July 29, 2019

3108 words 15 mins read

Paper Group ANR 21

A Function Approximation Method for Model-based High-Dimensional Inverse Reinforcement Learning. A Class of Logistic Functions for Approximating State-Inclusive Koopman Operators. Tumour Ellipsification in Ultrasound Images for Treatment Prediction in Breast Cancer. Objects that Sound. On denoising modulo 1 samples of a function. Localizing Actions …

A Function Approximation Method for Model-based High-Dimensional Inverse Reinforcement Learning


Title	A Function Approximation Method for Model-based High-Dimensional Inverse Reinforcement Learning
Authors	Kun Li, Joel W. Burdick
Abstract	This works handles the inverse reinforcement learning problem in high-dimensional state spaces, which relies on an efficient solution of model-based high-dimensional reinforcement learning problems. To solve the computationally expensive reinforcement learning problems, we propose a function approximation method to ensure that the Bellman Optimality Equation always holds, and then estimate a function based on the observed human actions for inverse reinforcement learning problems. The time complexity of the proposed method is linearly proportional to the cardinality of the action set, thus it can handle high-dimensional even continuous state spaces efficiently. We test the proposed method in a simulated environment to show its accuracy, and three clinical tasks to show how it can be used to evaluate a doctor’s proficiency.
Tasks
Published	2017-08-23
URL	http://arxiv.org/abs/1708.07738v1
PDF	http://arxiv.org/pdf/1708.07738v1.pdf
PWC	https://paperswithcode.com/paper/a-function-approximation-method-for-model
Repo
Framework

A Class of Logistic Functions for Approximating State-Inclusive Koopman Operators


Title	A Class of Logistic Functions for Approximating State-Inclusive Koopman Operators
Authors	Charles A. Johnson, Enoch Yeung
Abstract	An outstanding challenge in nonlinear systems theory is identification or learning of a given nonlinear system’s Koopman operator directly from data or models. Advances in extended dynamic mode decomposition approaches and machine learning methods have enabled data-driven discovery of Koopman operators, for both continuous and discrete-time systems. Since Koopman operators are often infinite-dimensional, they are approximated in practice using finite-dimensional systems. The fidelity and convergence of a given finite-dimensional Koopman approximation is a subject of ongoing research. In this paper we introduce a class of Koopman observable functions that confer an approximate closure property on their corresponding finite-dimensional approximations of the Koopman operator. We derive error bounds for the fidelity of this class of observable functions, as well as identify two key learning parameters which can be used to tune performance. We illustrate our approach on two classical nonlinear system models: the Van Der Pol oscillator and the bistable toggle switch.
Tasks
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03132v1
PDF	http://arxiv.org/pdf/1712.03132v1.pdf
PWC	https://paperswithcode.com/paper/a-class-of-logistic-functions-for
Repo
Framework

Tumour Ellipsification in Ultrasound Images for Treatment Prediction in Breast Cancer


Title	Tumour Ellipsification in Ultrasound Images for Treatment Prediction in Breast Cancer
Authors	Mehrdad J. Gangeh, Hamid R. Tizhoosh, Kan Wu, Dun Huang, Hadi Tadayyon, Gregory J. Czarnota
Abstract	Recent advances in using quantitative ultrasound (QUS) methods have provided a promising framework to non-invasively and inexpensively monitor or predict the effectiveness of therapeutic cancer responses. One of the earliest steps in using QUS methods is contouring a region of interest (ROI) inside the tumour in ultrasound B-mode images. While manual segmentation is a very time-consuming and tedious task for human experts, auto-contouring is also an extremely difficult task for computers due to the poor quality of ultrasound B-mode images. However, for the purpose of cancer response prediction, a rough boundary of the tumour as an ROI is only needed. In this research, a semi-automated tumour localization approach is proposed for ROI estimation in ultrasound B-mode images acquired from patients with locally advanced breast cancer (LABC). The proposed approach comprised several modules, including 1) feature extraction using keypoint descriptors, 2) augmenting the feature descriptors with the distance of the keypoints to the user-input pixel as the centre of the tumour, 3) supervised learning using a support vector machine (SVM) to classify keypoints as “tumour” or “non-tumour”, and 4) computation of an ellipse as an outline of the ROI representing the tumour. Experiments with 33 B-mode images from 10 LABC patients yielded promising results with an accuracy of 76.7% based on the Dice coefficient performance measure. The results demonstrated that the proposed method can potentially be used as the first stage in a computer-assisted cancer response prediction system for semi-automated contouring of breast tumours.
Tasks
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03779v1
PDF	http://arxiv.org/pdf/1701.03779v1.pdf
PWC	https://paperswithcode.com/paper/tumour-ellipsification-in-ultrasound-images
Repo
Framework

Objects that Sound


Title	Objects that Sound
Authors	Relja Arandjelović, Andrew Zisserman
Abstract	In this paper our objectives are, first, networks that can embed audio and visual inputs into a common space that is suitable for cross-modal retrieval; and second, a network that can localize the object that sounds in an image, given the audio signal. We achieve both these objectives by training from unlabelled video using only audio-visual correspondence (AVC) as the objective function. This is a form of cross-modal self-supervision from video. To this end, we design new network architectures that can be trained for cross-modal retrieval and localizing the sound source in an image, by using the AVC task. We make the following contributions: (i) show that audio and visual embeddings can be learnt that enable both within-mode (e.g. audio-to-audio) and between-mode retrieval; (ii) explore various architectures for the AVC task, including those for the visual stream that ingest a single image, or multiple images, or a single image and multi-frame optical flow; (iii) show that the semantic object that sounds within an image can be localized (using only the sound, no motion or flow information); and (iv) give a cautionary tale on how to avoid undesirable shortcuts in the data preparation.
Tasks	Cross-Modal Retrieval, Optical Flow Estimation
Published	2017-12-18
URL	http://arxiv.org/abs/1712.06651v2
PDF	http://arxiv.org/pdf/1712.06651v2.pdf
PWC	https://paperswithcode.com/paper/objects-that-sound
Repo
Framework

On denoising modulo 1 samples of a function


Title	On denoising modulo 1 samples of a function
Authors	Mihai Cucuringu, Hemant Tyagi
Abstract	Consider an unknown smooth function $f: [0,1] \rightarrow \mathbb{R}$, and say we are given $n$ noisy$\mod 1$ samples of $f$, i.e., $y_i = (f(x_i) + \eta_i)\mod 1$ for $x_i \in [0,1]$, where $\eta_i$ denotes noise. Given the samples $(x_i,y_i)_{i=1}^{n}$ our goal is to recover smooth, robust estimates of the clean samples $f(x_i) \bmod 1$. We formulate a natural approach for solving this problem which works with representations of mod 1 values over the unit circle. This amounts to solving a quadratically constrained quadratic program (QCQP) with non-convex constraints involving points lying on the unit circle. Our proposed approach is based on solving its relaxation which is a trust-region sub-problem, and hence solvable efficiently. We demonstrate its robustness to noise % of our approach via extensive simulations on several synthetic examples, and provide a detailed theoretical analysis.
Tasks	Denoising
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10210v4
PDF	http://arxiv.org/pdf/1710.10210v4.pdf
PWC	https://paperswithcode.com/paper/on-denoising-modulo-1-samples-of-a-function
Repo
Framework

Localizing Actions from Video Labels and Pseudo-Annotations


Title	Localizing Actions from Video Labels and Pseudo-Annotations
Authors	Pascal Mettes, Cees G. M. Snoek, Shih-Fu Chang
Abstract	The goal of this paper is to determine the spatio-temporal location of actions in video. Where training from hard to obtain box annotations is the norm, we propose an intuitive and effective algorithm that localizes actions from their class label only. We are inspired by recent work showing that unsupervised action proposals selected with human point-supervision perform as well as using expensive box annotations. Rather than asking users to provide point supervision, we propose fully automatic visual cues that replace manual point annotations. We call the cues pseudo-annotations, introduce five of them, and propose a correlation metric for automatically selecting and combining them. Thorough evaluation on challenging action localization datasets shows that we reach results comparable to results with full box supervision. We also show that pseudo-annotations can be leveraged during testing to improve weakly- and strongly-supervised localizers.
Tasks	Action Localization
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09143v1
PDF	http://arxiv.org/pdf/1707.09143v1.pdf
PWC	https://paperswithcode.com/paper/localizing-actions-from-video-labels-and
Repo
Framework

Spectral Modes of Network Dynamics Reveal Increased Informational Complexity Near Criticality


Title	Spectral Modes of Network Dynamics Reveal Increased Informational Complexity Near Criticality
Authors	Xerxes D. Arsiwalla, Pedro A. M. Mediano, Paul F. M. J. Verschure
Abstract	What does the informational complexity of dynamical networked systems tell us about intrinsic mechanisms and functions of these complex systems? Recent complexity measures such as integrated information have sought to operationalize this problem taking a whole-versus-parts perspective, wherein one explicitly computes the amount of information generated by a network as a whole over and above that generated by the sum of its parts during state transitions. While several numerical schemes for estimating network integrated information exist, it is instructive to pursue an analytic approach that computes integrated information as a function of network weights. Our formulation of integrated information uses a Kullback-Leibler divergence between the multi-variate distribution on the set of network states versus the corresponding factorized distribution over its parts. Implementing stochastic Gaussian dynamics, we perform computations for several prototypical network topologies. Our findings show increased informational complexity near criticality, which remains consistent across network topologies. Spectral decomposition of the system’s dynamics reveals how informational complexity is governed by eigenmodes of both, the network’s covariance and adjacency matrices. We find that as the dynamics of the system approach criticality, high integrated information is exclusively driven by the eigenmode corresponding to the leading eigenvalue of the covariance matrix, while sub-leading modes get suppressed. The implication of this result is that it might be favorable for complex dynamical networked systems such as the human brain or communication systems to operate near criticality so that efficient information integration might be achieved.
Tasks
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01446v1
PDF	http://arxiv.org/pdf/1707.01446v1.pdf
PWC	https://paperswithcode.com/paper/spectral-modes-of-network-dynamics-reveal
Repo
Framework

Semi-supervised Conditional GANs


Title	Semi-supervised Conditional GANs
Authors	Kumar Sricharan, Raja Bala, Matthew Shreve, Hui Ding, Kumar Saketh, Jin Sun
Abstract	We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework. The proposed semi-supervised GAN (SS-GAN) model uses a pair of stacked discriminators to learn the marginal distribution of the data, and the conditional distribution of the attributes given the data respectively. In the semi-supervised setting, the marginal distribution (which is often harder to learn) is learned from the labeled + unlabeled data, and the conditional distribution is learned purely from the labeled data. Our experimental results demonstrate that this model performs significantly better compared to existing semi-supervised conditional GAN models.
Tasks
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05789v1
PDF	http://arxiv.org/pdf/1708.05789v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-conditional-gans
Repo
Framework

Deep Learning Scaling is Predictable, Empirically


Title	Deep Learning Scaling is Predictable, Empirically
Authors	Joel Hestness, Sharan Narang, Newsha Ardalani, Gregory Diamos, Heewoo Jun, Hassan Kianinejad, Md. Mostofa Ali Patwary, Yang Yang, Yanqi Zhou
Abstract	Deep learning (DL) creates impactful advances following a virtuous recipe: model architecture search, creating large training data sets, and scaling computation. It is widely believed that growing training sets and models should improve accuracy and result in better products. As DL application domains grow, we would like a deeper understanding of the relationships between training set size, computational scale, and model accuracy improvements to advance the state-of-the-art. This paper presents a large scale empirical characterization of generalization error and model size growth as training sets grow. We introduce a methodology for this measurement and test four machine learning domains: machine translation, language modeling, image processing, and speech recognition. Our empirical results show power-law generalization error scaling across a breadth of factors, resulting in power-law exponents—the “steepness” of the learning curve—yet to be explained by theoretical work. Further, model improvements only shift the error but do not appear to affect the power-law exponent. We also show that model size scales sublinearly with data size. These scaling relationships have significant implications on deep learning research, practice, and systems. They can assist model debugging, setting accuracy targets, and decisions about data set growth. They can also guide computing system design and underscore the importance of continued computational scaling.
Tasks	Language Modelling, Machine Translation, Neural Architecture Search, Speech Recognition
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00409v1
PDF	http://arxiv.org/pdf/1712.00409v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-scaling-is-predictable
Repo
Framework

Brain Intelligence: Go Beyond Artificial Intelligence


Title	Brain Intelligence: Go Beyond Artificial Intelligence
Authors	Huimin Lu, Yujie Li, Min Chen, Hyoungseop Kim, Seiichi Serikawa
Abstract	Artificial intelligence (AI) is an important technology that supports daily social life and economic activities. It contributes greatly to the sustainable growth of Japan’s economy and solves various social problems. In recent years, AI has attracted attention as a key for growth in developed countries such as Europe and the United States and developing countries such as China and India. The attention has been focused mainly on developing new artificial intelligence information communication technology (ICT) and robot technology (RT). Although recently developed AI technology certainly excels in extracting certain patterns, there are many limitations. Most ICT models are overly dependent on big data, lack a self-idea function, and are complicated. In this paper, rather than merely developing next-generation artificial intelligence technology, we aim to develop a new concept of general-purpose intelligence cognition technology called Beyond AI. Specifically, we plan to develop an intelligent learning model called Brain Intelligence (BI) that generates new ideas about events without having experienced them by using artificial life with an imagine function. We will also conduct demonstrations of the developed BI intelligence learning model on automatic driving, precision medical care, and industrial robots.
Tasks	Artificial Life
Published	2017-06-04
URL	http://arxiv.org/abs/1706.01040v1
PDF	http://arxiv.org/pdf/1706.01040v1.pdf
PWC	https://paperswithcode.com/paper/brain-intelligence-go-beyond-artificial
Repo
Framework

Prune the Convolutional Neural Networks with Sparse Shrink


Title	Prune the Convolutional Neural Networks with Sparse Shrink
Authors	Xin Li, Changsong Liu
Abstract	Nowadays, it is still difficult to adapt Convolutional Neural Network (CNN) based models for deployment on embedded devices. The heavy computation and large memory footprint of CNN models become the main burden in real application. In this paper, we propose a “Sparse Shrink” algorithm to prune an existing CNN model. By analyzing the importance of each channel via sparse reconstruction, the algorithm is able to prune redundant feature maps accordingly. The resulting pruned model thus directly saves computational resource. We have evaluated our algorithm on CIFAR-100. As shown in our experiments, we can reduce 56.77% parameters and 73.84% multiplication in total with only minor decrease in accuracy. These results have demonstrated the effectiveness of our “Sparse Shrink” algorithm.
Tasks
Published	2017-08-08
URL	http://arxiv.org/abs/1708.02439v1
PDF	http://arxiv.org/pdf/1708.02439v1.pdf
PWC	https://paperswithcode.com/paper/prune-the-convolutional-neural-networks-with
Repo
Framework

Optimal Subsampling for Large Sample Logistic Regression


Title	Optimal Subsampling for Large Sample Logistic Regression
Authors	HaiYing Wang, Rong Zhu, Ping Ma
Abstract	For massive data, the family of subsampling algorithms is popular to downsize the data volume and reduce computational burden. Existing studies focus on approximating the ordinary least squares estimate in linear regression, where statistical leverage scores are often used to define subsampling probabilities. In this paper, we propose fast subsampling algorithms to efficiently approximate the maximum likelihood estimate in logistic regression. We first establish consistency and asymptotic normality of the estimator from a general subsampling algorithm, and then derive optimal subsampling probabilities that minimize the asymptotic mean squared error of the resultant estimator. An alternative minimization criterion is also proposed to further reduce the computational cost. The optimal subsampling probabilities depend on the full data estimate, so we develop a two-step algorithm to approximate the optimal subsampling procedure. This algorithm is computationally efficient and has a significant reduction in computing time compared to the full data approach. Consistency and asymptotic normality of the estimator from a two-step algorithm are also established. Synthetic and real data sets are used to evaluate the practical performance of the proposed method.
Tasks
Published	2017-02-03
URL	http://arxiv.org/abs/1702.01166v2
PDF	http://arxiv.org/pdf/1702.01166v2.pdf
PWC	https://paperswithcode.com/paper/optimal-subsampling-for-large-sample-logistic
Repo
Framework

Variance Reduced methods for Non-convex Composition Optimization


Title	Variance Reduced methods for Non-convex Composition Optimization
Authors	Liu Liu, Ji Liu, Dacheng Tao
Abstract	This paper explores the non-convex composition optimization in the form including inner and outer finite-sum functions with a large number of component functions. This problem arises in some important applications such as nonlinear embedding and reinforcement learning. Although existing approaches such as stochastic gradient descent (SGD) and stochastic variance reduced gradient (SVRG) descent can be applied to solve this problem, their query complexity tends to be high, especially when the number of inner component functions is large. In this paper, we apply the variance-reduced technique to derive two variance reduced algorithms that significantly improve the query complexity if the number of inner component functions is large. To the best of our knowledge, this is the first work that establishes the query complexity analysis for non-convex stochastic composition. Experiments validate the proposed algorithms and theoretical analysis.
Tasks
Published	2017-11-13
URL	http://arxiv.org/abs/1711.04416v1
PDF	http://arxiv.org/pdf/1711.04416v1.pdf
PWC	https://paperswithcode.com/paper/variance-reduced-methods-for-non-convex
Repo
Framework

Supervised Hashing based on Energy Minimization


Title	Supervised Hashing based on Energy Minimization
Authors	Zihao Hu, Xiyi Luo, Hongtao Lu, Yong Yu
Abstract	Recently, supervised hashing methods have attracted much attention since they can optimize retrieval speed and storage cost while preserving semantic information. Because hashing codes learning is NP-hard, many methods resort to some form of relaxation technique. But the performance of these methods can easily deteriorate due to the relaxation. Luckily, many supervised hashing formulations can be viewed as energy functions, hence solving hashing codes is equivalent to learning marginals in the corresponding conditional random field (CRF). By minimizing the KL divergence between a fully factorized distribution and the Gibbs distribution of this CRF, a set of consistency equations can be obtained, but updating them in parallel may not yield a local optimum since the variational lower bound is not guaranteed to increase. In this paper, we use a linear approximation of the sigmoid function to convert these consistency equations to linear systems, which have a closed-form solution. By applying this novel technique to two classical hashing formulations KSH and SPLH, we obtain two new methods called EM (energy minimizing based)-KSH and EM-SPLH. Experimental results on three datasets show the superiority of our methods.
Tasks
Published	2017-12-02
URL	http://arxiv.org/abs/1712.00573v1
PDF	http://arxiv.org/pdf/1712.00573v1.pdf
PWC	https://paperswithcode.com/paper/supervised-hashing-based-on-energy
Repo
Framework

Safe Learning of Quadrotor Dynamics Using Barrier Certificates


Title	Safe Learning of Quadrotor Dynamics Using Barrier Certificates
Authors	Li Wang, Evangelos A. Theodorou, Magnus Egerstedt
Abstract	To effectively control complex dynamical systems, accurate nonlinear models are typically needed. However, these models are not always known. In this paper, we present a data-driven approach based on Gaussian processes that learns models of quadrotors operating in partially unknown environments. What makes this challenging is that if the learning process is not carefully controlled, the system will go unstable, i.e., the quadcopter will crash. To this end, barrier certificates are employed for safe learning. The barrier certificates establish a non-conservative forward invariant safe region, in which high probability safety guarantees are provided based on the statistics of the Gaussian Process. A learning controller is designed to efficiently explore those uncertain states and expand the barrier certified safe region based on an adaptive sampling scheme. In addition, a recursive Gaussian Process prediction method is developed to learn the complex quadrotor dynamics in real-time. Simulation results are provided to demonstrate the effectiveness of the proposed approach.
Tasks	Gaussian Processes
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05472v1
PDF	http://arxiv.org/pdf/1710.05472v1.pdf
PWC	https://paperswithcode.com/paper/safe-learning-of-quadrotor-dynamics-using
Repo
Framework