Paper Group ANR 34
Are words easier to learn from infant- than adult-directed speech? A quantitative corpus-based investigation. Bias-Compensated Normalized Maximum Correntropy Criterion Algorithm for System Identification with Noisy Input. Sparse hierarchical interaction learning with epigraphical projection. Explainable Planning. Segment Parameter Labelling in MCMC …
Are words easier to learn from infant- than adult-directed speech? A quantitative corpus-based investigation
| Title | Are words easier to learn from infant- than adult-directed speech? A quantitative corpus-based investigation |
| Authors | Adriana Guevara-Rukoz, Alejandrina Cristia, Bogdan Ludusan, Roland Thiollière, Andrew Martin, Reiko Mazuka, Emmanuel Dupoux |
| Abstract | We investigate whether infant-directed speech (IDS) could facilitate word form learning when compared to adult-directed speech (ADS). To study this, we examine the distribution of word forms at two levels, acoustic and phonological, using a large database of spontaneous speech in Japanese. At the acoustic level we show that, as has been documented before for phonemes, the realizations of words are more variable and less discriminable in IDS than in ADS. At the phonological level, we find an effect in the opposite direction: the IDS lexicon contains more distinctive words (such as onomatopoeias) than the ADS counterpart. Combining the acoustic and phonological metrics together in a global discriminability score reveals that the bigger separation of lexical categories in the phonological space does not compensate for the opposite effect observed at the acoustic level. As a result, IDS word forms are still globally less discriminable than ADS word forms, even though the effect is numerically small. We discuss the implication of these findings for the view that the functional role of IDS is to improve language learnability. |
| Tasks | |
| Published | 2017-12-23 |
| URL | http://arxiv.org/abs/1712.08793v1 |
| http://arxiv.org/pdf/1712.08793v1.pdf | |
| PWC | https://paperswithcode.com/paper/are-words-easier-to-learn-from-infant-than |
| Repo | |
| Framework | |
Bias-Compensated Normalized Maximum Correntropy Criterion Algorithm for System Identification with Noisy Input
| Title | Bias-Compensated Normalized Maximum Correntropy Criterion Algorithm for System Identification with Noisy Input |
| Authors | Wentao Ma, Dongqiao Zheng, Yuanhao Li, Zhiyu Zhang, Badong Chen |
| Abstract | This paper proposed a bias-compensated normalized maximum correntropy criterion (BCNMCC) algorithm charactered by its low steady-state misalignment for system identification with noisy input in an impulsive output noise environment. The normalized maximum correntropy criterion (NMCC) is derived from a correntropy based cost function, which is rather robust with respect to impulsive noises. To deal with the noisy input, we introduce a bias-compensated vector (BCV) to the NMCC algorithm, and then an unbiasedness criterion and some reasonable assumptions are used to compute the BCV. Taking advantage of the BCV, the bias caused by the input noise can be effectively suppressed. System identification simulation results demonstrate that the proposed BCNMCC algorithm can outperform other related algorithms with noisy input especially in an impulsive output noise environment. |
| Tasks | |
| Published | 2017-11-23 |
| URL | http://arxiv.org/abs/1711.08677v1 |
| http://arxiv.org/pdf/1711.08677v1.pdf | |
| PWC | https://paperswithcode.com/paper/bias-compensated-normalized-maximum |
| Repo | |
| Framework | |
Sparse hierarchical interaction learning with epigraphical projection
| Title | Sparse hierarchical interaction learning with epigraphical projection |
| Authors | Mingyuan Jiu, Nelly Pustelnik, Stefan Janaqi, Mériam Chebre, Lin Qi, Philippe Ricoux |
| Abstract | This work focuses on learning optimization problems with quadratical interactions between variables, which go beyond the additive models of traditional linear learning. We investigate more specifically two different methods encountered in the literature to deal with this problem: “hierNet” and structured-sparsity regularization, and study their connections. We propose a primal-dual proximal algorithm based on an epigraphical projection to optimize a general formulation of these learning problems. The experimental setting first highlights the improvement of the proposed procedure compared to state-of-the-art methods based on fast iterative shrinkage-thresholding algorithm (i.e. FISTA) or alternating direction method of multipliers (i.e. ADMM), and then, using the proposed flexible optimization framework, we provide fair comparisons between the different hierarchical penalizations and their improvement over the standard $\ell_1$-norm penalization. The experiments are conducted both on synthetic and real data, and they clearly show that the proposed primal-dual proximal algorithm based on epigraphical projection is efficient and effective to solve and investigate the problem of hierarchical interaction learning. |
| Tasks | |
| Published | 2017-05-22 |
| URL | https://arxiv.org/abs/1705.07817v4 |
| https://arxiv.org/pdf/1705.07817v4.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-hierarchical-interaction-learning-with |
| Repo | |
| Framework | |
Explainable Planning
| Title | Explainable Planning |
| Authors | Maria Fox, Derek Long, Daniele Magazzeni |
| Abstract | As AI is increasingly being adopted into application solutions, the challenge of supporting interaction with humans is becoming more apparent. Partly this is to support integrated working styles, in which humans and intelligent systems cooperate in problem-solving, but also it is a necessary step in the process of building trust as humans migrate greater responsibility to such systems. The challenge is to find effective ways to communicate the foundations of AI-driven behaviour, when the algorithms that drive it are far from transparent to humans. In this paper we consider the opportunities that arise in AI planning, exploiting the model-based representations that form a familiar and common basis for communication with users, while acknowledging the gap between planning algorithms and human problem-solving. |
| Tasks | |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10256v1 |
| http://arxiv.org/pdf/1709.10256v1.pdf | |
| PWC | https://paperswithcode.com/paper/explainable-planning |
| Repo | |
| Framework | |
Segment Parameter Labelling in MCMC Mean-Shift Change Detection
| Title | Segment Parameter Labelling in MCMC Mean-Shift Change Detection |
| Authors | Alireza Ahrabian, Shirin Enshaeifar, Clive Cheong-Took, Payam Barnaghi |
| Abstract | This work addresses the problem of segmentation in time series data with respect to a statistical parameter of interest in Bayesian models. It is common to assume that the parameters are distinct within each segment. As such, many Bayesian change point detection models do not exploit the segment parameter patterns, which can improve performance. This work proposes a Bayesian mean-shift change point detection algorithm that makes use of repetition in segment parameters, by introducing segment class labels that utilise a Dirichlet process prior. The performance of the proposed approach was assessed on both synthetic and real world data, highlighting the enhanced performance when using parameter labelling. |
| Tasks | Change Point Detection, Time Series |
| Published | 2017-10-26 |
| URL | http://arxiv.org/abs/1710.09657v1 |
| http://arxiv.org/pdf/1710.09657v1.pdf | |
| PWC | https://paperswithcode.com/paper/segment-parameter-labelling-in-mcmc-mean |
| Repo | |
| Framework | |
Deep learning enhanced mobile-phone microscopy
| Title | Deep learning enhanced mobile-phone microscopy |
| Authors | Yair Rivenson, Hatice Ceylan Koydemir, Hongda Wang, Zhensong Wei, Zhengshuang Ren, Harun Gunaydin, Yibo Zhang, Zoltan Gorocs, Kyle Liang, Derek Tseng, Aydogan Ozcan |
| Abstract | Mobile-phones have facilitated the creation of field-portable, cost-effective imaging and sensing technologies that approach laboratory-grade instrument performance. However, the optical imaging interfaces of mobile-phones are not designed for microscopy and produce spatial and spectral distortions in imaging microscopic specimens. Here, we report on the use of deep learning to correct such distortions introduced by mobile-phone-based microscopes, facilitating the production of high-resolution, denoised and colour-corrected images, matching the performance of benchtop microscopes with high-end objective lenses, also extending their limited depth-of-field. After training a convolutional neural network, we successfully imaged various samples, including blood smears, histopathology tissue sections, and parasites, where the recorded images were highly compressed to ease storage and transmission for telemedicine applications. This method is applicable to other low-cost, aberrated imaging systems, and could offer alternatives for costly and bulky microscopes, while also providing a framework for standardization of optical images for clinical and biomedical applications. |
| Tasks | |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04139v1 |
| http://arxiv.org/pdf/1712.04139v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-enhanced-mobile-phone |
| Repo | |
| Framework | |
Estimation and Optimization of Composite Outcomes
| Title | Estimation and Optimization of Composite Outcomes |
| Authors | Daniel J. Luckett, Eric B. Laber, Michael R. Kosorok |
| Abstract | There is tremendous interest in precision medicine as a means to improve patient outcomes by tailoring treatment to individual characteristics. An individualized treatment rule formalizes precision medicine as a map from patient information to a recommended treatment. A treatment rule is defined to be optimal if it maximizes the mean of a scalar outcome in a population of interest, e.g., symptom reduction. However, clinical and intervention scientists often must balance multiple and possibly competing outcomes, e.g., symptom reduction and the risk of an adverse event. One approach to precision medicine in this setting is to elicit a composite outcome which balances all competing outcomes; unfortunately, eliciting a composite outcome directly from patients is difficult without a high-quality instrument, and an expert-derived composite outcome may not account for heterogeneity in patient preferences. We propose a new paradigm for the study of precision medicine using observational data that relies solely on the assumption that clinicians are approximately (i.e., imperfectly) making decisions to maximize individual patient utility. Estimated composite outcomes are subsequently used to construct an estimator of an individualized treatment rule which maximizes the mean of patient-specific composite outcomes. The estimated composite outcomes and estimated optimal individualized treatment rule provide new insights into patient preference heterogeneity, clinician behavior, and the value of precision medicine in a given domain. We derive inference procedures for the proposed estimators under mild conditions and demonstrate their finite sample performance through a suite of simulation experiments and an illustrative application to data from a study of bipolar depression. |
| Tasks | |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10581v3 |
| http://arxiv.org/pdf/1711.10581v3.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-and-optimization-of-composite |
| Repo | |
| Framework | |
Attentional Network for Visual Object Detection
| Title | Attentional Network for Visual Object Detection |
| Authors | Kota Hara, Ming-Yu Liu, Oncel Tuzel, Amir-massoud Farahmand |
| Abstract | We propose augmenting deep neural networks with an attention mechanism for the visual object detection task. As perceiving a scene, humans have the capability of multiple fixation points, each attended to scene content at different locations and scales. However, such a mechanism is missing in the current state-of-the-art visual object detection methods. Inspired by the human vision system, we propose a novel deep network architecture that imitates this attention mechanism. As detecting objects in an image, the network adaptively places a sequence of glimpses of different shapes at different locations in the image. Evidences of the presence of an object and its location are extracted from these glimpses, which are then fused for estimating the object class and bounding box coordinates. Due to lacks of ground truth annotations of the visual attention mechanism, we train our network using a reinforcement learning algorithm with policy gradients. Experiment results on standard object detection benchmarks show that the proposed network consistently outperforms the baseline networks that does not model the attention mechanism. |
| Tasks | Object Detection |
| Published | 2017-02-06 |
| URL | http://arxiv.org/abs/1702.01478v1 |
| http://arxiv.org/pdf/1702.01478v1.pdf | |
| PWC | https://paperswithcode.com/paper/attentional-network-for-visual-object |
| Repo | |
| Framework | |
Estimation and Inference of Treatment Effects with $L_2$-Boosting in High-Dimensional Settings
| Title | Estimation and Inference of Treatment Effects with $L_2$-Boosting in High-Dimensional Settings |
| Authors | Ye Luo, Martin Spindler |
| Abstract | Boosting algorithms are very popular in Machine Learning and have proven very useful for prediction and variable selection. Nevertheless in many applications the researcher is interested in inference on treatment effects or policy variables in a high-dimensional setting. Empirical researchers are more and more faced with rich datasets containing very many controls or instrumental variables, where variable selection is challenging. In this paper we give results for the valid inference of a treatment effect after selecting from among very many control variables and the estimation of instrumental variables with potentially very many instruments when post- or orthogonal $L_2$-Boosting is used for the variable selection. This setting allows for valid inference on low-dimensional components in a regression estimated with $L_2$-Boosting. We give simulation results for the proposed methods and an empirical application, in which we analyze the effectiveness of a pulmonary artery catheter. |
| Tasks | |
| Published | 2017-12-31 |
| URL | http://arxiv.org/abs/1801.00364v1 |
| http://arxiv.org/pdf/1801.00364v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-and-inference-of-treatment-effects |
| Repo | |
| Framework | |
See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content
| Title | See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content |
| Authors | Roozbeh Mottaghi, Connor Schenck, Dieter Fox, Ali Farhadi |
| Abstract | Humans have rich understanding of liquid containers and their contents; for example, we can effortlessly pour water from a pitcher to a cup. Doing so requires estimating the volume of the cup, approximating the amount of water in the pitcher, and predicting the behavior of water when we tilt the pitcher. Very little attention in computer vision has been made to liquids and their containers. In this paper, we study liquid containers and their contents, and propose methods to estimate the volume of containers, approximate the amount of liquid in them, and perform comparative volume estimations all from a single RGB image. Furthermore, we show the results of the proposed model for predicting the behavior of liquids inside containers when one tilts the containers. We also introduce a new dataset of Containers Of liQuid contEnt (COQE) that contains more than 5,000 images of 10,000 liquid containers in context labelled with volume, amount of content, bounding box annotation, and corresponding similar 3D CAD models. |
| Tasks | |
| Published | 2017-01-10 |
| URL | http://arxiv.org/abs/1701.02718v2 |
| http://arxiv.org/pdf/1701.02718v2.pdf | |
| PWC | https://paperswithcode.com/paper/see-the-glass-half-full-reasoning-about |
| Repo | |
| Framework | |
Federated Tensor Factorization for Computational Phenotyping
| Title | Federated Tensor Factorization for Computational Phenotyping |
| Authors | Yejin Kim, Jimeng Sun, Hwanjo Yu, Xiaoqian Jiang |
| Abstract | Tensor factorization models offer an effective approach to convert massive electronic health records into meaningful clinical concepts (phenotypes) for data analysis. These models need a large amount of diverse samples to avoid population bias. An open challenge is how to derive phenotypes jointly across multiple hospitals, in which direct patient-level data sharing is not possible (e.g., due to institutional policies). In this paper, we developed a novel solution to enable federated tensor factorization for computational phenotyping without sharing patient-level data. We developed secure data harmonization and federated computation procedures based on alternating direction method of multipliers (ADMM). Using this method, the multiple hospitals iteratively update tensors and transfer secure summarized information to a central server, and the server aggregates the information to generate phenotypes. We demonstrated with real medical datasets that our method resembles the centralized training model (based on combined datasets) in terms of accuracy and phenotypes discovery while respecting privacy. |
| Tasks | Computational Phenotyping |
| Published | 2017-04-11 |
| URL | http://arxiv.org/abs/1704.03141v1 |
| http://arxiv.org/pdf/1704.03141v1.pdf | |
| PWC | https://paperswithcode.com/paper/federated-tensor-factorization-for |
| Repo | |
| Framework | |
Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow
| Title | Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow |
| Authors | Jakub M. Tomczak, Max Welling |
| Abstract | In this paper, we propose a new volume-preserving flow and show that it performs similarly to the linear general normalizing flow. The idea is to enrich a linear Inverse Autoregressive Flow by introducing multiple lower-triangular matrices with ones on the diagonal and combining them using a convex combination. In the experimental studies on MNIST and Histopathology data we show that the proposed approach outperforms other volume-preserving flows and is competitive with current state-of-the-art linear normalizing flow. |
| Tasks | |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02326v2 |
| http://arxiv.org/pdf/1706.02326v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-variational-auto-encoders-using |
| Repo | |
| Framework | |
Medical Image Segmentation Based on Multi-Modal Convolutional Neural Network: Study on Image Fusion Schemes
| Title | Medical Image Segmentation Based on Multi-Modal Convolutional Neural Network: Study on Image Fusion Schemes |
| Authors | Zhe Guo, Xiang Li, Heng Huang, Ning Guo, Quanzheng Li |
| Abstract | Image analysis using more than one modality (i.e. multi-modal) has been increasingly applied in the field of biomedical imaging. One of the challenges in performing the multimodal analysis is that there exist multiple schemes for fusing the information from different modalities, where such schemes are application-dependent and lack a unified framework to guide their designs. In this work we firstly propose a conceptual architecture for the image fusion schemes in supervised biomedical image analysis: fusing at the feature level, fusing at the classifier level, and fusing at the decision-making level. Further, motivated by the recent success in applying deep learning for natural image analysis, we implement the three image fusion schemes above based on the Convolutional Neural Network (CNN) with varied structures, and combined into a single framework. The proposed image segmentation framework is capable of analyzing the multi-modality images using different fusing schemes simultaneously. The framework is applied to detect the presence of soft tissue sarcoma from the combination of Magnetic Resonance Imaging (MRI), Computed Tomography (CT) and Positron Emission Tomography (PET) images. It is found from the results that while all the fusion schemes outperform the single-modality schemes, fusing at the feature level can generally achieve the best performance in terms of both accuracy and computational cost, but also suffers from the decreased robustness in the presence of large errors in any image modalities. |
| Tasks | Computed Tomography (CT), Decision Making, Medical Image Segmentation, Semantic Segmentation |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00049v2 |
| http://arxiv.org/pdf/1711.00049v2.pdf | |
| PWC | https://paperswithcode.com/paper/medical-image-segmentation-based-on-multi |
| Repo | |
| Framework | |
Handwritten character recognition using some (anti)-diagonal structural features
| Title | Handwritten character recognition using some (anti)-diagonal structural features |
| Authors | José Manuel Casas, Nick Inassaridze, Manuel Ladra, Susana Ladra |
| Abstract | In this paper, we present a methodology for off-line handwritten character recognition. The proposed methodology relies on a new feature extraction technique based on structural characteristics, histograms and profiles. As novelty, we propose the extraction of new eight histograms and four profiles from the $32\times 32$ matrices that represent the characters, creating 256-dimension feature vectors. These feature vectors are then employed in a classification step that uses a $k$-means algorithm. We performed experiments using the NIST database to evaluate our proposal. Namely, the recognition system was trained using 1000 samples and 64 classes for each symbol and was tested on 500 samples for each symbol. We obtain promising accuracy results that vary from 81.74% to 93.75%, depending on the difficulty of the character category, showing better accuracy results than other methods from the state of the art also based on structural characteristics. |
| Tasks | |
| Published | 2017-07-27 |
| URL | http://arxiv.org/abs/1707.08951v3 |
| http://arxiv.org/pdf/1707.08951v3.pdf | |
| PWC | https://paperswithcode.com/paper/handwritten-character-recognition-using-some |
| Repo | |
| Framework | |
Neural Machine Translation with Word Predictions
| Title | Neural Machine Translation with Word Predictions |
| Authors | Rongxiang Weng, Shujian Huang, Zaixiang Zheng, Xinyu Dai, Jiajun Chen |
| Abstract | In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence.These vectors are generated by parameters which are updated by back-propagation of translation errors through time. We argue that propagating errors through the end-to-end recurrent structures are not a direct way of control the hidden vectors. In this paper, we propose to use word predictions as a mechanism for direct supervision. More specifically, we require these vectors to be able to predict the vocabulary in target sentence. Our simple mechanism ensures better representations in the encoder and decoder without using any extra data or annotation. It is also helpful in reducing the target side vocabulary and improving the decoding efficiency. Experiments on Chinese-English and German-English machine translation tasks show BLEU improvements by 4.53 and 1.3, respectively |
| Tasks | Machine Translation |
| Published | 2017-08-05 |
| URL | http://arxiv.org/abs/1708.01771v1 |
| http://arxiv.org/pdf/1708.01771v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-with-word |
| Repo | |
| Framework | |
