July 28, 2019

3134 words 15 mins read

Paper Group ANR 410

Transformational Sparse Coding. Large-scale analysis of disease pathways in the human interactome. Deformation estimation of an elastic object by partial observation using a neural network. Mean Field Residual Networks: On the Edge of Chaos. Efficiency of quantum versus classical annealing in non-convex learning problems. Vehicle Routing Problem wi …

Transformational Sparse Coding


Title	Transformational Sparse Coding
Authors	Dimitrios C. Gklezakos, Rajesh P. N. Rao
Abstract	A fundamental problem faced by object recognition systems is that objects and their features can appear in different locations, scales and orientations. Current deep learning methods attempt to achieve invariance to local translations via pooling, discarding the locations of features in the process. Other approaches explicitly learn transformed versions of the same feature, leading to representations that quickly explode in size. Instead of discarding the rich and useful information about feature transformations to achieve invariance, we argue that models should learn object features conjointly with their transformations to achieve equivariance. We propose a new model of unsupervised learning based on sparse coding that can learn object features jointly with their affine transformations directly from images. Results based on learning from natural images indicate that our approach matches the reconstruction quality of traditional sparse coding but with significantly fewer degrees of freedom while simultaneously learning transformations from data. These results open the door to scaling up unsupervised learning to allow deep feature+transformation learning in a manner consistent with the ventral+dorsal stream architecture of the primate visual cortex.
Tasks	Object Recognition
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03257v1
PDF	http://arxiv.org/pdf/1712.03257v1.pdf
PWC	https://paperswithcode.com/paper/transformational-sparse-coding
Repo
Framework

Large-scale analysis of disease pathways in the human interactome


Title	Large-scale analysis of disease pathways in the human interactome
Authors	Monica Agrawal, Marinka Zitnik, Jure Leskovec
Abstract	Discovering disease pathways, which can be defined as sets of proteins associated with a given disease, is an important problem that has the potential to provide clinically actionable insights for disease diagnosis, prognosis, and treatment. Computational methods aid the discovery by relying on protein-protein interaction (PPI) networks. They start with a few known disease-associated proteins and aim to find the rest of the pathway by exploring the PPI network around the known disease proteins. However, the success of such methods has been limited, and failure cases have not been well understood. Here we study the PPI network structure of 519 disease pathways. We find that 90% of pathways do not correspond to single well-connected components in the PPI network. Instead, proteins associated with a single disease tend to form many separate connected components/regions in the network. We then evaluate state-of-the-art disease pathway discovery methods and show that their performance is especially poor on diseases with disconnected pathways. Thus, we conclude that network connectivity structure alone may not be sufficient for disease pathway discovery. However, we show that higher-order network structures, such as small subgraphs of the pathway, provide a promising direction for the development of new methods.
Tasks
Published	2017-12-03
URL	http://arxiv.org/abs/1712.00843v1
PDF	http://arxiv.org/pdf/1712.00843v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-analysis-of-disease-pathways-in
Repo
Framework

Deformation estimation of an elastic object by partial observation using a neural network


Title	Deformation estimation of an elastic object by partial observation using a neural network
Authors	Utako Yamamoto, Megumi Nakao, Masayuki Ohzeki, Tetsuya Matsuda
Abstract	Deformation estimation of elastic object assuming an internal organ is important for the computer navigation of surgery. The aim of this study is to estimate the deformation of an entire three-dimensional elastic object using displacement information of very few observation points. A learning approach with a neural network was introduced to estimate the entire deformation of an object. We applied our method to two elastic objects; a rectangular parallelepiped model, and a human liver model reconstructed from computed tomography data. The average estimation error for the human liver model was 0.041 mm when the object was deformed up to 66.4 mm, from only around 3 % observations. These results indicate that the deformation of an entire elastic object can be estimated with an acceptable level of error from limited observations by applying a trained neural network to a new deformation.
Tasks
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10157v1
PDF	http://arxiv.org/pdf/1711.10157v1.pdf
PWC	https://paperswithcode.com/paper/deformation-estimation-of-an-elastic-object
Repo
Framework

Mean Field Residual Networks: On the Edge of Chaos


Title	Mean Field Residual Networks: On the Edge of Chaos
Authors	Greg Yang, Samuel S. Schoenholz
Abstract	We study randomly initialized residual networks using mean field theory and the theory of difference equations. Classical feedforward neural networks, such as those with tanh activations, exhibit exponential behavior on the average when propagating inputs forward or gradients backward. The exponential forward dynamics causes rapid collapsing of the input space geometry, while the exponential backward dynamics causes drastic vanishing or exploding gradients. We show, in contrast, that by adding skip connections, the network will, depending on the nonlinearity, adopt subexponential forward and backward dynamics, and in many cases in fact polynomial. The exponents of these polynomials are obtained through analytic methods and proved and verified empirically to be correct. In terms of the “edge of chaos” hypothesis, these subexponential and polynomial laws allow residual networks to “hover over the boundary between stability and chaos,” thus preserving the geometry of the input space and the gradient information flow. In our experiments, for each activation function we study here, we initialize residual networks with different hyperparameters and train them on MNIST. Remarkably, our initialization time theory can accurately predict test time performance of these networks, by tracking either the expected amount of gradient explosion or the expected squared distance between the images of two input vectors. Importantly, we show, theoretically as well as empirically, that common initializations such as the Xavier or the He schemes are not optimal for residual networks, because the optimal initialization variances depend on the depth. Finally, we have made mathematical contributions by deriving several new identities for the kernels of powers of ReLU functions by relating them to the zeroth Bessel function of the second kind.
Tasks
Published	2017-12-24
URL	http://arxiv.org/abs/1712.08969v1
PDF	http://arxiv.org/pdf/1712.08969v1.pdf
PWC	https://paperswithcode.com/paper/mean-field-residual-networks-on-the-edge-of-1
Repo
Framework

Efficiency of quantum versus classical annealing in non-convex learning problems


Title	Efficiency of quantum versus classical annealing in non-convex learning problems
Authors	Carlo Baldassi, Riccardo Zecchina
Abstract	Quantum annealers aim at solving non-convex optimization problems by exploiting cooperative tunneling effects to escape local minima. The underlying idea consists in designing a classical energy function whose ground states are the sought optimal solutions of the original optimization problem and add a controllable quantum transverse field to generate tunneling processes. A key challenge is to identify classes of non-convex optimization problems for which quantum annealing remains efficient while thermal annealing fails. We show that this happens for a wide class of problems which are central to machine learning. Their energy landscapes is dominated by local minima that cause exponential slow down of classical thermal annealers while simulated quantum annealing converges efficiently to rare dense regions of optimal solutions.
Tasks
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08470v3
PDF	http://arxiv.org/pdf/1706.08470v3.pdf
PWC	https://paperswithcode.com/paper/efficiency-of-quantum-versus-classical
Repo
Framework

Vehicle Routing Problem with Vector Profits (VRPVP) with Max-Min Criterion


Title	Vehicle Routing Problem with Vector Profits (VRPVP) with Max-Min Criterion
Authors	Dongoo Lee, Jaemyung Ahn
Abstract	This paper introduces a new routing problem referred to as the vehicle routing problem with vector profits. Given a network composed of nodes (depot/sites) and arcs connecting the nodes, the problem determines routes that depart from the depot, visit sites to collect profits, and return to the depot. There are multiple stakeholders interested in the mission and each site is associated with a vector whose k-th element represents the profit value for the k-th stakeholder. The objective of the problem is to maximize the profit sum for the least satisfied stakeholder, i.e., the stakeholder with the smallest total profit value. An approach based on the linear programming relaxation and column-generation to solve this max-min type routing problem was developed. Two cases studies - the planetary surface exploration and the Rome tour cases - were presented to demonstrate the effectiveness of the proposed problem formulation and solution methodology.
Tasks
Published	2017-10-29
URL	http://arxiv.org/abs/1710.10550v1
PDF	http://arxiv.org/pdf/1710.10550v1.pdf
PWC	https://paperswithcode.com/paper/vehicle-routing-problem-with-vector-profits
Repo
Framework

AI Challenges in Human-Robot Cognitive Teaming


Title	AI Challenges in Human-Robot Cognitive Teaming
Authors	Tathagata Chakraborti, Subbarao Kambhampati, Matthias Scheutz, Yu Zhang
Abstract	Among the many anticipated roles for robots in the future is that of being a human teammate. Aside from all the technological hurdles that have to be overcome with respect to hardware and control to make robots fit to work with humans, the added complication here is that humans have many conscious and subconscious expectations of their teammates - indeed, we argue that teaming is mostly a cognitive rather than physical coordination activity. This introduces new challenges for the AI and robotics community and requires fundamental changes to the traditional approach to the design of autonomy. With this in mind, we propose an update to the classical view of the intelligent agent architecture, highlighting the requirements for mental modeling of the human in the deliberative process of the autonomous agent. In this article, we outline briefly the recent efforts of ours, and others in the community, towards developing cognitive teammates along these guidelines.
Tasks
Published	2017-07-15
URL	http://arxiv.org/abs/1707.04775v2
PDF	http://arxiv.org/pdf/1707.04775v2.pdf
PWC	https://paperswithcode.com/paper/ai-challenges-in-human-robot-cognitive
Repo
Framework

Learning to detect chest radiographs containing lung nodules using visual attention networks


Title	Learning to detect chest radiographs containing lung nodules using visual attention networks
Authors	Emanuele Pesce, Petros-Pavlos Ypsilantis, Samuel Withey, Robert Bakewell, Vicky Goh, Giovanni Montana
Abstract	Machine learning approaches hold great potential for the automated detection of lung nodules in chest radiographs, but training the algorithms requires vary large amounts of manually annotated images, which are difficult to obtain. Weak labels indicating whether a radiograph is likely to contain pulmonary nodules are typically easier to obtain at scale by parsing historical free-text radiological reports associated to the radiographs. Using a repositotory of over 700,000 chest radiographs, in this study we demonstrate that promising nodule detection performance can be achieved using weak labels through convolutional neural networks for radiograph classification. We propose two network architectures for the classification of images likely to contain pulmonary nodules using both weak labels and manually-delineated bounding boxes, when these are available. Annotated nodules are used at training time to deliver a visual attention mechanism informing the model about its localisation performance. The first architecture extracts saliency maps from high-level convolutional layers and compares the estimated position of a nodule against the ground truth, when this is available. A corresponding localisation error is then back-propagated along with the softmax classification error. The second approach consists of a recurrent attention model that learns to observe a short sequence of smaller image portions through reinforcement learning. When a nodule annotation is available at training time, the reward function is modified accordingly so that exploring portions of the radiographs away from a nodule incurs a larger penalty. Our empirical results demonstrate the potential advantages of these architectures in comparison to competing methodologies.
Tasks
Published	2017-12-04
URL	http://arxiv.org/abs/1712.00996v3
PDF	http://arxiv.org/pdf/1712.00996v3.pdf
PWC	https://paperswithcode.com/paper/learning-to-detect-chest-radiographs
Repo
Framework

Strictly proper kernel scores and characteristic kernels on compact spaces


Title	Strictly proper kernel scores and characteristic kernels on compact spaces
Authors	Ingo Steinwart, Johanna F. Ziegel
Abstract	Strictly proper kernel scores are well-known tool in probabilistic forecasting, while characteristic kernels have been extensively investigated in the machine learning literature. We first show that both notions coincide, so that insights from one part of the literature can be used in the other. We then show that the metric induced by a characteristic kernel cannot reliably distinguish between distributions that are far apart in the total variation norm as soon as the underlying space of measures is infinite dimensional. In addition, we provide a characterization of characteristic kernels in terms of eigenvalues and -functions and apply this characterization to the case of continuous kernels on (locally) compact spaces. In the compact case we further show that characteristic kernels exist if and only if the space is metrizable. As special cases of our general theory we investigate translation-invariant kernels on compact Abelian groups and isotropic kernels on spheres. The latter are of particular interest for forecast evaluation of probabilistic predictions on spherical domains as frequently encountered in meteorology and climatology.
Tasks
Published	2017-12-14
URL	http://arxiv.org/abs/1712.05279v1
PDF	http://arxiv.org/pdf/1712.05279v1.pdf
PWC	https://paperswithcode.com/paper/strictly-proper-kernel-scores-and
Repo
Framework

GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval


Title	GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
Authors	Longhui Wei, Shiliang Zhang, Hantao Yao, Wen Gao, Qi Tian
Abstract	The huge variance of human pose and the misalignment of detected human images significantly increase the difficulty of person Re-Identification (Re-ID). Moreover, efficient Re-ID systems are required to cope with the massive visual data being produced by video surveillance systems. Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively. GLAD explicitly leverages the local and global cues in human body to generate a discriminative and robust representation. It consists of part extraction and descriptor learning modules, where several part regions are first detected and then deep neural networks are designed for representation learning on both the local and global regions. A hierarchical indexing and retrieval framework is designed to eliminate the huge redundancy in the gallery set, and accelerate the online Re-ID procedure. Extensive experimental results show GLAD achieves competitive accuracy compared to the state-of-the-art methods. Our retrieval framework significantly accelerates the online Re-ID procedure without loss of accuracy. Therefore, this work has potential to work better on person Re-ID tasks in real scenarios.
Tasks	Person Re-Identification, Representation Learning
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04329v1
PDF	http://arxiv.org/pdf/1709.04329v1.pdf
PWC	https://paperswithcode.com/paper/glad-global-local-alignment-descriptor-for
Repo
Framework

Photographic dataset: playing cards


Title	Photographic dataset: playing cards
Authors	David Villacis, Santeri Kaupinmäki, Samuli Siltanen, Teemu Helenius
Abstract	This is a photographic dataset collected for testing image processing algorithms. The idea is to have images that can exploit the properties of total variation, therefore a set of playing cards was distributed on the scene. The dataset is made available at www.fips.fi/photographic_dataset2.php
Tasks
Published	2017-01-25
URL	http://arxiv.org/abs/1701.07354v1
PDF	http://arxiv.org/pdf/1701.07354v1.pdf
PWC	https://paperswithcode.com/paper/photographic-dataset-playing-cards
Repo
Framework

Link Mining for Kernel-based Compound-Protein Interaction Predictions Using a Chemogenomics Approach


Title	Link Mining for Kernel-based Compound-Protein Interaction Predictions Using a Chemogenomics Approach
Authors	Masahito Ohue, Takuro Yamazaki, Tomohiro Ban, Yutaka Akiyama
Abstract	Virtual screening (VS) is widely used during computational drug discovery to reduce costs. Chemogenomics-based virtual screening (CGBVS) can be used to predict new compound-protein interactions (CPIs) from known CPI network data using several methods, including machine learning and data mining. Although CGBVS facilitates highly efficient and accurate CPI prediction, it has poor performance for prediction of new compounds for which CPIs are unknown. The pairwise kernel method (PKM) is a state-of-the-art CGBVS method and shows high accuracy for prediction of new compounds. In this study, on the basis of link mining, we improved the PKM by combining link indicator kernel (LIK) and chemical similarity and evaluated the accuracy of these methods. The proposed method obtained an average area under the precision-recall curve (AUPR) value of 0.562, which was higher than that achieved by the conventional Gaussian interaction profile (GIP) method (0.425), and the calculation time was only increased by a few percent.
Tasks	Drug Discovery
Published	2017-05-04
URL	http://arxiv.org/abs/1705.01667v2
PDF	http://arxiv.org/pdf/1705.01667v2.pdf
PWC	https://paperswithcode.com/paper/link-mining-for-kernel-based-compound-protein
Repo
Framework

End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning


Title	End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
Authors	Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah, Larry Heck
Abstract	In this paper, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep reinforcement learning (RL). The system is able to track dialogue state, interface with knowledge bases, and incorporate query results into agent’s responses to successfully complete task-oriented dialogues. Dialogue policy learning is conducted with a hybrid supervised and deep RL methods. We first train the dialogue agent in a supervised manner by learning directly from task-oriented dialogue corpora, and further optimize it with deep RL during its interaction with users. In the experiments on two different dialogue task domains, our model demonstrates robust performance in tracking dialogue state and producing reasonable system responses. We show that deep RL based optimization leads to significant improvement on task success rate and reduction in dialogue length comparing to supervised training model. We further show benefits of training task-oriented dialogue model end-to-end comparing to component-wise optimization with experiment results on dialogue simulations and human evaluations.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10712v2
PDF	http://arxiv.org/pdf/1711.10712v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-optimization-of-task-oriented
Repo
Framework

Understanding trained CNNs by indexing neuron selectivity


Title	Understanding trained CNNs by indexing neuron selectivity
Authors	Ivet Rafegas, Maria Vanrell, Luis A. Alexandre, Guillem Arias
Abstract	The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these representations are organized. To help understanding these issues, we propose to describe the activity of individual neurons by their Neuron Feature visualization and quantify their inherent selectivity with two specific properties. We explore selectivity indexes for: an image feature (color); and an image label (class membership). Our contribution is a framework to seek or classify neurons by indexing on these selectivity properties. It helps to find color selective neurons, such as a red-mushroom neuron in layer Conv4 or class selective neurons such as dog-face neurons in layer Conv5 in VGG-M, and establishes a methodology to derive other selectivity properties. Indexing on neuron selectivity can statistically draw how features and classes are represented through layers in a moment when the size of trained nets is growing and automatic tools to index neurons can be helpful.
Tasks
Published	2017-02-01
URL	https://arxiv.org/abs/1702.00382v2
PDF	https://arxiv.org/pdf/1702.00382v2.pdf
PWC	https://paperswithcode.com/paper/understanding-trained-cnns-by-indexing-neuron
Repo
Framework

Generating Nontrivial Melodies for Music as a Service


Title	Generating Nontrivial Melodies for Music as a Service
Authors	Yifei Teng, An Zhao, Camille Goudeseune
Abstract	We present a hybrid neural network and rule-based system that generates pop music. Music produced by pure rule-based systems often sounds mechanical. Music produced by machine learning sounds better, but still lacks hierarchical temporal structure. We restore temporal hierarchy by augmenting machine learning with a temporal production grammar, which generates the music’s overall structure and chord progressions. A compatible melody is then generated by a conditional variational recurrent autoencoder. The autoencoder is trained with eight-measure segments from a corpus of 10,000 MIDI files, each of which has had its melody track and chord progressions identified heuristically. The autoencoder maps melody into a multi-dimensional feature space, conditioned by the underlying chord progression. A melody is then generated by feeding a random sample from that space to the autoencoder’s decoder, along with the chord progression generated by the grammar. The autoencoder can make musically plausible variations on an existing melody, suitable for recurring motifs. It can also reharmonize a melody to a new chord progression, keeping the rhythm and contour. The generated music compares favorably with that generated by other academic and commercial software designed for the music-as-a-service industry.
Tasks
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02280v1
PDF	http://arxiv.org/pdf/1710.02280v1.pdf
PWC	https://paperswithcode.com/paper/generating-nontrivial-melodies-for-music-as-a
Repo
Framework