reading of human behavior when a query is given. Extensive experiments are conducted on DUC query-focused summarization benchmark datasets. Without using any hand-crafted features, AttSum achieves competitive performance. It is also observed that the sentences recognized to focus on the query indeed meet the query need.
Tasks
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00125v2
PDF	http://arxiv.org/pdf/1604.00125v2.pdf
PWC	https://paperswithcode.com/paper/attsum-joint-learning-of-focusing-and
Repo
Framework

Context Discovery for Model Learning in Partially Observable Environments


Title	Context Discovery for Model Learning in Partially Observable Environments
Authors	Nikolas J. Hemion
Abstract	The ability to learn a model is essential for the success of autonomous agents. Unfortunately, learning a model is difficult in partially observable environments, where latent environmental factors influence what the agent observes. In the absence of a supervisory training signal, autonomous agents therefore require a mechanism to autonomously discover these environmental factors, or sensorimotor contexts. This paper presents a method to discover sensorimotor contexts in partially observable environments, by constructing a hierarchical transition model. The method is evaluated in a simulation experiment, in which a robot learns that different rooms are characterized by different objects that are found in them.
Tasks
Published	2016-08-02
URL	http://arxiv.org/abs/1608.00737v1
PDF	http://arxiv.org/pdf/1608.00737v1.pdf
PWC	https://paperswithcode.com/paper/context-discovery-for-model-learning-in
Repo
Framework

LFADS - Latent Factor Analysis via Dynamical Systems


Title	LFADS - Latent Factor Analysis via Dynamical Systems
Authors	David Sussillo, Rafal Jozefowicz, L. F. Abbott, Chethan Pandarinath
Abstract	Neuroscience is experiencing a data revolution in which many hundreds or thousands of neurons are recorded simultaneously. Currently, there is little consensus on how such data should be analyzed. Here we introduce LFADS (Latent Factor Analysis via Dynamical Systems), a method to infer latent dynamics from simultaneously recorded, single-trial, high-dimensional neural spiking data. LFADS is a sequential model based on a variational auto-encoder. By making a dynamical systems hypothesis regarding the generation of the observed data, LFADS reduces observed spiking to a set of low-dimensional temporal factors, per-trial initial conditions, and inferred inputs. We compare LFADS to existing methods on synthetic data and show that it significantly out-performs them in inferring neural firing rates and latent dynamics.
Tasks
Published	2016-08-22
URL	http://arxiv.org/abs/1608.06315v1
PDF	http://arxiv.org/pdf/1608.06315v1.pdf
PWC	https://paperswithcode.com/paper/lfads-latent-factor-analysis-via-dynamical
Repo
Framework

Verifying Heaps’ law using Google Books Ngram data


Title	Verifying Heaps’ law using Google Books Ngram data
Authors	Vladimir V. Bochkarev, Eduard Yu. Lerner, Anna V. Shevlyakova
Abstract	This article is devoted to the verification of the empirical Heaps law in European languages using Google Books Ngram corpus data. The connection between word distribution frequency and expected dependence of individual word number on text size is analysed in terms of a simple probability model of text generation. It is shown that the Heaps exponent varies significantly within characteristic time intervals of 60-100 years.
Tasks	Text Generation
Published	2016-12-29
URL	http://arxiv.org/abs/1612.09213v1
PDF	http://arxiv.org/pdf/1612.09213v1.pdf
PWC	https://paperswithcode.com/paper/verifying-heaps-law-using-google-books-ngram
Repo
Framework

Models of retrieval in sentence comprehension: A computational evaluation using Bayesian hierarchical modeling


Title	Models of retrieval in sentence comprehension: A computational evaluation using Bayesian hierarchical modeling
Authors	Bruno Nicenboim, Shravan Vasishth
Abstract	Research on interference has provided evidence that the formation of dependencies between non-adjacent words relies on a cue-based retrieval mechanism. Two different models can account for one of the main predictions of interference, i.e., a slowdown at a retrieval site, when several items share a feature associated with a retrieval cue: Lewis and Vasishth’s (2005) activation-based model and McElree’s (2000) direct access model. Even though these two models have been used almost interchangeably, they are based on different assumptions and predict differences in the relationship between reading times and response accuracy. The activation-based model follows the assumptions of ACT-R, and its retrieval process behaves as a lognormal race between accumulators of evidence with a single variance. Under this model, accuracy of the retrieval is determined by the winner of the race and retrieval time by its rate of accumulation. In contrast, the direct access model assumes a model of memory where only the probability of retrieval varies between items; in this model, differences in latencies are a by-product of the possibility and repairing incorrect retrievals. We implemented both models in a Bayesian hierarchical framework in order to evaluate them and compare them. We show that some aspects of the data are better fit under the direct access model than under the activation-based model. We suggest that this finding does not rule out the possibility that retrieval may be behaving as a race model with assumptions that follow less closely the ones from the ACT-R framework. We show that by introducing a modification of the activation model, i.e, by assuming that the accumulation of evidence for retrieval of incorrect items is not only slower but noisier (i.e., different variances for the correct and incorrect items), the model can provide a fit as good as the one of the direct access model.
Tasks
Published	2016-12-13
URL	http://arxiv.org/abs/1612.04174v2
PDF	http://arxiv.org/pdf/1612.04174v2.pdf
PWC	https://paperswithcode.com/paper/models-of-retrieval-in-sentence-comprehension
Repo
Framework

GAL: A Global-Attributes Assisted Labeling System for Outdoor Scenes


Title	GAL: A Global-Attributes Assisted Labeling System for Outdoor Scenes
Authors	Yuzhuo Ren, Chen Chen, Shangwen Li, C. -C. Jay Kuo
Abstract	An approach that extracts global attributes from outdoor images to facilitate geometric layout labeling is investigated in this work. The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes. First, by following a classical method, we use local features to provide initial labels for all super-pixels. Then, we develop a set of techniques to extract global attributes from 2D outdoor images. They include sky lines, ground lines, vanishing lines, etc. Finally, we propose the GAL system that integrates global attributes in the conditional random field (CRF) framework to improve initial labels so as to offer a more robust labeling result. The performance of the proposed GAL system is demonstrated and benchmarked with several state-of-the-art algorithms against a popular outdoor scene layout dataset.
Tasks
Published	2016-04-03
URL	http://arxiv.org/abs/1604.00606v1
PDF	http://arxiv.org/pdf/1604.00606v1.pdf
PWC	https://paperswithcode.com/paper/gal-a-global-attributes-assisted-labeling
Repo
Framework

An Approach for Parallel Genetic Algorithms in the Cloud using Software Containers


Title	An Approach for Parallel Genetic Algorithms in the Cloud using Software Containers
Authors	Pasquale Salza, Filomena Ferrucci
Abstract	Genetic Algorithms (GAs) are a powerful technique to address hard optimisation problems. However, scalability issues might prevent them from being applied to real-world problems. Exploiting parallel GAs in the cloud might be an affordable approach to get time efficient solutions that benefit of the appealing features of the cloud, such as scalability, reliability, fault-tolerance and cost-effectiveness. Nevertheless, distributed computation is very prone to cause considerable overhead for communication and making GAs distributed in an on-demand fashion is not trivial. Aiming to keep under control the communication overhead and support GAs developers in the construction and deployment of parallel GAs in the cloud, in this paper we propose an approach to distribute GAs using the global parallelisation model, exploiting software containers and their cloud orchestration. We also devised a conceptual workflow covering each cloud GAs distribution phase, from resources allocation to actual deployment and execution, in a DevOps fashion.
Tasks
Published	2016-06-22
URL	http://arxiv.org/abs/1606.06961v1
PDF	http://arxiv.org/pdf/1606.06961v1.pdf
PWC	https://paperswithcode.com/paper/an-approach-for-parallel-genetic-algorithms
Repo
Framework

TheanoLM - An Extensible Toolkit for Neural Network Language Modeling


Title	TheanoLM - An Extensible Toolkit for Neural Network Language Modeling
Authors	Seppo Enarvi, Mikko Kurimo
Abstract	We present a new tool for training neural network language models (NNLMs), scoring sentences, and generating text. The tool has been written using Python library Theano, which allows researcher to easily extend it and tune any aspect of the training process. Regardless of the flexibility, Theano is able to generate extremely fast native code that can utilize a GPU or multiple CPU cores in order to parallelize the heavy numerical computations. The tool has been evaluated in difficult Finnish and English conversational speech recognition tasks, and significant improvement was obtained over our best back-off n-gram models. The results that we obtained in the Finnish task were compared to those from existing RNNLM and RWTHLM toolkits, and found to be as good or better, while training times were an order of magnitude shorter.
Tasks	English Conversational Speech Recognition, Language Modelling, Speech Recognition
Published	2016-05-03
URL	http://arxiv.org/abs/1605.00942v2
PDF	http://arxiv.org/pdf/1605.00942v2.pdf
PWC	https://paperswithcode.com/paper/theanolm-an-extensible-toolkit-for-neural
Repo
Framework

Cross-Lingual Syntactic Transfer with Limited Resources


Title	Cross-Lingual Syntactic Transfer with Limited Resources
Authors	Mohammad Sadegh Rasooli, Michael Collins
Abstract	We describe a simple but effective method for cross-lingual syntactic transfer of dependency parsers, in the scenario where a large amount of translation data is not available. The method makes use of three steps: 1) a method for deriving cross-lingual word clusters, which can then be used in a multilingual parser; 2) a method for transferring lexical information from a target language to source language treebanks; 3) a method for integrating these steps with the density-driven annotation projection method of Rasooli and Collins (2015). Experiments show improvements over the state-of-the-art in several languages used in previous work, in a setting where the only source of translation data is the Bible, a considerably smaller corpus than the Europarl corpus used in previous work. Results using the Europarl corpus as a source of translation data show additional improvements over the results of Rasooli and Collins (2015). We conclude with results on 38 datasets from the Universal Dependencies corpora.
Tasks
Published	2016-10-19
URL	http://arxiv.org/abs/1610.06227v2
PDF	http://arxiv.org/pdf/1610.06227v2.pdf
PWC	https://paperswithcode.com/paper/cross-lingual-syntactic-transfer-with-limited
Repo
Framework

Graph Clustering Bandits for Recommendation


Title	Graph Clustering Bandits for Recommendation
Authors	Shuai Li, Claudio Gentile, Alexandros Karatzoglou
Abstract	We investigate an efficient context-dependent clustering technique for recommender systems based on exploration-exploitation strategies through multi-armed bandits over multiple users. Our algorithm dynamically groups users based on their observed behavioral similarity during a sequence of logged activities. In doing so, the algorithm reacts to the currently served user by shaping clusters around him/her but, at the same time, it explores the generation of clusters over users which are not currently engaged. We motivate the effectiveness of this clustering policy, and provide an extensive empirical analysis on real-world datasets, showing scalability and improved prediction performance over state-of-the-art methods for sequential clustering of users in multi-armed bandit scenarios.
Tasks	Graph Clustering, Multi-Armed Bandits, Recommendation Systems
Published	2016-05-02
URL	http://arxiv.org/abs/1605.00596v1
PDF	http://arxiv.org/pdf/1605.00596v1.pdf
PWC	https://paperswithcode.com/paper/graph-clustering-bandits-for-recommendation
Repo
Framework