Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Recommendation": models, code, and papers

Quantifying Explainability of Saliency Methods in Deep Neural Networks

Sep 07, 2020
Erico Tjoa, Cuntai Guan

One way to achieve eXplainable artificial intelligence (XAI) is through the use of post-hoc analysis methods. In particular, methods that generate heatmaps have been used to explain black-box models, such as deep neural network. In some cases, heatmaps are appealing due to the intuitive and visual ways to understand them. However, quantitative analysis that demonstrates the actual potential of heatmaps have been lacking, and comparison between different methods are not standardized as well. In this paper, we introduce a synthetic data that can be generated adhoc along with the ground-truth heatmaps for better quantitative assessment. Each sample data is an image of a cell with easily distinguishable features, facilitating a more transparent assessment of different XAI methods. Comparison and recommendations are made, shortcomings are clarified along with suggestions for future research directions to handle the finer details of select post-hoc analysis methods.

  Access Paper or Ask Questions

On the Use/Misuse of the Term 'Phoneme'

Jul 26, 2019
Roger K. Moore, Lucy Skidmore

The term 'phoneme' lies at the heart of speech science and technology, and yet it is not clear that the research community fully appreciates its meaning and implications. In particular, it is suspected that many researchers use the term in a casual sense to refer to the sounds of speech, rather than as a well defined abstract concept. If true, this means that some sections of the community may be missing an opportunity to understand and exploit the implications of this important psychological phenomenon. Here we review the correct meaning of the term 'phoneme' and report the results of an investigation into its use/misuse in the accepted papers at INTERSPEECH-2018. It is confirmed that a significant proportion of the community (i) may not be aware of the critical difference between `phonetic' and 'phonemic' levels of description, (ii) may not fully understand the significance of 'phonemic contrast', and as a consequence, (iii) consistently misuse the term 'phoneme'. These findings are discussed, and recommendations are made as to how this situation might be mitigated.

* Accepted at INTERSPEECH-2019 

  Access Paper or Ask Questions

Hierarchical Annotation of Images with Two-Alternative-Forced-Choice Metric Learning

Jun 05, 2019
Niels Hellinga, Vlado Menkovski

Many tasks such as retrieval and recommendations can significantly benefit from structuring the data, commonly in a hierarchical way. To achieve this through annotations of high dimensional data such as images or natural text can be significantly labor intensive. We propose an approach for uncovering the hierarchical structure of data based on efficient discriminative testing rather than annotations of individual datapoints. Using two-alternative-forced-choice (2AFC) testing and deep metric learning we achieve embedding of the data in semantic space where we are able to successfully hierarchically cluster. We actively select triplets for the 2AFC test such that the modeling process is highly efficient with respect to the number of tests presented to the annotator. We empirically demonstrate the feasibility of the method by confirming the shape bias on synthetic data and extract hierarchical structure on the Fashion-MNIST dataset to a finer granularity than the original labels.

* presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA 

  Access Paper or Ask Questions

Predicting Sparse Clients' Actions with CPOPT-Net in the Banking Environment

May 23, 2019
Jeremy Charlier, Radu State, Jean Hilger

The digital revolution of the banking system with evolving European regulations have pushed the major banking actors to innovate by a newly use of their clients' digital information. Given highly sparse client activities, we propose CPOPT-Net, an algorithm that combines the CP canonical tensor decomposition, a multidimensional matrix decomposition that factorizes a tensor as the sum of rank-one tensors, and neural networks. CPOPT-Net removes efficiently sparse information with a gradient-based resolution while relying on neural networks for time series predictions. Our experiments show that CPOPT-Net is capable to perform accurate predictions of the clients' actions in the context of personalized recommendation. CPOPT-Net is the first algorithm to use non-linear conjugate gradient tensor resolution with neural networks to propose predictions of financial activities on a public data set.

  Access Paper or Ask Questions

Multi-Task Learning for Contextual Bandits

May 24, 2017
Aniket Anand Deshmukh, Urun Dogan, Clayton Scott

Contextual bandits are a form of multi-armed bandit in which the agent has access to predictive side information (known as the context) for each arm at each time step, and have been used to model personalized news recommendation, ad placement, and other applications. In this work, we propose a multi-task learning framework for contextual bandit problems. Like multi-task learning in the batch setting, the goal is to leverage similarities in contexts for different arms so as to improve the agent's ability to predict rewards from contexts. We propose an upper confidence bound-based multi-task learning algorithm for contextual bandits, establish a corresponding regret bound, and interpret this bound to quantify the advantages of learning in the presence of high task (arm) similarity. We also describe an effective scheme for estimating task similarity from data, and demonstrate our algorithm's performance on several data sets.

  Access Paper or Ask Questions

Content Selection in Data-to-Text Systems: A Survey

Oct 26, 2016
Dimitra Gkatzia

Data-to-text systems are powerful in generating reports from data automatically and thus they simplify the presentation of complex data. Rather than presenting data using visualisation techniques, data-to-text systems use natural (human) language, which is the most common way for human-human communication. In addition, data-to-text systems can adapt their output content to users' preferences, background or interests and therefore they can be pleasant for users to interact with. Content selection is an important part of every data-to-text system, because it is the module that determines which from the available information should be conveyed to the user. This survey initially introduces the field of data-to-text generation, describes the general data-to-text system architecture and then it reviews the state-of-the-art content selection methods. Finally, it provides recommendations for choosing an approach and discusses opportunities for future research.

  Access Paper or Ask Questions

A Mood-based Genre Classification of Television Content

Aug 06, 2015
Humberto Corona, Michael P. O'Mahony

The classification of television content helps users organise and navigate through the large list of channels and programs now available. In this paper, we address the problem of television content classification by exploiting text information extracted from program transcriptions. We present an analysis which adapts a model for sentiment that has been widely and successfully applied in other fields such as music or blog posts. We use a real-world dataset obtained from the Boxfish API to compare the performance of classifiers trained on a number of different feature sets. Our experiments show that, over a large collection of television content, program genres can be represented in a three-dimensional space of valence, arousal and dominance, and that promising classification results can be achieved using features based on this representation. This finding supports the use of the proposed representation of television content as a feature space for similarity computation and recommendation generation.

* in ACM Workshop on Recommendation Systems for Television and Online Video 2014 Foster City, California USA 

  Access Paper or Ask Questions

Fantasy Football Prediction

May 26, 2015
Roman Lutz

The ubiquity of professional sports and specifically the NFL have lead to an increase in popularity for Fantasy Football. Users have many tools at their disposal: statistics, predictions, rankings of experts and even recommendations of peers. There are issues with all of these, though. Especially since many people pay money to play, the prediction tools should be enhanced as they provide unbiased and easy-to-use assistance for users. This paper provides and discusses approaches to predict Fantasy Football scores of Quarterbacks with relatively limited data. In addition to that, it includes several suggestions on how the data could be enhanced to achieve better results. The dataset consists only of game data from the last six NFL seasons. I used two different methods to predict the Fantasy Football scores of NFL players: Support Vector Regression (SVR) and Neural Networks. The results of both are promising given the limited data that was used.

* class project, 7 pages (1 sources, 1 appendix) 

  Access Paper or Ask Questions

CAD-based approach for identification of elasto-static parameters of robotic manipulators

Nov 26, 2013
Alexandr Klimchik, Anatol Pashkevich, Damien Chablat

The paper presents an approach for the identification of elasto-static parameters of a robotic manipulator using the virtual experiments in a CAD environment. It is based on the numerical processing of the data extracted from the finite element analysis results, which are obtained for isolated manipulator links. This approach allows to obtain the desired stiffness matrices taking into account the complex shape of the links, couplings between rotational/translational deflections and particularities of the joints connecting adjacent links. These matrices are integral parts of the manipulator lumped stiffness model that are widely used in robotics due to its high computational efficiency. To improve the identification accuracy, recommendations for optimal settings of the virtual experiments are given, as well as relevant statistical processing techniques are proposed. Efficiency of the developed approach is confirmed by a simulation study that shows that the accuracy in evaluating the stiffness matrix elements is about 0.1%.

* Finite Elements in Analysis and Design 75 (2013) 19-30 
* arXiv admin note: substantial text overlap with arXiv:0909.1460 

  Access Paper or Ask Questions