October 18, 2019

3336 words 16 mins read

Paper Group ANR 569

An Industrial Case Study on Shrinking Code Review Changesets through Remark Prediction. Lifted Neural Networks. Artwork Identification from Wearable Camera Images for Enhancing Experience of Museum Audiences. On Machine Learning and Structure for Mobile Robots. Correcting the bias in least squares regression with volume-rescaled sampling. Monitorin …

An Industrial Case Study on Shrinking Code Review Changesets through Remark Prediction


Title	An Industrial Case Study on Shrinking Code Review Changesets through Remark Prediction
Authors	Tobias Baum, Steffen Herbold, Kurt Schneider
Abstract	Change-based code review is used widely in industrial software development. Thus, research on tools that help the reviewer to achieve better review performance can have a high impact. We analyze one possibility to provide cognitive support for the reviewer: Determining the importance of change parts for review, specifically determining which parts of the code change can be left out from the review without harm. To determine the importance of change parts, we extract data from software repositories and build prediction models for review remarks based on this data. The approach is discussed in detail. To gather the input data, we propose a novel algorithm to trace review remarks to their triggers. We apply our approach in a medium-sized software company. In this company, we can avoid the review of 25% of the change parts and of 23% of the changed Java source code lines, while missing only about 1% of the review remarks. Still, we also observe severe limitations of the tried approach: Much of the savings are due to simple syntactic rules, noise in the data hampers the search for better prediction models, and some developers in the case company oppose the taken approach. Besides the main results on the mining and prediction of triggers for review remarks, we contribute experiences with a novel, multi-objective and interactive rule mining approach. The anonymized dataset from the company is made available, as are the implementations for the devised algorithms.
Tasks
Published	2018-12-22
URL	http://arxiv.org/abs/1812.09510v1
PDF	http://arxiv.org/pdf/1812.09510v1.pdf
PWC	https://paperswithcode.com/paper/an-industrial-case-study-on-shrinking-code
Repo
Framework

Lifted Neural Networks


Title	Lifted Neural Networks
Authors	Armin Askari, Geoffrey Negiar, Rajiv Sambharya, Laurent El Ghaoui
Abstract	We describe a novel family of models of multi- layer feedforward neural networks in which the activation functions are encoded via penalties in the training problem. Our approach is based on representing a non-decreasing activation function as the argmin of an appropriate convex optimiza- tion problem. The new framework allows for algo- rithms such as block-coordinate descent methods to be applied, in which each step is composed of a simple (no hidden layer) supervised learning problem that is parallelizable across data points and/or layers. Experiments indicate that the pro- posed models provide excellent initial guesses for weights for standard neural networks. In addi- tion, the model provides avenues for interesting extensions, such as robustness against noisy in- puts and optimizing over parameters in activation functions.
Tasks
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01532v2
PDF	http://arxiv.org/pdf/1805.01532v2.pdf
PWC	https://paperswithcode.com/paper/lifted-neural-networks
Repo
Framework

Artwork Identification from Wearable Camera Images for Enhancing Experience of Museum Audiences


Title	Artwork Identification from Wearable Camera Images for Enhancing Experience of Museum Audiences
Authors	Rui Zhang, Yusuf Tas, Piotr Koniusz
Abstract	Recommendation systems based on image recognition could prove a vital tool in enhancing the experience of museum audiences. However, for practical systems utilizing wearable cameras, a number of challenges exist which affect the quality of image recognition. In this pilot study, we focus on recognition of museum collections by using a wearable camera in three different museum spaces. We discuss the application of wearable cameras, and the practical and technical challenges in devising a robust system that can recognize artworks viewed by the visitors to create a detailed record of their visit. Specifically, to illustrate the impact of different kinds of museum spaces on image recognition, we collect three training datasets of museum exhibits containing variety of paintings, clocks, and sculptures. Subsequently, we equip selected visitors with wearable cameras to capture artworks viewed by them as they stroll along exhibitions. We use Convolutional Neural Networks (CNN) which are pre-trained on the ImageNet dataset and fine-tuned on each of the training sets for the purpose of artwork identification. In the testing stage, we use CNNs to identify artworks captured by the visitors with a wearable camera. We analyze the accuracy of their recognition and provide an insight into the applicability of such a system to further engage audiences with museum exhibitions.
Tasks	Recommendation Systems
Published	2018-06-24
URL	http://arxiv.org/abs/1806.09084v1
PDF	http://arxiv.org/pdf/1806.09084v1.pdf
PWC	https://paperswithcode.com/paper/artwork-identification-from-wearable-camera
Repo
Framework

On Machine Learning and Structure for Mobile Robots


Title	On Machine Learning and Structure for Mobile Robots
Authors	Markus Wulfmeier
Abstract	Due to recent advances - compute, data, models - the role of learning in autonomous systems has expanded significantly, rendering new applications possible for the first time. While some of the most significant benefits are obtained in the perception modules of the software stack, other aspects continue to rely on known manual procedures based on prior knowledge on geometry, dynamics, kinematics etc. Nonetheless, learning gains relevance in these modules when data collection and curation become easier than manual rule design. Building on this coarse and broad survey of current research, the final sections aim to provide insights into future potentials and challenges as well as the necessity of structure in current practical applications.
Tasks
Published	2018-06-15
URL	http://arxiv.org/abs/1806.06003v1
PDF	http://arxiv.org/pdf/1806.06003v1.pdf
PWC	https://paperswithcode.com/paper/on-machine-learning-and-structure-for-mobile
Repo
Framework

Correcting the bias in least squares regression with volume-rescaled sampling


Title	Correcting the bias in least squares regression with volume-rescaled sampling
Authors	Michał Dereziński, Manfred K. Warmuth, Daniel Hsu
Abstract	Consider linear regression where the examples are generated by an unknown distribution on $R^d\times R$. Without any assumptions on the noise, the linear least squares solution for any i.i.d. sample will typically be biased w.r.t. the least squares optimum over the entire distribution. However, we show that if an i.i.d. sample of any size k is augmented by a certain small additional sample, then the solution of the combined sample becomes unbiased. We show this when the additional sample consists of d points drawn jointly according to the input distribution that is rescaled by the squared volume spanned by the points. Furthermore, we propose algorithms to sample from this volume-rescaled distribution when the data distribution is only known through an i.i.d sample.
Tasks
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02453v1
PDF	http://arxiv.org/pdf/1810.02453v1.pdf
PWC	https://paperswithcode.com/paper/correcting-the-bias-in-least-squares
Repo
Framework

Monitoring the shape of weather, soundscapes, and dynamical systems: a new statistic for dimension-driven data analysis on large data sets


Title	Monitoring the shape of weather, soundscapes, and dynamical systems: a new statistic for dimension-driven data analysis on large data sets
Authors	Henry Kvinge, Elin Farnell, Michael Kirby, Chris Peterson
Abstract	Dimensionality-reduction methods are a fundamental tool in the analysis of large data sets. These algorithms work on the assumption that the “intrinsic dimension” of the data is generally much smaller than the ambient dimension in which it is collected. Alongside their usual purpose of mapping data into a smaller dimension with minimal information loss, dimensionality-reduction techniques implicitly or explicitly provide information about the dimension of the data set. In this paper, we propose a new statistic that we call the $\kappa$-profile for analysis of large data sets. The $\kappa$-profile arises from a dimensionality-reduction optimization problem: namely that of finding a projection into $k$-dimensions that optimally preserves the secants between points in the data set. From this optimal projection we extract $\kappa,$ the norm of the shortest projected secant from among the set of all normalized secants. This $\kappa$ can be computed for any $k$; thus the tuple of $\kappa$ values (indexed by dimension) becomes a $\kappa$-profile. Algorithms such as the Secant-Avoidance Projection algorithm and the Hierarchical Secant-Avoidance Projection algorithm, provide a computationally feasible means of estimating the $\kappa$-profile for large data sets, and thus a method of understanding and monitoring their behavior. As we demonstrate in this paper, the $\kappa$-profile serves as a useful statistic in several representative settings: weather data, soundscape data, and dynamical systems data.
Tasks	Dimensionality Reduction
Published	2018-10-27
URL	http://arxiv.org/abs/1810.11562v1
PDF	http://arxiv.org/pdf/1810.11562v1.pdf
PWC	https://paperswithcode.com/paper/monitoring-the-shape-of-weather-soundscapes
Repo
Framework

Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks


Title	Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks
Authors	Samyak Parajuli, Aswin Raghavan, Sek Chai
Abstract	The use of deep neural networks in edge computing devices hinges on the balance between accuracy and complexity of computations. Ternary Connect (TC) \cite{lin2015neural} addresses this issue by restricting the parameters to three levels $-1, 0$, and $+1$, thus eliminating multiplications in the forward pass of the network during prediction. We propose Generalized Ternary Connect (GTC), which allows an arbitrary number of levels while at the same time eliminating multiplications by restricting the parameters to integer powers of two. The primary contribution is that GTC learns the number of levels and their values for each layer, jointly with the weights of the network in an end-to-end fashion. Experiments on MNIST and CIFAR-10 show that GTC naturally converges to an `almost binary’ network for deep classification networks (e.g. VGG-16) and deep variational auto-encoders, with negligible loss of classification accuracy and comparable visual quality of generated samples respectively. We demonstrate superior compression and similar accuracy of GTC in comparison to several state-of-the-art methods for neural network compression. We conclude with simulations showing the potential benefits of GTC in hardware. \|
Tasks	Neural Network Compression
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04985v1
PDF	http://arxiv.org/pdf/1811.04985v1.pdf
PWC	https://paperswithcode.com/paper/generalized-ternary-connect-end-to-end
Repo
Framework

Learning color space adaptation from synthetic to real images of cirrus clouds


Title	Learning color space adaptation from synthetic to real images of cirrus clouds
Authors	Qing Lyu, Xiang Chen
Abstract	Training on synthetic data is becoming popular in vision due to the convenient acquisition of accurate pixel-level labels. But the domain gap between synthetic and real images significantly degrades the performance of the trained model. We propose a color space adaptation method to bridge the gap. A set of closed-form operations are adopted to make color space adjustments while preserving the labels. We embed these operations into a two-stage learning approach, and demonstrate the adaptation efficacy on the semantic segmentation task of cirrus clouds.
Tasks	Semantic Segmentation
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10286v1
PDF	http://arxiv.org/pdf/1810.10286v1.pdf
PWC	https://paperswithcode.com/paper/learning-color-space-adaptation-from
Repo
Framework

An efficient supervised dictionary learning method for audio signal recognition


Title	An efficient supervised dictionary learning method for audio signal recognition
Authors	Imad Rida, Romain Hérault, Gilles Gasso
Abstract	Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example, Mel-Frequency Cepstral Coefficients (MFCCs) and its variants were successfully applied to computational auditory scene recognition while Chroma vectors are good at music chord recognition. Unfortunately, these predefined features may be of variable discrimination power while extended to other tasks or even within the same task due to different nature of clips. Motivated by this need of a principled framework across domain applications for machine listening, we propose a generic and data-driven representation learning approach. For this sake, a novel and efficient supervised dictionary learning method is presented. The method learns dissimilar dictionaries, one per each class, in order to extract heterogeneous information for classification. In other words, we are seeking to minimize the intra-class homogeneity and maximize class separability. This is made possible by promoting pairwise orthogonality between class specific dictionaries and controlling the sparsity structure of the audio clip’s decomposition over these dictionaries. The resulting optimization problem is non-convex and solved using a proximal gradient descent method. Experiments are performed on both computational auditory scene (East Anglia and Rouen) and synthetic music chord recognition datasets. Obtained results show that our method is capable to reach state-of-the-art hand-crafted features for both applications.
Tasks	Audio Signal Recognition, Chord Recognition, Dictionary Learning, Representation Learning, Scene Recognition
Published	2018-12-12
URL	http://arxiv.org/abs/1812.04748v1
PDF	http://arxiv.org/pdf/1812.04748v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-supervised-dictionary-learning
Repo
Framework

ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks


Title	ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks
Authors	Tae-Hoon Kim, Jonghyun Choi
Abstract	We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called ScreenerNet. Specifically, we learn a weight for each sample by jointly training the ScreenerNet and the main network in an end-to-end self-paced fashion. The ScreenerNet neither has sampling bias nor requires to remember the past learning history. We show the networks augmented with the ScreenerNet achieve early convergence with better accuracy than the state-of-the-art curricular learning methods in extensive experiments using three popular vision datasets such as MNIST, CIFAR10 and Pascal VOC2012, and a Cart-pole task using Deep Q-learning. Moreover, the ScreenerNet can extend other curriculum learning methods such as Prioritized Experience Replay (PER) for further accuracy improvement.
Tasks	Q-Learning
Published	2018-01-03
URL	http://arxiv.org/abs/1801.00904v4
PDF	http://arxiv.org/pdf/1801.00904v4.pdf
PWC	https://paperswithcode.com/paper/screenernet-learning-self-paced-curriculum
Repo
Framework

Improved Chord Recognition by Combining Duration and Harmonic Language Models


Title	Improved Chord Recognition by Combining Duration and Harmonic Language Models
Authors	Filip Korzeniowski, Gerhard Widmer
Abstract	Chord recognition systems typically comprise an acoustic model that predicts chords for each audio frame, and a temporal model that casts these predictions into labelled chord segments. However, temporal models have been shown to only smooth predictions, without being able to incorporate musical information about chord progressions. Recent research discovered that it might be the low hierarchical level such models have been applied to (directly on audio frames) which prevents learning musical relationships, even for expressive models such as recurrent neural networks (RNNs). However, if applied on the level of chord sequences, RNNs indeed can become powerful chord predictors. In this paper, we disentangle temporal models into a harmonic language model—to be applied on chord sequences—and a chord duration model that connects the chord-level predictions of the language model to the frame-level predictions of the acoustic model. In our experiments, we explore the impact of each model on the chord recognition score, and show that using harmonic language and duration models improves the results.
Tasks	Chord Recognition, Language Modelling
Published	2018-08-16
URL	http://arxiv.org/abs/1808.05335v1
PDF	http://arxiv.org/pdf/1808.05335v1.pdf
PWC	https://paperswithcode.com/paper/improved-chord-recognition-by-combining
Repo
Framework

A Deep Learning Driven Active Framework for Segmentation of Large 3D Shape Collections


Title	A Deep Learning Driven Active Framework for Segmentation of Large 3D Shape Collections
Authors	David George, Xianguha Xie, Yu-Kun Lai, Gary KL Tam
Abstract	High-level shape understanding and technique evaluation on large repositories of 3D shapes often benefit from additional information known about the shapes. One example of such information is the semantic segmentation of a shape into functional or meaningful parts. Generating accurate segmentations with meaningful segment boundaries is, however, a costly process, typically requiring large amounts of user time to achieve high quality results. In this paper we present an active learning framework for large dataset segmentation, which iteratively provides the user with new predictions by training new models based on already segmented shapes. Our proposed pipeline consists of three novel components. First, we a propose a fast and relatively accurate feature-based deep learning model to provide dataset-wide segmentation predictions. Second, we propose an information theory measure to estimate the prediction quality and for ordering subsequent fast and meaningful shape selection. Our experiments show that such suggestive ordering helps reduce users time and effort, produce high quality predictions, and construct a model that generalizes well. Finally, we provide effective segmentation refinement features to help the user quickly correct any incorrect predictions. We show that our framework is more accurate and in general more efficient than state-of-the-art, for massive dataset segmentation with while also providing consistent segment boundaries.
Tasks	Active Learning, Semantic Segmentation
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06551v1
PDF	http://arxiv.org/pdf/1807.06551v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-driven-active-framework-for
Repo
Framework

High Dimensional Discrete Integration over the Hypergrid


Title	High Dimensional Discrete Integration over the Hypergrid
Authors	Raj Kumar Maity, Arya Mazumdar, Soumyabrata Pal
Abstract	Recently Ermon et al. (2013) pioneered a way to practically compute approximations to large scale counting or discrete integration problems by using random hashes. The hashes are used to reduce the counting problem into many separate discrete optimization problems. The optimization problems then can be solved by an NP-oracle such as commercial SAT solvers or integer linear programming (ILP) solvers. In particular, Ermon et al. showed that if the domain of integration is ${0,1}^n$ then it is possible to obtain a solution within a factor of $16$ of the optimal (a 16-approximation) by this technique. In many crucial counting tasks, such as computation of partition function of ferromagnetic Potts model, the domain of integration is naturally ${0,1,\dots, q-1}^n, q>2$, the hypergrid. The straightforward extension of Ermon et al.‘s method allows a $q^2$-approximation for this problem. For large values of $q$, this is undesirable. In this paper, we show an improved technique to obtain an approximation factor of $4+O(1/q^2)$ to this problem. We are able to achieve this by using an idea of optimization over multiple bins of the hash functions, that can be easily implemented by inequality constraints, or even in unconstrained way. Also the burden on the NP-oracle is not increased by our method (an ILP solver can still be used). We provide experimental simulation results to support the theoretical guarantees of our algorithms.
Tasks
Published	2018-06-29
URL	https://arxiv.org/abs/1806.11542v3
PDF	https://arxiv.org/pdf/1806.11542v3.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-discrete-integration-by
Repo
Framework

BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback


Title	BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback
Authors	Chang Li, Branislav Kveton, Tor Lattimore, Ilya Markov, Maarten de Rijke, Csaba Szepesvari, Masrour Zoghi
Abstract	In this paper, we study the problem of safe online learning to re-rank, where user feedback is used to improve the quality of displayed lists. Learning to rank has traditionally been studied in two settings. In the offline setting, rankers are typically learned from relevance labels created by judges. This approach has generally become standard in industrial applications of ranking, such as search. However, this approach lacks exploration and thus is limited by the information content of the offline training data. In the online setting, an algorithm can experiment with lists and learn from feedback on them in a sequential fashion. Bandit algorithms are well-suited for this setting but they tend to learn user preferences from scratch, which results in a high initial cost of exploration. This poses an additional challenge of safe exploration in ranked lists. We propose BubbleRank, a bandit algorithm for safe re-ranking that combines the strengths of both the offline and online settings. The algorithm starts with an initial base list and improves it online by gradually exchanging higher-ranked less attractive items for lower-ranked more attractive items. We prove an upper bound on the n-step regret of BubbleRank that degrades gracefully with the quality of the initial base list. Our theoretical findings are supported by extensive experiments on a large-scale real-world click dataset.
Tasks	Learning-To-Rank, Safe Exploration
Published	2018-06-15
URL	https://arxiv.org/abs/1806.05819v2
PDF	https://arxiv.org/pdf/1806.05819v2.pdf
PWC	https://paperswithcode.com/paper/bubblerank-safe-online-learning-to-rerank
Repo
Framework

3D Deep Learning with voxelized atomic configurations for modeling atomistic potentials in complex solid-solution alloys


Title	3D Deep Learning with voxelized atomic configurations for modeling atomistic potentials in complex solid-solution alloys
Authors	Rahul Singh, Aayush Sharma, Onur Rauf Bingol, Aditya Balu, Ganesh Balasubramanian, Duane D. Johnson, Soumik Sarkar
Abstract	The need for advanced materials has led to the development of complex, multi-component alloys or solid-solution alloys. These materials have shown exceptional properties like strength, toughness, ductility, electrical and electronic properties. Current development of such material systems are hindered by expensive experiments and computationally demanding first-principles simulations. Atomistic simulations can provide reasonable insights on properties in such material systems. However, the issue of designing robust potentials still exists. In this paper, we explore a deep convolutional neural-network based approach to develop the atomistic potential for such complex alloys to investigate materials for insights into controlling properties. In the present work, we propose a voxel representation of the atomic configuration of a cell and design a 3D convolutional neural network to learn the interaction of the atoms. Our results highlight the performance of the 3D convolutional neural network and its efficacy in machine-learning the atomistic potential. We also explore the role of voxel resolution and provide insights into the two bounding box methodologies implemented for voxelization.
Tasks
Published	2018-11-23
URL	http://arxiv.org/abs/1811.09724v1
PDF	http://arxiv.org/pdf/1811.09724v1.pdf
PWC	https://paperswithcode.com/paper/3d-deep-learning-with-voxelized-atomic
Repo
Framework