January 31, 2020

3100 words 15 mins read

Paper Group ANR 157

Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications. Gradients of Generative Models for Improved Discriminative Analysis of Tandem Mass Spectra. Model-Agnostic Linear Competitors – When Interpretable Models Compete and Collaborate with Black-Box Models. Data Context Adaptation for Accurate Recommendation with Additional Inf …

Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications


Title	Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications
Authors	Dibakar Gope, Ganesh Dasika, Matthew Mattina
Abstract	Machine learning-based applications are increasingly prevalent in IoT devices. The power and storage constraints of these devices make it particularly challenging to run modern neural networks, limiting the number of new applications that can be deployed on an IoT system. A number of compression techniques have been proposed, each with its own trade-offs. We propose a hybrid network which combines the strengths of current neural- and tree-based learning techniques in conjunction with ternary quantization, and show a detailed analysis of the associated model design space. Using this hybrid model we obtained a 11.1% reduction in the number of computations, a 52.2% reduction in the model size, and a 30.6% reduction in the overall memory footprint over a state-of-the-art keyword-spotting neural network, with negligible loss in accuracy.
Tasks	Keyword Spotting, Quantization
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01531v1
PDF	http://arxiv.org/pdf/1903.01531v1.pdf
PWC	https://paperswithcode.com/paper/ternary-hybrid-neural-tree-networks-for
Repo
Framework

Gradients of Generative Models for Improved Discriminative Analysis of Tandem Mass Spectra


Title	Gradients of Generative Models for Improved Discriminative Analysis of Tandem Mass Spectra
Authors	John T. Halloran, David M. Rocke
Abstract	Tandem mass spectrometry (MS/MS) is a high-throughput technology used toidentify the proteins in a complex biological sample, such as a drop of blood. A collection of spectra is generated at the output of the process, each spectrum of which is representative of a peptide (protein subsequence) present in the original complex sample. In this work, we leverage the log-likelihood gradients of generative models to improve the identification of such spectra. In particular, we show that the gradient of a recently proposed dynamic Bayesian network (DBN) may be naturally employed by a kernel-based discriminative classifier. The resulting Fisher kernel substantially improves upon recent attempts to combine generative and discriminative models for post-processing analysis, outperforming all other methods on the evaluated datasets. We extend the improved accuracy offered by the Fisher kernel framework to other search algorithms by introducing Theseus, a DBN representing a large number of widely used MS/MS scoring functions. Furthermore, with gradient ascent and max-product inference at hand, we use Theseus to learn model parameters without any supervision.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.02093v1
PDF	https://arxiv.org/pdf/1909.02093v1.pdf
PWC	https://paperswithcode.com/paper/gradients-of-generative-models-for-improved-1
Repo
Framework

Model-Agnostic Linear Competitors – When Interpretable Models Compete and Collaborate with Black-Box Models


Title	Model-Agnostic Linear Competitors – When Interpretable Models Compete and Collaborate with Black-Box Models
Authors	Hassan Rafique, Tong Wang, Qihang Lin
Abstract	Driven by an increasing need for model interpretability, interpretable models have become strong competitors for black-box models in many real applications. In this paper, we propose a novel type of model where interpretable models compete and collaborate with black-box models. We present the Model-Agnostic Linear Competitors (MALC) for partially interpretable classification. MALC is a hybrid model that uses linear models to locally substitute any black-box model, capturing subspaces that are most likely to be in a class while leaving the rest of the data to the black-box. MALC brings together the interpretable power of linear models and good predictive performance of a black-box model. We formulate the training of a MALC model as a convex optimization. The predictive accuracy and transparency (defined as the percentage of data captured by the linear models) balance through a carefully designed objective function and the optimization problem is solved with the accelerated proximal gradient method. Experiments show that MALC can effectively trade prediction accuracy for transparency and provide an efficient frontier that spans the entire spectrum of transparency.
Tasks
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10467v1
PDF	https://arxiv.org/pdf/1909.10467v1.pdf
PWC	https://paperswithcode.com/paper/190910467
Repo
Framework

Data Context Adaptation for Accurate Recommendation with Additional Information


Title	Data Context Adaptation for Accurate Recommendation with Additional Information
Authors	Hyunsik Jeon, Bonhun Koo, U Kang
Abstract	Given a sparse rating matrix and an auxiliary matrix of users or items, how can we accurately predict missing ratings considering different data contexts of entities? Many previous studies proved that utilizing the additional information with rating data is helpful to improve the performance. However, existing methods are limited in that 1) they ignore the fact that data contexts of rating and auxiliary matrices are different, 2) they have restricted capability of expressing independence information of users or items, and 3) they assume the relation between a user and an item is linear. We propose DaConA, a neural network based method for recommendation with a rating matrix and an auxiliary matrix. DaConA is designed with the following three main ideas. First, we propose a data context adaptation layer to extract pertinent features for different data contexts. Second, DaConA represents each entity with latent interaction vector and latent independence vector. Unlike previous methods, both of the two vectors are not limited in size. Lastly, while previous matrix factorization based methods predict missing values through the inner-product of latent vectors, DaConA learns a non-linear function of them via a neural network. We show that DaConA is a generalized algorithm including the standard matrix factorization and the collective matrix factorization as special cases. Through comprehensive experiments on real-world datasets, we show that DaConA provides the state-of-the-art accuracy.
Tasks
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08469v1
PDF	https://arxiv.org/pdf/1908.08469v1.pdf
PWC	https://paperswithcode.com/paper/data-context-adaptation-for-accurate
Repo
Framework

Prototypical Metric Transfer Learning for Continuous Speech Keyword Spotting With Limited Training Data


Title	Prototypical Metric Transfer Learning for Continuous Speech Keyword Spotting With Limited Training Data
Authors	Harshita Seth, Pulkit Kumar, Muktabh Mayank Srivastava
Abstract	Continuous Speech Keyword Spotting (CSKS) is the problem of spotting keywords in recorded conversations, when a small number of instances of keywords are available in training data. Unlike the more common Keyword Spotting, where an algorithm needs to detect lone keywords or short phrases like “Alexa”, “Cortana”, “Hi Alexa!", “Whatsup Octavia?” etc. in speech, CSKS needs to filter out embedded words from a continuous flow of speech, ie. spot “Anna” and “github” in “I know a developer named Anna who can look into this github issue.” Apart from the issue of limited training data availability, CSKS is an extremely imbalanced classification problem. We address the limitations of simple keyword spotting baselines for both aforementioned challenges by using a novel combination of loss functions (Prototypical networks’ loss and metric loss) and transfer learning. Our method improves F1 score by over 10%.
Tasks	Keyword Spotting, Transfer Learning
Published	2019-01-12
URL	http://arxiv.org/abs/1901.03860v1
PDF	http://arxiv.org/pdf/1901.03860v1.pdf
PWC	https://paperswithcode.com/paper/prototypical-metric-transfer-learning-for
Repo
Framework

Extending Multi-Object Tracking systems to better exploit appearance and 3D information


Title	Extending Multi-Object Tracking systems to better exploit appearance and 3D information
Authors	Kanchana Ranasinghe, Sahan Liyanaarachchi, Harsha Ranasinghe, Mayuka Jayawardhana
Abstract	Tracking multiple objects in real time is essential for a variety of real-world applications, with self-driving industry being at the foremost. This work involves exploiting temporally varying appearance and motion information for tracking. Siamese networks have recently become highly successful at appearance based single object tracking and Recurrent Neural Networks have started dominating both motion and appearance based tracking. Our work focuses on combining Siamese networks and RNNs to exploit appearance and motion information respectively to build a joint system capable of real time multi-object tracking. We further explore heuristics based constraints for tracking in the Birds Eye View Space for efficiently exploiting 3D information as a constrained optimization problem for track prediction.
Tasks	Multi-Object Tracking, Object Tracking
Published	2019-12-25
URL	https://arxiv.org/abs/1912.11651v1
PDF	https://arxiv.org/pdf/1912.11651v1.pdf
PWC	https://paperswithcode.com/paper/extending-multi-object-tracking-systems-to
Repo
Framework

AutoAIViz: Opening the Blackbox of Automated Artificial Intelligence with Conditional Parallel Coordinates


Title	AutoAIViz: Opening the Blackbox of Automated Artificial Intelligence with Conditional Parallel Coordinates
Authors	Daniel Karl I. Weidele, Justin D. Weisz, Eno Oduor, Michael Muller, Josh Andres, Alexander Gray, Dakuo Wang
Abstract	Artificial Intelligence (AI) can now automate the algorithm selection, feature engineering, and hyperparameter tuning steps in a machine learning workflow. Commonly known as AutoML or AutoAI, these technologies aim to relieve data scientists from the tedious manual work. However, today’s AutoAI systems often present only limited to no information about the process of how they select and generate model results. Thus, users often do not understand the process, neither do they trust the outputs. In this short paper, we provide a first user evaluation by 10 data scientists of an experimental system, AutoAIViz, that aims to visualize AutoAI’s model generation process. We find that the proposed system helps users to complete the data science tasks, and increases their understanding, toward the goal of increasing trust in the AutoAI system.
Tasks	AutoML, Feature Engineering
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06723v3
PDF	https://arxiv.org/pdf/1912.06723v3.pdf
PWC	https://paperswithcode.com/paper/autoaiviz-opening-the-blackbox-of-automated
Repo
Framework

Adaptive Power System Emergency Control using Deep Reinforcement Learning


Title	Adaptive Power System Emergency Control using Deep Reinforcement Learning
Authors	Qiuhua Huang, Renke Huang, Weituo Hao, Jie Tan, Rui Fan, Zhenyu Huang
Abstract	Power system emergency control is generally regarded as the last safety net for grid security and resiliency. Existing emergency control schemes are usually designed off-line based on either the conceived “worst” case scenario or a few typical operation scenarios. These schemes are facing significant adaptiveness and robustness issues as increasing uncertainties and variations occur in modern electrical grids. To address these challenges, for the first time, this paper developed novel adaptive emergency control schemes using deep reinforcement learning (DRL), by leveraging the high-dimensional feature extraction and non-linear generalization capabilities of DRL for complex power systems. Furthermore, an open-source platform named RLGC has been designed for the first time to assist the development and benchmarking of DRL algorithms for power system control. Details of the platform and DRL-based emergency control schemes for generator dynamic braking and under-voltage load shedding are presented. Extensive case studies performed in both two-area four-machine system and IEEE 39-Bus system have demonstrated the excellent performance and robustness of the proposed schemes.
Tasks
Published	2019-03-09
URL	http://arxiv.org/abs/1903.03712v2
PDF	http://arxiv.org/pdf/1903.03712v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-power-system-emergency-control-using
Repo
Framework

Client/Server Based Online Environment for Manual Segmentation of Medical Images


Title	Client/Server Based Online Environment for Manual Segmentation of Medical Images
Authors	Daniel Wild, Maximilian Weber, Jan Egger
Abstract	Segmentation is a key step in analyzing and processing medical images. Due to the low fault tolerance in medical imaging, manual segmentation remains the de facto standard in this domain. Besides, efforts to automate the segmentation process often rely on large amounts of manually labeled data. While existing software supporting manual segmentation is rich in features and delivers accurate results, the necessary time to set it up and get comfortable using it can pose a hurdle for the collection of large datasets. This work introduces a client/server based online environment, referred to as Studierfenster (studierfenster.at), that can be used to perform manual segmentations directly in a web browser. The aim of providing this functionality in the form of a web application is to ease the collection of ground truth segmentation datasets. Providing a tool that is quickly accessible and usable on a broad range of devices, offers the potential to accelerate this process. The manual segmentation workflow of Studierfenster consists of dragging and dropping the input file into the browser window and slice-by-slice outlining the object under consideration. The final segmentation can then be exported as a file storing its contours and as a binary segmentation mask. In order to evaluate the usability of Studierfenster, a user study was performed. The user study resulted in a mean of 6.3 out of 7.0 possible points given by users, when asked about their overall impression of the tool. The evaluation also provides insights into the results achievable with the tool in practice, by presenting two ground truth segmentations performed by physicians.
Tasks
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08610v1
PDF	http://arxiv.org/pdf/1904.08610v1.pdf
PWC	https://paperswithcode.com/paper/clientserver-based-online-environment-for
Repo
Framework

Averaging Essential and Fundamental Matrices in Collinear Camera Settings


Title	Averaging Essential and Fundamental Matrices in Collinear Camera Settings
Authors	Amnon Geifman, Yoni Kasten, Meirav Galun, Ronen Basri
Abstract	Global methods to Structure from Motion have gained popularity in recent years. A significant drawback of global methods is their sensitivity to collinear camera settings. In this paper, we introduce an analysis and algorithms for averaging bifocal tensors (essential or fundamental matrices) when either subsets or all of the camera centers are collinear. We provide a complete spectral characterization of bifocal tensors in collinear scenarios and further propose two averaging algorithms. The first algorithm uses rank constrained minimization to recover camera matrices in fully collinear settings. The second algorithm enriches the set of possibly mixed collinear and non-collinear cameras with additional, “virtual cameras,” which are placed in general position, enabling the application of existing averaging methods to the enriched set of bifocal tensors. Our algorithms are shown to achieve state of the art results on various benchmarks that include autonomous car datasets and unordered image collections in both calibrated and unclibrated settings.
Tasks
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00254v1
PDF	https://arxiv.org/pdf/1912.00254v1.pdf
PWC	https://paperswithcode.com/paper/averaging-essential-and-fundamental-matrices
Repo
Framework

A lattice-based approach to the expressivity of deep ReLU neural networks


Title	A lattice-based approach to the expressivity of deep ReLU neural networks
Authors	Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, Loic Brunel
Abstract	We present new families of continuous piecewise linear (CPWL) functions in Rn having a number of affine pieces growing exponentially in $n$. We show that these functions can be seen as the high-dimensional generalization of the triangle wave function used by Telgarsky in 2016. We prove that they can be computed by ReLU networks with quadratic depth and linear width in the space dimension. We also investigate the approximation error of one of these functions by shallower networks and prove a separation result. The main difference between our functions and other constructions is their practical interest: they arise in the scope of channel coding. Hence, computing such functions amounts to performing a decoding operation.
Tasks
Published	2019-02-28
URL	https://arxiv.org/abs/1902.11294v2
PDF	https://arxiv.org/pdf/1902.11294v2.pdf
PWC	https://paperswithcode.com/paper/a-lattice-based-approach-to-the-expressivity
Repo
Framework

3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders


Title	3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders
Authors	Wentai Zhang, Zhangsihao Yang, Haoliang Jiang, Suyash Nigam, Soji Yamakawa, Tomotake Furuhata, Kenji Shimada, Levent Burak Kara
Abstract	We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs. The approach learns an encoding of the samples in the training corpus using an unsupervised variational autoencoder-decoder architecture, without the need for an explicit parametric representation of the original designs. To facilitate the generation of smooth final surfaces, we develop a 3D shape representation based on a distance transformation of the original 3D data, rather than using the commonly utilized binary voxel representation. Once established, the generator maps the latent space representations to the high-dimensional distance transformation fields, which are then automatically surfaced to produce 3D representations amenable to physics simulations or other objective function evaluation modules. We demonstrate our approach for the computational design of gliders that are optimized to attain prescribed performance scores. Our results show that when combined with genetic optimization, the proposed approach can generate a rich set of candidate concept designs that achieve prescribed functional goals, even when the original dataset has only a few or no solutions that achieve these goals.
Tasks	3D Shape Representation
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07964v1
PDF	http://arxiv.org/pdf/1904.07964v1.pdf
PWC	https://paperswithcode.com/paper/3d-shape-synthesis-for-conceptual-design-and
Repo
Framework

Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network


Title	Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network
Authors	Anjith George, Zohreh Mostaani, David Geissenbuhler, Olegs Nikisins, Andre Anjos, Sebastien Marcel
Abstract	Face recognition is a mainstream biometric authentication method. However, vulnerability to presentation attacks (a.k.a spoofing) limits its usability in unsupervised applications. Even though there are many methods available for tackling presentation attacks (PA), most of them fail to detect sophisticated attacks such as silicone masks. As the quality of presentation attack instruments improves over time, achieving reliable PA detection with visual spectra alone remains very challenging. We argue that analysis in multiple channels might help to address this issue. In this context, we propose a multi-channel Convolutional Neural Network based approach for presentation attack detection (PAD). We also introduce the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks. Data from different channels such as color, depth, near-infrared and thermal are available to advance the research in face PAD. The proposed method was compared with feature-based approaches and found to outperform the baselines achieving an ACER of 0.3% on the introduced dataset. The database and the software to reproduce the results are made available publicly.
Tasks	Face Presentation Attack Detection, Face Recognition
Published	2019-09-19
URL	https://arxiv.org/abs/1909.08848v1
PDF	https://arxiv.org/pdf/1909.08848v1.pdf
PWC	https://paperswithcode.com/paper/biometric-face-presentation-attack-detection-1
Repo
Framework

Consensus Monte Carlo for Random Subsets using Shared Anchors


Title	Consensus Monte Carlo for Random Subsets using Shared Anchors
Authors	Yang Ni, Yuan Ji, Peter Mueller
Abstract	We present a consensus Monte Carlo algorithm that scales existing Bayesian nonparametric models for clustering and feature allocation to big data. The algorithm is valid for any prior on random subsets such as partitions and latent feature allocation, under essentially any sampling model. Motivated by three case studies, we focus on clustering induced by a Dirichlet process mixture sampling model, inference under an Indian buffet process prior with a binomial sampling model, and with a categorical sampling model. We assess the proposed algorithm with simulation studies and show results for inference with three datasets: an MNIST image dataset, a dataset of pancreatic cancer mutations, and a large set of electronic health records (EHR). Supplementary materials for this article are available online.
Tasks
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12309v2
PDF	https://arxiv.org/pdf/1906.12309v2.pdf
PWC	https://paperswithcode.com/paper/consensus-monte-carlo-for-random-subsets
Repo
Framework

Re-determinizing Information Set Monte Carlo Tree Search in Hanabi


Title	Re-determinizing Information Set Monte Carlo Tree Search in Hanabi
Authors	James Goodman
Abstract	This technical report documents the winner of the Computational Intelligence in Games(CIG) 2018 Hanabi competition. We introduce Re-determinizing IS-MCTS, a novel extension of Information Set Monte Carlo Tree Search (IS-MCTS) that prevents a leakage of hidden information into opponent models that can occur in IS-MCTS, and is particularly severe in Hanabi. Re-determinizing IS-MCTS scores higher in Hanabi for 2-4 players than previously published work at the time of the competition. Given the 40ms competition time limit per move we use a learned evaluation function to estimate leaf node values and avoid full simulations during MCTS. For the Mixed track competition, in which the identity of the other players is unknown, a simple Bayesian opponent model is used that is updated as each game proceeds.
Tasks
Published	2019-02-16
URL	https://arxiv.org/abs/1902.06075v2
PDF	https://arxiv.org/pdf/1902.06075v2.pdf
PWC	https://paperswithcode.com/paper/re-determinizing-information-set-monte-carlo
Repo
Framework