January 25, 2020

3061 words 15 mins read

Paper Group ANR 1677

On Training Flexible Robots using Deep Reinforcement Learning. A Framework For Identifying Group Behavior Of Wild Animals. Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding. A Study of Machine Learning Models in Predicting the Intention of Adolescents to Smoke Cigarettes. Multi-defect microscopy …

On Training Flexible Robots using Deep Reinforcement Learning


Title	On Training Flexible Robots using Deep Reinforcement Learning
Authors	Zach Dwiel, Madhavun Candadai, Mariano Phielipp
Abstract	The use of robotics in controlled environments has flourished over the last several decades and training robots to perform tasks using control strategies developed from dynamical models of their hardware have proven very effective. However, in many real-world settings, the uncertainties of the environment, the safety requirements and generalized capabilities that are expected of robots make rigid industrial robots unsuitable. This created great research interest into developing control strategies for flexible robot hardware for which building dynamical models are challenging. In this paper, inspired by the success of deep reinforcement learning (DRL) in other areas, we systematically study the efficacy of policy search methods using DRL in training flexible robots. Our results indicate that DRL is successfully able to learn efficient and robust policies for complex tasks at various degrees of flexibility. We also note that DRL using Deep Deterministic Policy Gradients can be sensitive to the choice of sensors and adding more informative sensors does not necessarily make the task easier to learn.
Tasks
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00269v2
PDF	https://arxiv.org/pdf/1907.00269v2.pdf
PWC	https://paperswithcode.com/paper/on-training-flexible-robots-using-deep
Repo
Framework

A Framework For Identifying Group Behavior Of Wild Animals


Title	A Framework For Identifying Group Behavior Of Wild Animals
Authors	Guido Muscioni, Riccardo Pressiani, Matteo Foglio, Margaret C. Crofoot, Marco D. Santambrogio, Tanya Berger-Wolf
Abstract	Activity recognition and, more generally, behavior inference tasks are gaining a lot of interest. Much of it is work in the context of human behavior. New available tracking technologies for wild animals are generating datasets that indirectly may provide information about animal behavior. In this work, we propose a method for classifying these data into behavioral annotation, particularly collective behavior of a social group. Our method is based on sequence analysis with a direct encoding of the interactions of a group of wild animals. We evaluate our approach on a real world dataset, showing significant accuracy improvements over baseline methods.
Tasks	Activity Recognition
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00932v1
PDF	https://arxiv.org/pdf/1907.00932v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-identifying-group-behavior-of
Repo
Framework

Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding


Title	Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding
Authors	Alexander H. Liu, Tzu-Wei Sung, Shun-Po Chuang, Hung-yi Lee, Lin-shan Lee
Abstract	In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduced the word embedding regularization by maximizing the cosine similarity between a transformed decoder feature and the target word embedding. Based on the regularized decoder, we further proposed the fused decoding mechanism. This allows the decoder to consider the semantic consistency during decoding by absorbing the information carried by the transformed decoder feature, which is learned to be close to the target word embedding. Initial results on LibriSpeech demonstrated that pre-trained word embedding can significantly lower ASR recognition error with a negligible cost, and the choice of word embedding algorithms among Skip-gram, CBOW and BERT is important.
Tasks	Speech Recognition
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12740v2
PDF	https://arxiv.org/pdf/1910.12740v2.pdf
PWC	https://paperswithcode.com/paper/sequence-to-sequence-automatic-speech
Repo
Framework

A Study of Machine Learning Models in Predicting the Intention of Adolescents to Smoke Cigarettes


Title	A Study of Machine Learning Models in Predicting the Intention of Adolescents to Smoke Cigarettes
Authors	Seung Joon Nam, Han Min Kim, Thomas Kang, Cheol Young Park
Abstract	The use of electronic cigarette (e-cigarette) is increasing among adolescents. This is problematic since consuming nicotine at an early age can cause harmful effects in developing teenager’s brain and health. Additionally, the use of e-cigarette has a possibility of leading to the use of cigarettes, which is more severe. There were many researches about e-cigarette and cigarette that mostly focused on finding and analyzing causes of smoking using conventional statistics. However, there is a lack of research on developing prediction models, which is more applicable to anti-smoking campaign, about e-cigarette and cigarette. In this paper, we research the prediction models that can be used to predict an individual e-cigarette user’s (including non-e-cigarette users) intention to smoke cigarettes, so that one can be early informed about the risk of going down the path of smoking cigarettes. To construct the prediction models, five machine learning (ML) algorithms are exploited and tested for their accuracy in predicting the intention to smoke cigarettes among never smokers using data from the 2018 National Youth Tobacco Survey (NYTS). In our investigation, the Gradient Boosting Classifier, one of the prediction models, shows the highest accuracy out of all the other models. Also, with the best prediction model, we made a public website that enables users to input information to predict their intentions of smoking cigarettes.
Tasks
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12748v2
PDF	https://arxiv.org/pdf/1910.12748v2.pdf
PWC	https://paperswithcode.com/paper/the-study-of-machine-learning-models-in
Repo
Framework

Multi-defect microscopy image restoration under limited data conditions


Title	Multi-defect microscopy image restoration under limited data conditions
Authors	Anastasia Razdaibiedina, Jeevaa Velayutham, Miti Modi
Abstract	Deep learning methods are becoming widely used for restoration of defects associated with fluorescence microscopy imaging. One of the major challenges in application of such methods is the availability of training data. In this work, we pro-pose a unified method for reconstruction of multi-defect fluorescence microscopy images when training data is limited. Our approach consists of two steps: first, we perform data augmentation using Generative Adversarial Network (GAN) with conditional instance normalization (CIN); second, we train a conditional GAN(cGAN) on paired ground-truth and defected images to perform restoration. The experiments on three common types of imaging defects with different amounts of training data, show that the proposed method gives comparable results or outperforms CARE, deblurGAN and CycleGAN in restored image quality when limited data is available.
Tasks	Data Augmentation, Image Restoration
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14207v1
PDF	https://arxiv.org/pdf/1910.14207v1.pdf
PWC	https://paperswithcode.com/paper/multi-defect-microscopy-image-restoration
Repo
Framework

Informative sample generation using class aware generative adversarial networks for classification of chest Xrays


Title	Informative sample generation using class aware generative adversarial networks for classification of chest Xrays
Authors	Behzad Bozorgtabar, Dwarikanath Mahapatra, Hendrik von Teng, Alexander Pollinger, Lukas Ebner, Jean-Phillipe Thiran, Mauricio Reyes
Abstract	Training robust deep learning (DL) systems for disease detection from medical images is challenging due to limited images covering different disease types and severity. The problem is especially acute, where there is a severe class imbalance. We propose an active learning (AL) framework to select most informative samples for training our model using a Bayesian neural network. Informative samples are then used within a novel class aware generative adversarial network (CAGAN) to generate realistic chest xray images for data augmentation by transferring characteristics from one class label to another. Experiments show our proposed AL framework is able to achieve state-of-the-art performance by using about $35%$ of the full dataset, thus saving significant time and effort over conventional methods.
Tasks	Active Learning, Data Augmentation
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10781v2
PDF	http://arxiv.org/pdf/1904.10781v2.pdf
PWC	https://paperswithcode.com/paper/informative-sample-generation-using-class
Repo
Framework

Deep Learning-based Polar Code Design


Title	Deep Learning-based Polar Code Design
Authors	Moustafa Ebada, Sebastian Cammerer, Ahmed Elkelesh, Stephan ten Brink
Abstract	In this work, we introduce a deep learning-based polar code construction algorithm. The core idea is to represent the information/frozen bit indices of a polar code as a binary vector which can be interpreted as trainable weights of a neural network (NN). For this, we demonstrate how this binary vector can be relaxed to a soft-valued vector, facilitating the learning process through gradient descent and enabling an efficient code construction. We further show how different polar code design constraints (e.g., code rate) can be taken into account by means of careful binary-to-soft and soft-to-binary conversions, along with rate-adjustment after each learning iteration. Besides its conceptual simplicity, this approach benefits from having the “decoder-in-the-loop”, i.e., the nature of the decoder is inherently taken into consideration while learning (designing) the polar code. We show results for belief propagation (BP) decoding over both AWGN and Rayleigh fading channels with considerable performance gains over state-of-the-art construction schemes.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12035v2
PDF	https://arxiv.org/pdf/1909.12035v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-polar-code-design
Repo
Framework

Edge, Ridge, and Blob Detection with Symmetric Molecules


Title	Edge, Ridge, and Blob Detection with Symmetric Molecules
Authors	Rafael Reisenhofer, Emily J. King
Abstract	We present a novel approach to the detection and characterization of edges, ridges, and blobs in two-dimensional images which exploits the symmetry properties of directionally sensitive analyzing functions in multiscale systems that are constructed in the framework of alpha-molecules. The proposed feature detectors are inspired by the notion of phase congruency, stable in the presence of noise, and by definition invariant to changes in contrast. We also show how the behavior of coefficients corresponding to differently scaled and oriented analyzing functions can be used to obtain a comprehensive characterization of the geometry of features in terms of local tangent directions, widths, and heights. The accuracy and robustness of the proposed measures are validated and compared to various state-of-the-art algorithms in extensive numerical experiments in which we consider sets of clean and distorted synthetic images that are associated with reliable ground truths. To further demonstrate the applicability, we show how the proposed ridge measure can be used to detect and characterize blood vessels in digital retinal images and how the proposed blob measure can be applied to automatically count the number of cell colonies in a Petri dish.
Tasks
Published	2019-01-28
URL	https://arxiv.org/abs/1901.09723v2
PDF	https://arxiv.org/pdf/1901.09723v2.pdf
PWC	https://paperswithcode.com/paper/edge-ridge-and-blob-detection-with-symmetric
Repo
Framework

Predictive Online Convex Optimization


Title	Predictive Online Convex Optimization
Authors	Antoine Lesage-Landry, Iman Shames, Joshua A. Taylor
Abstract	We incorporate future information in the form of the estimated value of future gradients in online convex optimization. This is motivated by demand response in power systems, where forecasts about the current round, e.g., the weather or the loads’ behavior, can be used to improve on predictions made with only past observations. Specifically, we introduce an additional predictive step that follows the standard online convex optimization step when certain conditions on the estimated gradient and descent direction are met. We show that under these conditions and without any assumptions on the predictability of the environment, the predictive update strictly improves on the performance of the standard update. We give two types of predictive update for various family of loss functions. We provide a regret bound for each of our predictive online convex optimization algorithms. Finally, we apply our framework to an example based on demand response which demonstrates its superior performance to a standard online convex optimization algorithm.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06263v2
PDF	https://arxiv.org/pdf/1905.06263v2.pdf
PWC	https://paperswithcode.com/paper/predictive-online-convex-optimization
Repo
Framework

Decoding Neural Responses in Mouse Visual Cortex through a Deep Neural Network


Title	Decoding Neural Responses in Mouse Visual Cortex through a Deep Neural Network
Authors	Asim Iqbal, Phil Dong, Christopher M Kim, Heeun Jang
Abstract	Finding a code to unravel the population of neural responses that leads to a distinct animal behavior has been a long-standing question in the field of neuroscience. With the recent advances in machine learning, it is shown that the hierarchically Deep Neural Networks (DNNs) perform optimally in decoding unique features out of complex datasets. In this study, we utilize the power of a DNN to explore the computational principles in the mammalian brain by exploiting the Neuropixel data from Allen Brain Institute. We decode the neural responses from mouse visual cortex to predict the presented stimuli to the animal for natural (bear, trees, cheetah, etc.) and artificial (drifted gratings, orientated bars, etc.) classes. Our results indicate that neurons in mouse visual cortex encode the features of natural and artificial objects in a distinct manner, and such neural code is consistent across animals. We investigate this by applying transfer learning to train a DNN on the neural responses of a single animal and test its generalized performance across multiple animals. Within a single animal, DNN is able to decode the neural responses with as much as 100% classification accuracy. Across animals, this accuracy is reduced to 91%. This study demonstrates the potential of utilizing the DNN models as a computational framework to understand the neural coding principles in the mammalian brain.
Tasks	Transfer Learning
Published	2019-10-26
URL	https://arxiv.org/abs/1911.05479v1
PDF	https://arxiv.org/pdf/1911.05479v1.pdf
PWC	https://paperswithcode.com/paper/decoding-neural-responses-in-mouse-visual
Repo
Framework

Supervised classification via minimax probabilistic transformations


Title	Supervised classification via minimax probabilistic transformations
Authors	Santiago Mazuelas, Andrea Zanoni, Aritz Perez
Abstract	Conventional techniques for supervised classification constrain the classification rules considered and use surrogate losses for classification 0-1 loss. Favored families of classification rules are those that enjoy parametric representations suitable for surrogate loss minimization, and low complexity properties suitable for overfitting control. This paper presents classification techniques based on robust risk minimization (RRM) that we call linear probabilistic classifiers (LPCs). The proposed techniques consider unconstrained classification rules, optimize the classification 0-1 loss, and provide performance bounds during learning. LPCs enable efficient learning by using linear optimization, and avoid overffiting by using RRM over polyhedral uncertainty sets of distributions. We also provide finite-sample generalization bounds for LPCs and show their competitive performance with state-of-the-art techniques using benchmark datasets.
Tasks
Published	2019-02-02
URL	https://arxiv.org/abs/1902.00693v3
PDF	https://arxiv.org/pdf/1902.00693v3.pdf
PWC	https://paperswithcode.com/paper/supervised-classification-via-minimax
Repo
Framework

Tooth morphometry using quasi-conformal theory


Title	Tooth morphometry using quasi-conformal theory
Authors	Gary P. T. Choi, Hei Long Chan, Robin Yong, Sarbin Ranjitkar, Alan Brook, Grant Townsend, Ke Chen, Lok Ming Lui
Abstract	Shape analysis is important in anthropology, bioarchaeology and forensic science for interpreting useful information from human remains. In particular, teeth are morphologically stable and hence well-suited for shape analysis. In this work, we propose a framework for tooth morphometry using quasi-conformal theory. Landmark-matching Teichm"uller maps are used for establishing a 1-1 correspondence between tooth surfaces with prescribed anatomical landmarks. Then, a quasi-conformal statistical shape analysis model based on the Teichm"uller mapping results is proposed for building a tooth classification scheme. We deploy our framework on a dataset of human premolars to analyze the tooth shape variation among genders and ancestries. Experimental results show that our method achieves much higher classification accuracy with respect to both gender and ancestry when compared to the existing methods. Furthermore, our model reveals the underlying tooth shape difference between different genders and ancestries in terms of the local geometric distortion and curvatures.
Tasks
Published	2019-01-07
URL	http://arxiv.org/abs/1901.01651v1
PDF	http://arxiv.org/pdf/1901.01651v1.pdf
PWC	https://paperswithcode.com/paper/tooth-morphometry-using-quasi-conformal
Repo
Framework

Improving Federated Learning Personalization via Model Agnostic Meta Learning


Title	Improving Federated Learning Personalization via Model Agnostic Meta Learning
Authors	Yihan Jiang, Jakub Konečný, Keith Rush, Sreeram Kannan
Abstract	Federated Learning (FL) refers to learning a high quality global model based on decentralized data storage, without ever copying the raw data. A natural scenario arises with data created on mobile phones by the activity of their users. Given the typical data heterogeneity in such situations, it is natural to ask how can the global model be personalized for every such device, individually. In this work, we point out that the setting of Model Agnostic Meta Learning (MAML), where one optimizes for a fast, gradient-based, few-shot adaptation to a heterogeneous distribution of tasks, has a number of similarities with the objective of personalization for FL. We present FL as a natural source of practical applications for MAML algorithms, and make the following observations. 1) The popular FL algorithm, Federated Averaging, can be interpreted as a meta learning algorithm. 2) Careful fine-tuning can yield a global model with higher accuracy, which is at the same time easier to personalize. However, solely optimizing for the global model accuracy yields a weaker personalization result. 3) A model trained using a standard datacenter optimization method is much harder to personalize, compared to one trained using Federated Averaging, supporting the first claim. These results raise new questions for FL, MAML, and broader ML research.
Tasks	Meta-Learning
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12488v1
PDF	https://arxiv.org/pdf/1909.12488v1.pdf
PWC	https://paperswithcode.com/paper/improving-federated-learning-personalization-1
Repo
Framework

What Syntactic Structures block Dependencies in RNN Language Models?


Title	What Syntactic Structures block Dependencies in RNN Language Models?
Authors	Ethan Wilcox, Roger Levy, Richard Futrell
Abstract	Recurrent Neural Networks (RNNs) trained on a language modeling task have been shown to acquire a number of non-local grammatical dependencies with some success. Here, we provide new evidence that RNN language models are sensitive to hierarchical syntactic structure by investigating the filler–gap dependency and constraints on it, known as syntactic islands. Previous work is inconclusive about whether RNNs learn to attenuate their expectations for gaps in island constructions in particular or in any sufficiently complex syntactic environment. This paper gives new evidence for the former by providing control studies that have been lacking so far. We demonstrate that two state-of-the-art RNN models are are able to maintain the filler–gap dependency through unbounded sentential embeddings and are also sensitive to the hierarchical relationship between the filler and the gap. Next, we demonstrate that the models are able to maintain possessive pronoun gender expectations through island constructions—this control case rules out the possibility that island constructions block all information flow in these networks. We also evaluate three untested islands constraints: coordination islands, left branch islands, and sentential subject islands. Models are able to learn left branch islands and learn coordination islands gradiently, but fail to learn sentential subject islands. Through these controls and new tests, we provide evidence that model behavior is due to finer-grained expectations than gross syntactic complexity, but also that the models are conspicuously un-humanlike in some of their performance characteristics.
Tasks	Language Modelling
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10431v1
PDF	https://arxiv.org/pdf/1905.10431v1.pdf
PWC	https://paperswithcode.com/paper/what-syntactic-structures-block-dependencies
Repo
Framework

Accurate Hydrologic Modeling Using Less Information


Title	Accurate Hydrologic Modeling Using Less Information
Authors	Guy Shalev, Ran El-Yaniv, Daniel Klotz, Frederik Kratzert, Asher Metzger, Sella Nevo
Abstract	Joint models are a common and important tool in the intersection of machine learning and the physical sciences, particularly in contexts where real-world measurements are scarce. Recent developments in rainfall-runoff modeling, one of the prime challenges in hydrology, show the value of a joint model with shared representation in this important context. However, current state-of-the-art models depend on detailed and reliable attributes characterizing each site to help the model differentiate correctly between the behavior of different sites. This dependency can present a challenge in data-poor regions. In this paper, we show that we can replace the need for such location-specific attributes with a completely data-driven learned embedding, and match previous state-of-the-art results with less information.
Tasks
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09427v1
PDF	https://arxiv.org/pdf/1911.09427v1.pdf
PWC	https://paperswithcode.com/paper/accurate-hydrologic-modeling-using-less
Repo
Framework