April 2, 2020

3372 words 16 mins read

Paper Group ANR 121

Paper Group ANR 121

G-LBM:Generative Low-dimensional Background Model Estimation from Video Sequences. Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Model. Active learning workflows and integrable deep neural networks for representing the free energy functions of alloy. Geometric Formulation for Disc …

G-LBM:Generative Low-dimensional Background Model Estimation from Video Sequences

Title G-LBM:Generative Low-dimensional Background Model Estimation from Video Sequences
Authors Behnaz Rezaei, Amirreza Farnoosh, Sarah Ostadabbas
Abstract In this paper, we propose a computationally tractable and theoretically supported non-linear low-dimensional generative model to represent real-world data in the presence of noise and sparse outliers. The non-linear low-dimensional manifold discovery of data is done through describing a joint distribution over observations, and their low-dimensional representations (i.e. manifold coordinates). Our model, called generative low-dimensional background model (G-LBM) admits variational operations on the distribution of the manifold coordinates and simultaneously generates a low-rank structure of the latent manifold given the data. Therefore, our probabilistic model contains the intuition of the non-probabilistic low-dimensional manifold learning. G-LBM selects the intrinsic dimensionality of the underling manifold of the observations, and its probabilistic nature models the noise in the observation data. G-LBM has direct application in the background scenes model estimation from video sequences and we have evaluated its performance on SBMnet-2016 and BMC2012 datasets, where it achieved a performance higher or comparable to other state-of-the-art methods while being agnostic to the background scenes in videos. Besides, in challenges such as camera jitter and background motion, G-LBM is able to robustly estimate the background by effectively modeling the uncertainties in video observations in these scenarios.
Tasks
Published 2020-03-16
URL https://arxiv.org/abs/2003.07335v1
PDF https://arxiv.org/pdf/2003.07335v1.pdf
PWC https://paperswithcode.com/paper/g-lbmgenerative-low-dimensional-background
Repo
Framework

Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Model

Title Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Model
Authors Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi, Tetsunari Inamura
Abstract Robots are required to not only learn spatial concepts autonomously but also utilize such knowledge for various tasks in a domestic environment. Spatial concept represents a multimodal place category acquired from the robot’s spatial experience including vision, speech-language, and self-position. The aim of this study is to enable a mobile robot to perform navigational tasks with human speech instructions, such as `Go to the kitchen’, via probabilistic inference on a Bayesian generative model using spatial concepts. Specifically, path planning was formalized as the maximization of probabilistic distribution on the path-trajectory under speech instruction, based on a control-as-inference framework. Furthermore, we described the relationship between probabilistic inference based on the Bayesian generative model and control problem including reinforcement learning. We demonstrated path planning based on human instruction using acquired spatial concepts to verify the usefulness of the proposed approach in the simulator and in real environments. Experimentally, places instructed by the user’s speech commands showed high probability values, and the trajectory toward the target place was correctly estimated. Our approach, based on probabilistic inference concerning decision-making, can lead to further improvement in robot autonomy. |
Tasks Decision Making
Published 2020-02-18
URL https://arxiv.org/abs/2002.07381v1
PDF https://arxiv.org/pdf/2002.07381v1.pdf
PWC https://paperswithcode.com/paper/spatial-concept-based-navigation-with-human
Repo
Framework

Active learning workflows and integrable deep neural networks for representing the free energy functions of alloy

Title Active learning workflows and integrable deep neural networks for representing the free energy functions of alloy
Authors Gregory Teichert, Anirudh Natarajan, Anton Van der Ven, Krishna Garikipati
Abstract The free energy plays a fundamental role in descriptions of many systems in continuum physics. Notably, in multiphysics applications, it encodes thermodynamic coupling between different fields, such as mechanics and chemistry. It thereby gives rise to driving forces on the dynamics of interaction between the constituent phenomena. In mechano-chemically interacting materials systems, even consideration of only compositions, order parameters and strains can render the free energy to be reasonably high-dimensional. In proposing free energy functions as a paradigm for scale bridging, we have previously exploited neural networks for their representation of such high-dimensional functions. Specifically, we have developed an integrable deep neural network (IDNN) that can be trained to free energy derivative data obtained from atomic scale models and statistical mechanics, then analytically integrated to recover a free energy function. The motivation comes from the statistical mechanics formalism, in which certain free energy derivatives are accessible for control of the system, rather than the free energy itself in its entirety. Our current work combines the IDNN with an active learning workflow to improve sampling of the free energy derivative data in a high-dimensional input space. Treated as input-output maps, machine learning representations accommodate role reversals between independent and dependent quantities as the mathematical descriptions change across scale boundaries. As a prototypical material system we focus on Ni-Al. Phase field simulations using the resulting IDNN representation for the free energy of Ni-Al demonstrates that the appropriate physics of the material have been learned.
Tasks Active Learning
Published 2020-01-30
URL https://arxiv.org/abs/2002.02305v1
PDF https://arxiv.org/pdf/2002.02305v1.pdf
PWC https://paperswithcode.com/paper/active-learning-workflows-and-integrable-deep
Repo
Framework

Geometric Formulation for Discrete Points and its Applications

Title Geometric Formulation for Discrete Points and its Applications
Authors Yuuya Takayama
Abstract We introduce a novel formulation for geometry on discrete points. It is based on a universal differential calculus, which gives a geometric description of a discrete set by the algebra of functions. We expand this mathematical framework so that it is consistent with differential geometry, and works on spectral graph theory and random walks. Consequently, our formulation comprehensively demonstrates many discrete frameworks in probability theory, physics, applied harmonic analysis, and machine learning. Our approach would suggest the existence of an intrinsic theory and a unified picture of those discrete frameworks.
Tasks
Published 2020-02-07
URL https://arxiv.org/abs/2002.03767v1
PDF https://arxiv.org/pdf/2002.03767v1.pdf
PWC https://paperswithcode.com/paper/geometric-formulation-for-discrete-points-and
Repo
Framework

Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE

Title Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE
Authors Petru-Daniel Tudosiu, Thomas Varsavsky, Richard Shaw, Mark Graham, Parashkev Nachev, Sebastien Ourselin, Carole H. Sudre, M. Jorge Cardoso
Abstract The increasing efficiency and compactness of deep learning architectures, together with hardware improvements, have enabled the complex and high-dimensional modelling of medical volumetric data at higher resolutions. Recently, Vector-Quantised Variational Autoencoders (VQ-VAE) have been proposed as an efficient generative unsupervised learning approach that can encode images to a small percentage of their initial size, while preserving their decoded fidelity. Here, we show a VQ-VAE inspired network can efficiently encode a full-resolution 3D brain volume, compressing the data to $0.825%$ of the original size while maintaining image fidelity, and significantly outperforming the previous state-of-the-art. We then demonstrate that VQ-VAE decoded images preserve the morphological characteristics of the original data through voxel-based morphology and segmentation experiments. Lastly, we show that such models can be pre-trained and then fine-tuned on different datasets without the introduction of bias.
Tasks
Published 2020-02-13
URL https://arxiv.org/abs/2002.05692v1
PDF https://arxiv.org/pdf/2002.05692v1.pdf
PWC https://paperswithcode.com/paper/neuromorphologicaly-preserving-volumetric
Repo
Framework

Elaborating on Learned Demonstrations with Temporal Logic Specifications

Title Elaborating on Learned Demonstrations with Temporal Logic Specifications
Authors Craig Innes, Subramanian Ramamoorthy
Abstract Most current methods for learning from demonstrations assume that those demonstrations alone are sufficient to learn the underlying task. This is often untrue, especially if extra safety specifications exist which were not present in the original demonstrations. In this paper, we allow an expert to elaborate on their original demonstration with additional specification information using linear temporal logic (LTL). Our system converts LTL specifications into a differentiable loss. This loss is then used to learn a dynamic movement primitive that satisfies the underlying specification, while remaining close to the original demonstration. Further, by leveraging adversarial training, our system learns to robustly satisfy the given LTL specification on unseen inputs, not just those seen in training. We show that our method is expressive enough to work across a variety of common movement specification patterns such as obstacle avoidance, patrolling, keeping steady, and speed limitation. In addition, we show that our system can modify a base demonstration with complex specifications by incrementally composing multiple simpler specifications. We also implement our system on a PR-2 robot to show how a demonstrator can start with an initial (sub-optimal) demonstration, then interactively improve task success by including additional specifications enforced with our differentiable LTL loss.
Tasks
Published 2020-02-03
URL https://arxiv.org/abs/2002.00784v1
PDF https://arxiv.org/pdf/2002.00784v1.pdf
PWC https://paperswithcode.com/paper/elaborating-on-learned-demonstrations-with
Repo
Framework

L^2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

Title L^2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks
Authors Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen
Abstract Graph convolution networks (GCN) are increasingly popular in many applications, yet remain notoriously hard to train over large graph datasets. They need to compute node representations recursively from their neighbors. Current GCN training algorithms suffer from either high computational costs that grow exponentially with the number of layers, or high memory usage for loading the entire graph and node embeddings. In this paper, we propose a novel efficient layer-wise training framework for GCN (L-GCN), that disentangles feature aggregation and feature transformation during training, hence greatly reducing time and memory complexities. We present theoretical analysis for L-GCN under the graph isomorphism framework, that L-GCN leads to as powerful GCNs as the more costly conventional training algorithm does, under mild conditions. We further propose L^2-GCN, which learns a controller for each layer that can automatically adjust the training epochs per layer in L-GCN. Experiments show that L-GCN is faster than state-of-the-arts by at least an order of magnitude, with a consistent of memory usage not dependent on dataset size, while maintaining comparable prediction performance. With the learned controller, L^2-GCN can further cut the training time in half. Our codes are available at https://github.com/Shen-Lab/L2-GCN.
Tasks
Published 2020-03-30
URL https://arxiv.org/abs/2003.13606v2
PDF https://arxiv.org/pdf/2003.13606v2.pdf
PWC https://paperswithcode.com/paper/l-2-gcn-layer-wise-and-learned-efficient
Repo
Framework

Optimally adaptive Bayesian spectral density estimation

Title Optimally adaptive Bayesian spectral density estimation
Authors Nick James, Max Menzies
Abstract This paper studies spectral density estimates obtained assuming a \emph{Gaussian process} prior, with various stationary and non-stationary covariance structures, modelling the log of the unknown power spectrum. We unify previously disparate techniques from machine learning and statistics, applying various covariance functions to spectral density estimation, and investigate their performance and properties. We show that all covariance functions perform comparatively well, with the smoothing spline model in the existing AdaptSPEC technique performing slightly worse. Subsequently, we propose an improvement on AdaptSPEC based on an optimisation of the number of eigenvectors used. We show this improves on every existing method in the case of stationary time series, and describe an application to non-stationary time series. We introduce new measures of accuracy for the spectral density estimate, inspired from the physical sciences. Finally, we validate our models in an extensive simulation study and with real data, analysing autoregressive processes with known spectra, and sunspot and airline passenger data respectively.
Tasks Density Estimation, Time Series
Published 2020-03-04
URL https://arxiv.org/abs/2003.02367v1
PDF https://arxiv.org/pdf/2003.02367v1.pdf
PWC https://paperswithcode.com/paper/optimally-adaptive-bayesian-spectral-density
Repo
Framework

Measures to Evaluate Generative Adversarial Networks Based on Direct Analysis of Generated Images

Title Measures to Evaluate Generative Adversarial Networks Based on Direct Analysis of Generated Images
Authors Shuyue Guan, Murray H. Loew
Abstract The Generative Adversarial Network (GAN) is a state-of-the-art technique in the field of deep learning. A number of recent papers address the theory and applications of GANs in various fields of image processing. Fewer studies, however, have directly evaluated GAN outputs. Those that have been conducted focused on using classification performance (e.g., Inception Score) and statistical metrics (e.g., Fr'echet Inception Distance). , Here, we consider a fundamental way to evaluate GANs by directly analyzing the images they generate, instead of using them as inputs to other classifiers. We characterize the performance of a GAN as an image generator according to three aspects: 1) Creativity: non-duplication of the real images. 2) Inheritance: generated images should have the same style, which retains key features of the real images. 3) Diversity: generated images are different from each other. A GAN should not generate a few different images repeatedly. Based on the three aspects of ideal GANs, we have designed two measures: Creativity-Inheritance-Diversity (CID) index and Likeness Score (LS) to evaluate GAN performance, and have applied them to evaluate three typical GANs. We compared our proposed measures with three commonly used GAN evaluation methods: Inception Score (IS), Fr'echet Inception Distance (FID) and 1-Nearest Neighbor classifier (1NNC). In addition, we discuss how these evaluations could help us deepen our understanding of GANs and improve their performance.
Tasks
Published 2020-02-27
URL https://arxiv.org/abs/2002.12345v1
PDF https://arxiv.org/pdf/2002.12345v1.pdf
PWC https://paperswithcode.com/paper/measures-to-evaluate-generative-adversarial
Repo
Framework

Artificial intelligence in medicine and healthcare: a review and classification of current and near-future applications and their ethical and social Impact

Title Artificial intelligence in medicine and healthcare: a review and classification of current and near-future applications and their ethical and social Impact
Authors Emilio Gómez-González, Emilia Gomez, Javier Márquez-Rivas, Manuel Guerrero-Claro, Isabel Fernández-Lizaranzu, María Isabel Relimpio-López, Manuel E. Dorado, María José Mayorga-Buiza, Guillermo Izquierdo-Ayuso, Luis Capitán-Morales
Abstract This paper provides an overview of the current and near-future applications of Artificial Intelligence (AI) in Medicine and Health Care and presents a classification according to their ethical and societal aspects, potential benefits and pitfalls, and issues that can be considered controversial and are not deeply discussed in the literature. This work is based on an analysis of the state of the art of research and technology, including existing software, personal monitoring devices, genetic tests and editing tools, personalized digital models, online platforms, augmented reality devices, and surgical and companion robotics. Motivated by our review, we present and describe the notion of ‘extended personalized medicine’, we then review existing applications of AI in medicine and healthcare and explore the public perception of medical AI systems, and how they show, simultaneously, extraordinary opportunities and drawbacks that even question fundamental medical concepts. Many of these topics coincide with urgent priorities recently defined by the World Health Organization for the coming decade. In addition, we study the transformations of the roles of doctors and patients in an age of ubiquitous information, identify the risk of a division of Medicine into ‘fake-based’, ‘patient-generated’, and ‘scientifically tailored’, and draw the attention of some aspects that need further thorough analysis and public debate.
Tasks
Published 2020-01-22
URL https://arxiv.org/abs/2001.09778v2
PDF https://arxiv.org/pdf/2001.09778v2.pdf
PWC https://paperswithcode.com/paper/artificial-intelligence-in-medicine-and
Repo
Framework

Quantum Boosting

Title Quantum Boosting
Authors Srinivasan Arunachalam, Reevu Maity
Abstract Suppose we have a weak learning algorithm $\mathcal{A}$ for a Boolean-valued problem: $\mathcal{A}$ produces hypotheses whose bias $\gamma$ is small, only slightly better than random guessing (this could, for instance, be due to implementing $\mathcal{A}$ on a noisy device), can we boost the performance of $\mathcal{A}$ so that $\mathcal{A}$'s output is correct on $2/3$ of the inputs? Boosting is a technique that converts a weak and inaccurate machine learning algorithm into a strong accurate learning algorithm. The AdaBoost algorithm by Freund and Schapire (for which they were awarded the G"odel prize in 2003) is one of the widely used boosting algorithms, with many applications in theory and practice. Suppose we have a $\gamma$-weak learner for a Boolean concept class $C$ that takes time $R(C)$, then the time complexity of AdaBoost scales as $VC(C)\cdot poly(R(C), 1/\gamma)$, where $VC(C)$ is the $VC$-dimension of $C$. In this paper, we show how quantum techniques can improve the time complexity of classical AdaBoost. To this end, suppose we have a $\gamma$-weak quantum learner for a Boolean concept class $C$ that takes time $Q(C)$, we introduce a quantum boosting algorithm whose complexity scales as $\sqrt{VC(C)}\cdot poly(Q(C),1/\gamma);$ thereby achieving a quadratic quantum improvement over classical AdaBoost in terms of $VC(C)$.
Tasks
Published 2020-02-12
URL https://arxiv.org/abs/2002.05056v1
PDF https://arxiv.org/pdf/2002.05056v1.pdf
PWC https://paperswithcode.com/paper/quantum-boosting
Repo
Framework

Unifying Specialist Image Embedding into Universal Image Embedding

Title Unifying Specialist Image Embedding into Universal Image Embedding
Authors Yang Feng, Futang Peng, Xu Zhang, Wei Zhu, Shanfeng Zhang, Howard Zhou, Zhen Li, Tom Duerig, Shih-Fu Chang, Jiebo Luo
Abstract Deep image embedding provides a way to measure the semantic similarity of two images. It plays a central role in many applications such as image search, face verification, and zero-shot learning. It is desirable to have a universal deep embedding model applicable to various domains of images. However, existing methods mainly rely on training specialist embedding models each of which is applicable to images from a single domain. In this paper, we study an important but unexplored task: how to train a single universal image embedding model to match the performance of several specialists on each specialist’s domain. Simply fusing the training data from multiple domains cannot solve this problem because some domains become overfitted sooner when trained together using existing methods. Therefore, we propose to distill the knowledge in multiple specialists into a universal embedding to solve this problem. In contrast to existing embedding distillation methods that distill the absolute distances between images, we transform the absolute distances between images into a probabilistic distribution and minimize the KL-divergence between the distributions of the specialists and the universal embedding. Using several public datasets, we validate that our proposed method accomplishes the goal of universal image embedding.
Tasks Face Verification, Image Retrieval, Semantic Similarity, Semantic Textual Similarity, Zero-Shot Learning
Published 2020-03-08
URL https://arxiv.org/abs/2003.03701v1
PDF https://arxiv.org/pdf/2003.03701v1.pdf
PWC https://paperswithcode.com/paper/unifying-specialist-image-embedding-into
Repo
Framework

autoNLP: NLP Feature Recommendations for Text Analytics Applications

Title autoNLP: NLP Feature Recommendations for Text Analytics Applications
Authors Janardan Misra
Abstract While designing machine learning based text analytics applications, often, NLP data scientists manually determine which NLP features to use based upon their knowledge and experience with related problems. This results in increased efforts during feature engineering process and renders automated reuse of features across semantically related applications inherently difficult. In this paper, we argue for standardization in feature specification by outlining structure of a language for specifying NLP features and present an approach for their reuse across applications to increase likelihood of identifying optimal features.
Tasks Feature Engineering
Published 2020-02-08
URL https://arxiv.org/abs/2002.03056v1
PDF https://arxiv.org/pdf/2002.03056v1.pdf
PWC https://paperswithcode.com/paper/autonlp-nlp-feature-recommendations-for-text
Repo
Framework

Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction

Title Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
Authors Eunju Cha, Gyutaek Oh, Jong Chul Ye
Abstract Recently, deep learning approaches have been extensively investigated to reconstruct images from accelerated magnetic resonance image (MRI) acquisition. Although these approaches provide significant performance gain compared to compressed sensing MRI (CS-MRI), it is not clear how to choose a suitable network architecture to balance the trade-off between network complexity and performance. Recently, it was shown that an encoder-decoder convolutional neural network (CNN) can be interpreted as a piecewise linear basis-like representation, whose specific representation is determined by the ReLU activation patterns for a given input image. Thus, the expressivity or the representation power is determined by the number of piecewise linear regions. As an extension of this geometric understanding, this paper proposes a systematic geometric approach using bootstrapping and subnetwork aggregation using an attention module to increase the expressivity of the underlying neural network. Our method can be implemented in both k-space domain and image domain that can be trained in an end-to-end manner. Experimental results show that the proposed schemes significantly improve reconstruction performance with negligible complexity increases.
Tasks
Published 2020-03-17
URL https://arxiv.org/abs/2003.07740v1
PDF https://arxiv.org/pdf/2003.07740v1.pdf
PWC https://paperswithcode.com/paper/geometric-approaches-to-increase-the
Repo
Framework

Efficiently Guiding Imitation Learning Algorithms with Human Gaze

Title Efficiently Guiding Imitation Learning Algorithms with Human Gaze
Authors Akanksha Saran, Ruohan Zhang, Elaine Schaertl Short, Scott Niekum
Abstract Human gaze is known to be an intention-revealing signal in human demonstrations of tasks. In this work, we use gaze cues from human demonstrators to enhance the performance of state-of-the-art inverse reinforcement learning (IRL) and behavioral cloning (BC) algorithms. We propose a novel approach for utilizing gaze data in a computationally efficient manner — encoding the human’s attention as part of an auxiliary loss function, without adding any additional learnable parameters to those models and without requiring gaze data at test time. The auxiliary loss encourages a network to have convolutional activations in regions where the human’s gaze fixated. We show how to augment any existing convolutional architecture with our auxiliary gaze loss (coverage-based gaze loss or CGL) that can guide learning toward a better reward function or policy. We show that our proposed approach improves performance of both BC and IRL methods on a variety of Atari games. We also compare against two baseline methods for utilizing gaze data with imitation learning methods. Our approach outperforms a baseline method, called gaze-modulated dropout (GMD), and is comparable to another method (AGIL) which uses gaze as input to the network and thus increases the amount of learnable parameters.
Tasks Atari Games, Imitation Learning
Published 2020-02-28
URL https://arxiv.org/abs/2002.12500v2
PDF https://arxiv.org/pdf/2002.12500v2.pdf
PWC https://paperswithcode.com/paper/efficiently-guiding-imitation-learning
Repo
Framework
comments powered by Disqus