January 28, 2020

3156 words 15 mins read

Paper Group ANR 998

A note on ‘A fully parallel 3D thinning algorithm and its applications’. Provably Correct Learning Algorithms in the Presence of Time-Varying Features Using a Variational Perspective. Estimation of Tissue Oxygen Saturation from RGB images and Sparse Hyperspectral Signals based on Conditional Generative Adversarial Network. Assembly line balancing w …

A note on ‘A fully parallel 3D thinning algorithm and its applications’


Title	A note on ‘A fully parallel 3D thinning algorithm and its applications’
Authors	Tao Wang, Anup Basu
Abstract	A 3D thinning algorithm erodes a 3D binary image layer by layer to extract the skeletons. This paper presents a correction to Ma and Sonka’s thinning algorithm, A fully parallel 3D thinning algorithm and its applications, which fails to preserve connectivity of 3D objects. We start with Ma and Sonka’s algorithm and examine its verification of connectivity preservation. Our analysis leads to a group of different deleting templates, which can preserve connectivity of 3D objects.
Tasks
Published	2019-05-01
URL	http://arxiv.org/abs/1905.03705v1
PDF	http://arxiv.org/pdf/1905.03705v1.pdf
PWC	https://paperswithcode.com/paper/190503705
Repo
Framework

Provably Correct Learning Algorithms in the Presence of Time-Varying Features Using a Variational Perspective


Title	Provably Correct Learning Algorithms in the Presence of Time-Varying Features Using a Variational Perspective
Authors	Joseph E. Gaudio, Travis E. Gibson, Anuradha M. Annaswamy, Michael A. Bolender
Abstract	Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent methods unstable or weakens their convergence guarantees. Inspired by methods employed in adaptive control, this paper proposes new algorithms for the case when time-varying features are present, and demonstrates provable performance guarantees. In particular, we develop a unified variational perspective within a continuous time algorithm. This variational perspective includes higher order learning concepts and normalization, both of which stem from adaptive control, and allows stability to be established for dynamical machine learning problems where time-varying features are present. These higher order algorithms are also examined for provably correct learning in adaptive control and identification. Simulations are provided to verify the theoretical results.
Tasks
Published	2019-03-12
URL	https://arxiv.org/abs/1903.04666v3
PDF	https://arxiv.org/pdf/1903.04666v3.pdf
PWC	https://paperswithcode.com/paper/accelerated-learning-in-the-presence-of-time
Repo
Framework

Estimation of Tissue Oxygen Saturation from RGB images and Sparse Hyperspectral Signals based on Conditional Generative Adversarial Network


Title	Estimation of Tissue Oxygen Saturation from RGB images and Sparse Hyperspectral Signals based on Conditional Generative Adversarial Network
Authors	Qingbiao Li, Jianyu Lin, Neil T. Clancy, Daniel S. Elson
Abstract	Purpose: Intra-operative measurement of tissue oxygen saturation (StO2) is important in the detection of ischemia, monitoring perfusion and identifying disease. Hyperspectral imaging (HSI) measures the optical reflectance spectrum of the tissue and uses this information to quantify its composition, including StO2. However, real-time monitoring is difficult due to the capture rate and data processing time. Methods: An endoscopic system based on a multi-fiber probe was previously developed to sparsely capture HSI data (sHSI). These were combined with RGB images, via a deep neural network, to generate high-resolution hypercubes and calculate StO2. To improve accuracy and processing speed, we propose a dual-input conditional generative adversarial network (cGAN), Dual2StO2, to directly estimate StO2 by fusing features from both RGB and sHSI. Results: Validation experiments were carried out on in vivo porcine bowel data, where the ground truth StO2 was generated from the HSI camera. The performance was also compared to our previous super-spectral-resolution network, SSRNet in terms of mean StO2 prediction accuracy and structural similarity metrics. Dual2StO2 was also tested using simulated probe data with varying fiber number. Conclusions: StO2 estimation by Dual2StO2 is visually closer to ground truth in general structure, achieves higher prediction accuracy and faster processing speed than SSRNet. Simulations showed that results improved when a greater number of fibers are used in the probe. Future work will include refinement of the network architecture, hardware optimization based on simulation results, and evaluation of the technique in clinical applications beyond StO2 estimation.
Tasks
Published	2019-05-01
URL	https://arxiv.org/abs/1905.00391v2
PDF	https://arxiv.org/pdf/1905.00391v2.pdf
PWC	https://paperswithcode.com/paper/estimation-of-tissue-oxygen-saturation-from-1
Repo
Framework

Assembly line balancing with task division


Title	Assembly line balancing with task division
Authors	Carlos Alexandre X. Silva, Les Foulds, Humberto J. Longo
Abstract	In a commonly-used version of the Simple Assembly Line Balancing Problem (SALBP-1) tasks are assigned to stations along an assembly line with a fixed cycle time in order to minimize the required number of stations. It has traditionally been assumed that the total work needed for each product unit has been partitioned into economically indivisible tasks. However, in practice, it is sometimes possible to divide particular tasks in limited ways at additional time penalty cost. Despite the penalties, task division where possible, now and then leads to a reduction in the minimum number of stations. Deciding which allowable tasks to divide creates a new assembly line balancing problem, TDALBP (Task Division Assembly Line Balancing Problem). We propose a mathematical model of the TDALBP, an exact solution procedure for it and present promising computational results for the adaptation of some classical SALBP instances from the research literature. The results demonstrate that the TDALBP sometimes has the potential to significantly improve assembly line performance.
Tasks
Published	2019-06-22
URL	https://arxiv.org/abs/1906.10120v1
PDF	https://arxiv.org/pdf/1906.10120v1.pdf
PWC	https://paperswithcode.com/paper/assembly-line-balancing-with-task-division
Repo
Framework

Should All Cross-Lingual Embeddings Speak English?


Title	Should All Cross-Lingual Embeddings Speak English?
Authors	Antonios Anastasopoulos, Graham Neubig
Abstract	Most of recent work in cross-lingual word embeddings is severely Anglocentric. The vast majority of lexicon induction evaluation dictionaries are between English and another language, and the English embedding space is selected by default as the hub when learning in a multilingual setting. With this work, however, we challenge these practices. First, we show that the choice of hub language can significantly impact downstream lexicon induction performance. Second, we both expand the current evaluation dictionary collection to include all language pairs using triangulation, and also create new dictionaries for under-represented languages. Evaluating established methods over all these language pairs sheds light into their suitability and presents new challenges for the field. Finally, in our analysis we identify general guidelines for strong cross-lingual embeddings baselines, based on more than just Anglocentric experiments.
Tasks	Word Embeddings
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03058v1
PDF	https://arxiv.org/pdf/1911.03058v1.pdf
PWC	https://paperswithcode.com/paper/should-all-cross-lingual-embeddings-speak
Repo
Framework

Discriminative Topic Mining via Category-Name Guided Text Embedding


Title	Discriminative Topic Mining via Category-Name Guided Text Embedding
Authors	Yu Meng, Jiaxin Huang, Guangyuan Wang, Zihan Wang, Chao Zhang, Yu Zhang, Jiawei Han
Abstract	Mining a set of meaningful and distinctive topics automatically from massive text corpora has broad applications. Existing topic models, however, typically work in a purely unsupervised way, which often generate topics that do not fit users’ particular needs and yield suboptimal performance on downstream tasks. We propose a new task, discriminative topic mining, which leverages a set of user-provided category names to mine discriminative topics from text corpora. This new task not only helps a user understand clearly and distinctively the topics he/she is most interested in, but also benefits directly keyword-driven classification tasks. We develop CatE, a novel category-name guided text embedding method for discriminative topic mining, which effectively leverages minimal user guidance to learn a discriminative embedding space and discover category representative terms in an iterative manner. We conduct a comprehensive set of experiments to show that CatE mines high-quality set of topics guided by category names only, and benefits a variety of downstream applications including weakly-supervised classification and lexical entailment direction identification.
Tasks	Document Classification, Topic Models
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07162v2
PDF	https://arxiv.org/pdf/1908.07162v2.pdf
PWC	https://paperswithcode.com/paper/cate-category-name-guidedword-embedding
Repo
Framework

Topic Modeling with Wasserstein Autoencoders


Title	Topic Modeling with Wasserstein Autoencoders
Authors	Feng Nan, Ran Ding, Ramesh Nallapati, Bing Xiang
Abstract	We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much better than the Generative Adversarial Network (GAN) in matching high dimensional Dirichlet distribution. We further discover that incorporating randomness in the encoder output during training leads to significantly more coherent topics. To measure the diversity of the produced topics, we propose a simple topic uniqueness metric. Together with the widely used coherence measure NPMI, we offer a more wholistic evaluation of topic quality. Experiments on several real datasets show that our model produces significantly better topics than existing topic models.
Tasks	Topic Models
Published	2019-07-24
URL	https://arxiv.org/abs/1907.12374v2
PDF	https://arxiv.org/pdf/1907.12374v2.pdf
PWC	https://paperswithcode.com/paper/topic-modeling-with-wasserstein-autoencoders-1
Repo
Framework

A Game of Dice: Machine Learning and the Question Concerning Art


Title	A Game of Dice: Machine Learning and the Question Concerning Art
Authors	Paul Todorov
Abstract	We review some practical and philosophical questions raised by the use of machine learning in creative practice. Beyond the obvious problems regarding plagiarism and authorship, we argue that the novelty in AI Art relies mostly on a narrow machine learning contribution : manifold approximation. Nevertheless, this contribution creates a radical shift in the way we have to consider this movement. Is this omnipotent tool a blessing or a curse for the artists?
Tasks
Published	2019-04-02
URL	http://arxiv.org/abs/1904.01957v1
PDF	http://arxiv.org/pdf/1904.01957v1.pdf
PWC	https://paperswithcode.com/paper/a-game-of-dice-machine-learning-and-the
Repo
Framework

Neural networks on microcontrollers: saving memory at inference via operator reordering


Title	Neural networks on microcontrollers: saving memory at inference via operator reordering
Authors	Edgar Liberis, Nicholas D. Lane
Abstract	Designing deep learning models for highly-constrained hardware would allow imbuing many edge devices with intelligence. Microcontrollers (MCUs) are an attractive platform for building smart devices due to their low cost, wide availability, and modest power usage. However, they lack the computational resources to run neural networks as straightforwardly as mobile or server platforms, which necessitates changes to the network architecture and the inference software. In this work, we discuss the deployment and memory concerns of neural networks on MCUs and present a way of saving memory by changing the execution order of the network’s operators, which is orthogonal to other compression methods. We publish a tool for reordering operators of TensorFlow Lite models and demonstrate its utility by sufficiently reducing the memory footprint of a CNN to deploy it on an MCU with 512KB SRAM.
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.05110v2
PDF	https://arxiv.org/pdf/1910.05110v2.pdf
PWC	https://paperswithcode.com/paper/neural-networks-on-microcontrollers-saving
Repo
Framework

Simple Algorithms for Dueling Bandits


Title	Simple Algorithms for Dueling Bandits
Authors	Tyler Lekang, Andrew Lamperski
Abstract	In this paper, we present simple algorithms for Dueling Bandits. We prove that the algorithms have regret bounds for time horizon T of order O(T^rho ) with 1/2 <= rho <= 3/4, which importantly do not depend on any preference gap between actions, Delta. Dueling Bandits is an important extension of the Multi-Armed Bandit problem, in which the algorithm must select two actions at a time and only receives binary feedback for the duel outcome. This is analogous to comparisons in which the rater can only provide yes/no or better/worse type responses. We compare our simple algorithms to the current state-of-the-art for Dueling Bandits, ISS and DTS, discussing complexity and regret upper bounds, and conducting experiments on synthetic data that demonstrate their regret performance, which in some cases exceeds state-of-the-art.
Tasks
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07611v1
PDF	https://arxiv.org/pdf/1906.07611v1.pdf
PWC	https://paperswithcode.com/paper/simple-algorithms-for-dueling-bandits
Repo
Framework

Learning Predictive Models From Observation and Interaction


Title	Learning Predictive Models From Observation and Interaction
Authors	Karl Schmeckpeper, Annie Xie, Oleh Rybkin, Stephen Tian, Kostas Daniilidis, Sergey Levine, Chelsea Finn
Abstract	Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes. However, learning a model that captures the dynamics of complex skills represents a major challenge: if the agent needs a good model to perform these skills, it might never be able to collect the experience on its own that is required to learn these delicate and complex behaviors. Instead, we can imagine augmenting the training set with observational data of other agents, such as humans. Such data is likely more plentiful, but represents a different embodiment. For example, videos of humans might show a robot how to use a tool, but (i) are not annotated with suitable robot actions, and (ii) contain a systematic distributional shift due to the embodiment differences between humans and robots. We address the first challenge by formulating the corresponding graphical model and treating the action as an observed variable for the interaction data and an unobserved variable for the observation data, and the second challenge by using a domain-dependent prior. In addition to interaction data, our method is able to leverage videos of passive observations in a driving dataset and a dataset of robotic manipulation videos. A robotic planning agent equipped with our method can learn to use tools in a tabletop robotic manipulation setting by observing humans without ever seeing a robotic video of tool use.
Tasks
Published	2019-12-30
URL	https://arxiv.org/abs/1912.12773v1
PDF	https://arxiv.org/pdf/1912.12773v1.pdf
PWC	https://paperswithcode.com/paper/learning-predictive-models-from-observation
Repo
Framework

When to reply? Context Sensitive Models to Predict Instructor Interventions in MOOC Forums


Title	When to reply? Context Sensitive Models to Predict Instructor Interventions in MOOC Forums
Authors	Muthu Kumar Chandrasekaran, Min-Yen Kan
Abstract	Due to time constraints, course instructors often need to selectively participate in student discussion threads, due to their limited bandwidth and lopsided student–instructor ratio on online forums. We propose the first deep learning models for this binary prediction problem. We propose novel attention based models to infer the amount of latent context necessary to predict instructor intervention. Such models also allow themselves to be tuned to instructor’s preference to intervene early or late. Our three proposed attentive model variants to infer the latent context improve over the state-of-the-art by a significant, large margin of 11% in F1 and 10% in recall, on average. Further, introspection of attention help us better understand what aspects of a discussion post propagate through the discussion thread that prompts instructor intervention.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10851v1
PDF	https://arxiv.org/pdf/1905.10851v1.pdf
PWC	https://paperswithcode.com/paper/when-to-reply-context-sensitive-models-to
Repo
Framework

A Unified Framework for Speech Separation


Title	A Unified Framework for Speech Separation
Authors	Fahimeh Bahmaninezhad, Shi-Xiong Zhang, Yong Xu, Meng Yu, John H. L. Hansen, Dong Yu
Abstract	Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing of naturalistic audio streams. After incorporating deep learning techniques into speech separation, performance on these systems is improving faster. The initial solutions introduced for deep learning based speech separation analyzed the speech signals into time-frequency domain with STFT; and then encoded mixed signals were fed into a deep neural network based separator. Most recently, new methods are introduced to separate waveform of the mixed signal directly without analyzing them using STFT. Here, we introduce a unified framework to include both spectrogram and waveform separations into a single structure, while being only different in the kernel function used to encode and decode the data; where, both can achieve competitive performance. This new framework provides flexibility; in addition, depending on the characteristics of the data, or limitations of the memory and latency can set the hyper-parameters to flow in a pipeline of the framework which fits the task properly. We extend single-channel speech separation into multi-channel framework with end-to-end training of the network while optimizing the speech separation criterion (i.e., Si-SNR) directly. We emphasize on how tied kernel functions for calculating spatial features, encoder, and decoder in multi-channel framework can be effective. We simulate spatialized reverberate data for both WSJ0 and LibriSpeech corpora here, and while these two sets of data are different in the matter of size and duration, the effect of capturing shorter and longer dependencies of previous/+future samples are studied in detail. We report SDR, Si-SNR and PESQ to evaluate the performance of developed solutions.
Tasks	Speech Separation
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07814v1
PDF	https://arxiv.org/pdf/1912.07814v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-framework-for-speech-separation
Repo
Framework

Local Interpretation Methods to Machine Learning Using the Domain of the Feature Space


Title	Local Interpretation Methods to Machine Learning Using the Domain of the Feature Space
Authors	Tiago Botari, Rafael Izbicki, Andre C. P. L. F. de Carvalho
Abstract	As machine learning becomes an important part of many real world applications affecting human lives, new requirements, besides high predictive accuracy, become important. One important requirement is transparency, which has been associated with model interpretability. Many machine learning algorithms induce models difficult to interpret, named black box. Moreover, people have difficulty to trust models that cannot be explained. In particular for machine learning, many groups are investigating new methods able to explain black box models. These methods usually look inside the black models to explain their inner work. By doing so, they allow the interpretation of the decision making process used by black box models. Among the recently proposed model interpretation methods, there is a group, named local estimators, which are designed to explain how the label of particular instance is predicted. For such, they induce interpretable models on the neighborhood of the instance to be explained. Local estimators have been successfully used to explain specific predictions. Although they provide some degree of model interpretability, it is still not clear what is the best way to implement and apply them. Open questions include: how to best define the neighborhood of an instance? How to control the trade-off between the accuracy of the interpretation method and its interpretability? How to make the obtained solution robust to small variations on the instance to be explained? To answer to these questions, we propose and investigate two strategies: (i) using data instance properties to provide improved explanations, and (ii) making sure that the neighborhood of an instance is properly defined by taking the geometry of the domain of the feature space into account. We evaluate these strategies in a regression task and present experimental results that show that they can improve local explanations.
Tasks	Decision Making
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13525v1
PDF	https://arxiv.org/pdf/1907.13525v1.pdf
PWC	https://paperswithcode.com/paper/local-interpretation-methods-to-machine
Repo
Framework

A weakly supervised adaptive triplet loss for deep metric learning


Title	A weakly supervised adaptive triplet loss for deep metric learning
Authors	Xiaonan Zhao, Huan Qi, Rui Luo, Larry Davis
Abstract	We address the problem of distance metric learning in visual similarity search, defined as learning an image embedding model which projects images into Euclidean space where semantically and visually similar images are closer and dissimilar images are further from one another. We present a weakly supervised adaptive triplet loss (ATL) capable of capturing fine-grained semantic similarity that encourages the learned image embedding models to generalize well on cross-domain data. The method uses weakly labeled product description data to implicitly determine fine grained semantic classes, avoiding the need to annotate large amounts of training data. We evaluate on the Amazon fashion retrieval benchmark and DeepFashion in-shop retrieval data. The method boosts the performance of triplet loss baseline by 10.6% on cross-domain data and out-performs the state-of-art model on all evaluation metrics.
Tasks	Metric Learning, Semantic Similarity, Semantic Textual Similarity
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12939v1
PDF	https://arxiv.org/pdf/1909.12939v1.pdf
PWC	https://paperswithcode.com/paper/a-weakly-supervised-adaptive-triplet-loss-for
Repo
Framework