January 29, 2020

2919 words 14 mins read

Paper Group ANR 505

Lightweight Residual Network for The Classification of Thyroid Nodules. Brain MRI Segmentation using Rule-Based Hybrid Approach. Heterogeneity-Aware Asynchronous Decentralized Training. Human-Centered Artificial Intelligence and Machine Learning. The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision. …

Lightweight Residual Network for The Classification of Thyroid Nodules


Title	Lightweight Residual Network for The Classification of Thyroid Nodules
Authors	Ponugoti Nikhila, Sabari Nathan, Elmer Jeto Gomes Ataide, Alfredo Illanes, Dr. Michael Friebe, Srichandana Abbineni
Abstract	Ultrasound is a useful technique for diagnosing thyroid nodules. Benign and malignant nodules that automatically discriminate in the ultrasound pictures can provide diagnostic recommendations or, improve diagnostic accuracy in the absence of specialists. The main issue here is how to collect suitable features for this particular task. We suggest here a technique for extracting features from ultrasound pictures based on the Residual U-net. We attempt to introduce significant semantic characteristics to the classification. Our model gained 95% classification accuracy.
Tasks
Published	2019-11-16
URL	https://arxiv.org/abs/1911.08303v1
PDF	https://arxiv.org/pdf/1911.08303v1.pdf
PWC	https://paperswithcode.com/paper/lightweight-residual-network-for-the
Repo
Framework

Brain MRI Segmentation using Rule-Based Hybrid Approach


Title	Brain MRI Segmentation using Rule-Based Hybrid Approach
Authors	Mustansar Fiaz, Kamran Ali, Abdul Rehman, M. Junaid Gul, Soon Ki Jung
Abstract	Medical image segmentation being a substantial component of image processing plays a significant role to analyze gross anatomy, to locate an infirmity and to plan the surgical procedures. Segmentation of brain Magnetic Resonance Imaging (MRI) is of considerable importance for the accurate diagnosis. However, precise and accurate segmentation of brain MRI is a challenging task. Here, we present an efficient framework for segmentation of brain MR images. For this purpose, Gabor transform method is used to compute features of brain MRI. Then, these features are classified by using four different classifiers i.e., Incremental Supervised Neural Network (ISNN), K-Nearest Neighbor (KNN), Probabilistic Neural Network (PNN), and Support Vector Machine (SVM). Performance of these classifiers is investigated over different images of brain MRI and the variation in the performance of these classifiers is observed for different brain tissues. Thus, we proposed a rule-based hybrid approach to segment brain MRI. Experimental results show that the performance of these classifiers varies over each tissue MRI and the proposed rule-based hybrid approach exhibits better segmentation of brain MRI tissues.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04207v1
PDF	http://arxiv.org/pdf/1902.04207v1.pdf
PWC	https://paperswithcode.com/paper/brain-mri-segmentation-using-rule-based
Repo
Framework

Heterogeneity-Aware Asynchronous Decentralized Training


Title	Heterogeneity-Aware Asynchronous Decentralized Training
Authors	Qinyi Luo, Jiaao He, Youwei Zhuo, Xuehai Qian
Abstract	Distributed deep learning training usually adopts All-Reduce as the synchronization mechanism for data parallel algorithms due to its high performance in homogeneous environment. However, its performance is bounded by the slowest worker among all workers, and is significantly slower in heterogeneous situations. AD-PSGD, a newly proposed synchronization method which provides numerically fast convergence and heterogeneity tolerance, suffers from deadlock issues and high synchronization overhead. Is it possible to get the best of both worlds - designing a distributed training method that has both high performance as All-Reduce in homogeneous environment and good heterogeneity tolerance as AD-PSGD? In this paper, we propose Ripples, a high-performance heterogeneity-aware asynchronous decentralized training approach. We achieve the above goal with intensive synchronization optimization, emphasizing the interplay between algorithm and system implementation. To reduce synchronization cost, we propose a novel communication primitive Partial All-Reduce that allows a large group of workers to synchronize quickly. To reduce synchronization conflict, we propose static group scheduling in homogeneous environment and simple techniques (Group Buffer and Group Division) to avoid conflicts with slightly reduced randomness. Our experiments show that in homogeneous environment, Ripples is 1.1 times faster than the state-of-the-art implementation of All-Reduce, 5.1 times faster than Parameter Server and 4.3 times faster than AD-PSGD. In a heterogeneous setting, Ripples shows 2 times speedup over All-Reduce, and still obtains 3 times speedup over the Parameter Server baseline.
Tasks
Published	2019-09-17
URL	https://arxiv.org/abs/1909.08029v1
PDF	https://arxiv.org/pdf/1909.08029v1.pdf
PWC	https://paperswithcode.com/paper/heterogeneity-aware-asynchronous
Repo
Framework

Human-Centered Artificial Intelligence and Machine Learning


Title	Human-Centered Artificial Intelligence and Machine Learning
Authors	Mark O. Riedl
Abstract	Humans are increasingly coming into contact with artificial intelligence and machine learning systems. Human-centered artificial intelligence is a perspective on AI and ML that algorithms must be designed with awareness that they are part of a larger system consisting of humans. We lay forth an argument that human-centered artificial intelligence can be broken down into two aspects: (1) AI systems that understand humans from a sociocultural perspective, and (2) AI systems that help humans understand them. We further argue that issues of social responsibility such as fairness, accountability, interpretability, and transparency.
Tasks
Published	2019-01-31
URL	http://arxiv.org/abs/1901.11184v1
PDF	http://arxiv.org/pdf/1901.11184v1.pdf
PWC	https://paperswithcode.com/paper/human-centered-artificial-intelligence-and
Repo
Framework

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision


Title	The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
Authors	Jiayuan Mao, Chuang Gan, Pushmeet Kohli, Joshua B. Tenenbaum, Jiajun Wu
Abstract	We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers. Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analogical to human concept learning, the perception module learns visual concepts based on the language description of the object being referred to. Meanwhile, the learned visual concepts facilitate learning new words and parsing new sentences. We use curriculum learning to guide the searching over the large compositional space of images and language. Extensive experiments demonstrate the accuracy and efficiency of our model on learning visual concepts, word representations, and semantic parsing of sentences. Further, our method allows easy generalization to new object attributes, compositions, language concepts, scenes and questions, and even new program domains. It also empowers applications including visual question answering and bidirectional image-text retrieval.
Tasks	Question Answering, Semantic Parsing, Visual Question Answering
Published	2019-04-26
URL	http://arxiv.org/abs/1904.12584v1
PDF	http://arxiv.org/pdf/1904.12584v1.pdf
PWC	https://paperswithcode.com/paper/the-neuro-symbolic-concept-learner-1
Repo
Framework

Semantic Attribute Matching Networks


Title	Semantic Attribute Matching Networks
Authors	Seungryong Kim, Dongbo Min, Somi Jeong, Sunok Kim, Sangryul Jeon, Kwanghoon Sohn
Abstract	We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligently weaves the advantages of the two tasks while overcoming their limitations. SAM-Net accomplishes this through an iterative process of establishing reliable correspondences by reducing the attribute discrepancy between the images and synthesizing attribute transferred images using the learned correspondences. To learn the networks using weak supervisions in the form of image pairs, we present a semantic attribute matching loss based on the matching similarity between an attribute transferred source feature and a warped target feature. With SAM-Net, the state-of-the-art performance is attained on several benchmarks for semantic matching and attribute transfer.
Tasks
Published	2019-04-05
URL	http://arxiv.org/abs/1904.02969v1
PDF	http://arxiv.org/pdf/1904.02969v1.pdf
PWC	https://paperswithcode.com/paper/semantic-attribute-matching-networks
Repo
Framework

An Accuracy-Enhanced Stemming Algorithm for Arabic Information Retrieval


Title	An Accuracy-Enhanced Stemming Algorithm for Arabic Information Retrieval
Authors	Sadik Bessou, Mohamed Touahria
Abstract	This paper provides a method for indexing and retrieving Arabic texts, based on natural language processing. Our approach exploits the notion of template in word stemming and replaces the words by their stems. This technique has proven to be effective since it has returned significant relevant retrieval results by decreasing silence during the retrieval phase. Series of experiments have been conducted to test the performance of the proposed algorithm ESAIR (Enhanced Stemmer for Arabic Information Retrieval). The results obtained indicate that the algorithm extracts the exact root with an accuracy rate up to 96% and hence, improving information retrieval.
Tasks	Information Retrieval
Published	2019-11-15
URL	https://arxiv.org/abs/1911.08249v1
PDF	https://arxiv.org/pdf/1911.08249v1.pdf
PWC	https://paperswithcode.com/paper/an-accuracy-enhanced-stemming-algorithm-for
Repo
Framework

A Block Diagonal Markov Model for Indoor Software-Defined Power Line Communication


Title	A Block Diagonal Markov Model for Indoor Software-Defined Power Line Communication
Authors	Ayokunle Damilola Familua
Abstract	A Semi-Hidden Markov Model (SHMM) for bursty error channels is defined by a state transition probability matrix $A$, a prior probability vector $\Pi$, and the state dependent output symbol error probability matrix $B$. Several processes are utilized for estimating $A$, $\Pi$ and $B$ from a given empirically obtained or simulated error sequence. However, despite placing some restrictions on the underlying Markov model structure, we still have a computationally intensive estimation procedure, especially given a large error sequence containing long burst of identical symbols. Thus, in this paper, we utilize under some moderate assumptions, a Markov model with random state transition matrix $A$ equivalent to a unique Block Diagonal Markov model with state transition matrix $\Lambda$ to model an indoor software-defined power line communication system. A computationally efficient modified Baum-Welch algorithm for estimation of $\Lambda$ given an experimentally obtained error sequence from the indoor PLC channel is utilized. Resulting Equivalent Block Diagonal Markov models assist designers to accelerate and facilitate the procedure of novel PLC systems design and evaluation.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.13598v1
PDF	https://arxiv.org/pdf/1905.13598v1.pdf
PWC	https://paperswithcode.com/paper/a-block-diagonal-markov-model-for-indoor
Repo
Framework

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation


Title	Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation
Authors	Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson
Abstract	We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained via Gradient Emphasis Learning (GEM), a novel combination of the key ideas of Gradient Temporal Difference Learning and Emphatic Temporal Difference Learning. With the help of the emphasis critic and the canonical value function critic, we show convergence for COF-PAC, where the critics are linear and the actor can be nonlinear.
Tasks
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04384v3
PDF	https://arxiv.org/pdf/1911.04384v3.pdf
PWC	https://paperswithcode.com/paper/provably-convergent-off-policy-actor-critic
Repo
Framework

Reducing malicious use of synthetic media research: Considerations and potential release practices for machine learning


Title	Reducing malicious use of synthetic media research: Considerations and potential release practices for machine learning
Authors	Aviv Ovadya, Jess Whittlestone
Abstract	The aim of this paper is to facilitate nuanced discussion around research norms and practices to mitigate the harmful impacts of advances in machine learning (ML). We focus particularly on the use of ML to create “synthetic media” (e.g. to generate or manipulate audio, video, images, and text), and the question of what publication and release processes around such research might look like, though many of the considerations discussed will apply to ML research more broadly. We are not arguing for any specific approach on when or how research should be distributed, but instead try to lay out some useful tools, analogies, and options for thinking about these issues. We begin with some background on the idea that ML research might be misused in harmful ways, and why advances in synthetic media, in particular, are raising concerns. We then outline in more detail some of the different paths to harm from ML research, before reviewing research risk mitigation strategies in other fields and identifying components that seem most worth emulating in the ML and synthetic media research communities. Next, we outline some important dimensions of disagreement on these issues which risk polarizing conversations. Finally, we conclude with recommendations, suggesting that the machine learning community might benefit from: working with subject matter experts to increase understanding of the risk landscape and possible mitigation strategies; building a community and norms around understanding the impacts of ML research, e.g. through regular workshops at major conferences; and establishing institutions and systems to support release practices that would otherwise be onerous and error-prone.
Tasks
Published	2019-07-25
URL	https://arxiv.org/abs/1907.11274v2
PDF	https://arxiv.org/pdf/1907.11274v2.pdf
PWC	https://paperswithcode.com/paper/reducing-malicious-use-of-synthetic-media
Repo
Framework

Prediction of multi-dimensional spatial variation data via Bayesian tensor completion


Title	Prediction of multi-dimensional spatial variation data via Bayesian tensor completion
Authors	Jiali Luan, Zheng Zhang
Abstract	This paper presents a multi-dimensional computational method to predict the spatial variation data inside and across multiple dies of a wafer. This technique is based on tensor computation. A tensor is a high-dimensional generalization of a matrix or a vector. By exploiting the hidden low-rank property of a high-dimensional data array, the large amount of unknown variation testing data may be predicted from a few random measurement samples. The tensor rank, which decides the complexity of a tensor representation, is decided by an available variational Bayesian approach. Our approach is validated by a practical chip testing data set, and it can be easily generalized to characterize the process variations of multiple wafers. Our approach is more efficient than the previous virtual probe techniques in terms of memory and computational cost when handling high-dimensional chip testing data.
Tasks
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00578v1
PDF	http://arxiv.org/pdf/1901.00578v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-multi-dimensional-spatial
Repo
Framework

Deep Iterative Surface Normal Estimation


Title	Deep Iterative Surface Normal Estimation
Authors	Jan Eric Lenssen, Christian Osendorfer, Jonathan Masci
Abstract	This paper presents an end-to-end differentiable algorithm for robust and detail-preserving surface normal estimation on unstructured point-clouds. We utilize graph neural networks to iteratively parameterize an adaptive anisotropic kernel that produces point weights for weighted least-squares plane fitting in local neighborhoods. The approach retains the interpretability and efficiency of traditional sequential plane fitting while benefiting from adaptation to data set statistics through deep learning. This results in a state-of-the-art surface normal estimator that is robust to noise, outliers and point density variation, preserves sharp features through anisotropic kernels and equivariance through a local quaternion-based spatial transformer. Contrary to previous deep learning methods, the proposed approach does not require any hand-crafted features or preprocessing. It improves on the state-of-the-art results while being more than two orders of magnitude faster and more parameter efficient.
Tasks
Published	2019-04-15
URL	https://arxiv.org/abs/1904.07172v2
PDF	https://arxiv.org/pdf/1904.07172v2.pdf
PWC	https://paperswithcode.com/paper/differentiable-iterative-surface-normal
Repo
Framework

An Empirical Study on Post-processing Methods for Word Embeddings


Title	An Empirical Study on Post-processing Methods for Word Embeddings
Authors	Shuai Tang, Mahta Mousavi, Virginia R. de Sa
Abstract	Word embeddings learnt from large corpora have been adopted in various applications in natural language processing and served as the general input representations to learning systems. Recently, a series of post-processing methods have been proposed to boost the performance of word embeddings on similarity comparison and analogy retrieval tasks, and some have been adapted to compose sentence representations. The general hypothesis behind these methods is that by enforcing the embedding space to be more isotropic, the similarity between words can be better expressed. We view these methods as an approach to shrink the covariance/gram matrix, which is estimated by learning word vectors, towards a scaled identity matrix. By optimising an objective in the semi-Riemannian manifold with Centralised Kernel Alignment (CKA), we are able to search for the optimal shrinkage parameter, and provide a post-processing method to smooth the spectrum of learnt word vectors which yields improved performance on downstream tasks.
Tasks	Word Embeddings
Published	2019-05-27
URL	https://arxiv.org/abs/1905.10971v3
PDF	https://arxiv.org/pdf/1905.10971v3.pdf
PWC	https://paperswithcode.com/paper/an-empirical-study-on-post-processing-methods
Repo
Framework

A General Upper Bound for Unsupervised Domain Adaptation


Title	A General Upper Bound for Unsupervised Domain Adaptation
Authors	Dexuan Zhang, Tatsuya Harada
Abstract	In this work, we present a novel upper bound of target error to address the problem for unsupervised domain adaptation. Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks. Furthermore, a theory proposed by Ben-David et al. (2010) provides a upper bound for target error when transferring the knowledge, which can be summarized as minimizing the source error and distance between marginal distributions simultaneously. However, common methods based on the theory usually ignore the joint error such that samples from different classes might be mixed together when matching marginal distribution. And in such case, no matter how we minimize the marginal discrepancy, the target error is not bounded due to an increasing joint error. To address this problem, we propose a general upper bound taking joint error into account, such that the undesirable case can be properly penalized. In addition, we utilize constrained hypothesis space to further formalize a tighter bound as well as a novel cross margin discrepancy to measure the dissimilarity between hypotheses which alleviates instability during adversarial learning. Extensive empirical evidence shows that our proposal outperforms related approaches in image classification error rates on standard domain adaptation benchmarks.
Tasks	Domain Adaptation, Image Classification, Unsupervised Domain Adaptation
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01409v2
PDF	https://arxiv.org/pdf/1910.01409v2.pdf
PWC	https://paperswithcode.com/paper/a-general-upper-bound-for-unsupervised-domain
Repo
Framework

Life After Bootstrap: Residual Randomization Inference in Regression Models


Title	Life After Bootstrap: Residual Randomization Inference in Regression Models
Authors	Panos Toulis
Abstract	We develop a randomization-based method for inference in regression models. The basis of inference is an invariance assumption on the regression errors, such as invariance to permutations or random signs. To test significance, the randomization method repeatedly calculates a suitable test statistic over transformations of the regression residuals according to the invariant. Inversion of the test can produce confidence intervals. We prove general conditions for asymptotic validity of this residual randomization test and illustrate in many models, including clustered errors with one-way or two-way clustering structure. We also show that finite-sample validity is possible under a suitable construction, and illustrate with an exact test for a case of the Behrens-Fisher problem. The proposed method offers four main advantages over the bootstrap: (1) it addresses the inference problem in a unified way, while bootstrap typically needs to be adapted to the task; (2) it can be more powerful by exploiting a richer and more flexible set of invariances than exchangeability; (3) it does not rely on asymptotic normality; and (4) it can be valid in finite samples. In extensive empirical evaluations, including high dimensional regression and autocorrelated errors, the proposed method performs favorably against many alternatives, including bootstrap variants and asymptotic robust error methods.
Tasks
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04218v1
PDF	https://arxiv.org/pdf/1908.04218v1.pdf
PWC	https://paperswithcode.com/paper/life-after-bootstrap-residual-randomization
Repo
Framework