Paper Group ANR 315
Automatic Keyboard Layout Design for Low-Resource Latin-Script Languages. Representable Matrices: Enabling High Accuracy Analog Computation for Inference of DNNs using Memristors. Go with the Flow: Perception-refined Physics Simulation. ScieNet: Deep Learning with Spike-assisted Contextual Information Extraction. A Distributed Online Convex Optimiz …
Automatic Keyboard Layout Design for Low-Resource Latin-Script Languages
| Title | Automatic Keyboard Layout Design for Low-Resource Latin-Script Languages |
| Authors | Theresa Breiner, Chieu Nguyen, Daan van Esch, Jeremy O’Brien |
| Abstract | We present our approach to automatically designing and implementing keyboard layouts on mobile devices for typing low-resource languages written in the Latin script. For many speakers, one of the barriers in accessing and creating text content on the web is the absence of input tools for their language. Ease in typing in these languages would lower technological barriers to online communication and collaboration, likely leading to the creation of more web content. Unfortunately, it can be time-consuming to develop layouts manually even for language communities that use a keyboard layout very similar to English; starting from scratch requires many configuration files to describe multiple possible behaviors for each key. With our approach, we only need a small amount of data in each language to generate keyboard layouts with very little human effort. This process can help serve speakers of low-resource languages in a scalable way, allowing us to develop input tools for more languages. Having input tools that reflect the linguistic diversity of the world will let as many people as possible use technology to learn, communicate, and express themselves in their own native languages. |
| Tasks | |
| Published | 2019-01-18 |
| URL | http://arxiv.org/abs/1901.06039v1 |
| http://arxiv.org/pdf/1901.06039v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-keyboard-layout-design-for-low |
| Repo | |
| Framework | |
Representable Matrices: Enabling High Accuracy Analog Computation for Inference of DNNs using Memristors
| Title | Representable Matrices: Enabling High Accuracy Analog Computation for Inference of DNNs using Memristors |
| Authors | Baogang Zhang, Necati Uysal, Deliang Fan, Rickard Ewetz |
| Abstract | Analog computing based on memristor technology is a promising solution to accelerating the inference phase of deep neural networks (DNNs). A fundamental problem is to map an arbitrary matrix to a memristor crossbar array (MCA) while maximizing the resulting computational accuracy. The state-of-the-art mapping technique is based on a heuristic that only guarantees to produce the correct output for two input vectors. In this paper, a technique that aims to produce the correct output for every input vector is proposed, which involves specifying the memristor conductance values and a scaling factor realized by the peripheral circuitry. The key insight of the paper is that the conductance matrix realized by an MCA is only required to be proportional to the target matrix. The selection of the scaling factor between the two regulates the utilization of the programmable memristor conductance range and the representability of the target matrix. Consequently, the scaling factor is set to balance precision and value range errors. Moreover, a technique of converting conductance values into state variables and vice versa is proposed to handle memristors with non-ideal device characteristics. Compared with the state-of-the-art technique, the proposed mapping results in 4X-9X smaller errors. The improvements translate into that the classification accuracy of a seven-layer convolutional neural network (CNN) on CIFAR-10 is improved from 20.5% to 71.8%. |
| Tasks | |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12352v1 |
| https://arxiv.org/pdf/1911.12352v1.pdf | |
| PWC | https://paperswithcode.com/paper/representable-matrices-enabling-high-accuracy |
| Repo | |
| Framework | |
Go with the Flow: Perception-refined Physics Simulation
| Title | Go with the Flow: Perception-refined Physics Simulation |
| Authors | Tom F. H. Runia, Kirill Gavrilyuk, Cees G. M. Snoek, Arnold W. M. Smeulders |
| Abstract | For many of the physical phenomena around us, we have developed sophisticated models explaining their behavior. Nevertheless, inferring specifics from visual observations is challenging due to the high number of causally underlying physical parameters – including material properties and external forces. This paper addresses the problem of inferring such latent physical properties from observations. Our solution is an iterative refinement procedure with simulation at its core. The algorithm gradually updates the physical model parameters by running a simulation of the observed phenomenon and comparing the current simulation to a real-world observation. The physical similarity is computed using an embedding function that maps physically similar examples to nearby points. As a tangible example, we concentrate on flags curling in the wind – a seemingly simple phenomenon but physically highly involved. Based on its underlying physical model and visual manifestation, we propose an instantiation of the embedding function. For this mapping, modeled as a deep network, we introduce a spectral decomposition layer that decomposes a video volume into its temporal spectral power and corresponding frequencies. In experiments, we demonstrate our method’s ability to recover intrinsic and extrinsic physical parameters from both simulated and real-world video. |
| Tasks | |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.07861v1 |
| https://arxiv.org/pdf/1910.07861v1.pdf | |
| PWC | https://paperswithcode.com/paper/go-with-the-flow-perception-refined-physics |
| Repo | |
| Framework | |
ScieNet: Deep Learning with Spike-assisted Contextual Information Extraction
| Title | ScieNet: Deep Learning with Spike-assisted Contextual Information Extraction |
| Authors | Xueyuan She, Yun Long, Daehyun Kim, Saibal Mukhopadhyay |
| Abstract | Deep neural networks (DNNs) provide high image classification accuracy, but experience significant performance degradation when perturbation from various sources are present in the input. The lack of resilience to input perturbations makes DNN less reliable for systems interacting with physical world such as autonomous vehicles, robotics, to name a few, where imperfect input is the normal condition. We present a hybrid deep network architecture with spike-assisted contextual information extraction (ScieNet). ScieNet integrates unsupervised learning using spiking neural network (SNN) for unsupervised contextual informationextraction with a back-end DNN trained for classification. The integrated network demonstrates high resilience to input perturbations without relying on prior training on perturbed inputs. We demonstrate ScieNet with different back-end DNNs for image classification using CIFAR dataset considering stochastic (noise) and structured (rain) input perturbations. Experimental results demonstrate significant improvement in accuracy on noisy and rainy images without prior training, while maintaining state-of-the-art accuracy on clean images. |
| Tasks | Autonomous Vehicles, Image Classification |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05314v1 |
| https://arxiv.org/pdf/1909.05314v1.pdf | |
| PWC | https://paperswithcode.com/paper/scienet-deep-learning-with-spike-assisted |
| Repo | |
| Framework | |
A Distributed Online Convex Optimization Algorithm with Improved Dynamic Regret
| Title | A Distributed Online Convex Optimization Algorithm with Improved Dynamic Regret |
| Authors | Yan Zhang, Robert J. Ravier, Michael M. Zavlanos, Vahid Tarokh |
| Abstract | In this paper, we consider the problem of distributed online convex optimization, where a network of local agents aim to jointly optimize a convex function over a period of multiple time steps. The agents do not have any information about the future. Existing algorithms have established dynamic regret bounds that have explicit dependence on the number of time steps. In this work, we show that we can remove this dependence assuming that the local objective functions are strongly convex. More precisely, we propose a gradient tracking algorithm where agents jointly communicate and descend based on corrected gradient steps. We verify our theoretical results through numerical experiments. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.05050v1 |
| https://arxiv.org/pdf/1911.05050v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-distributed-online-convex-optimization |
| Repo | |
| Framework | |
A convolutional neural network reaches optimal sensitivity for detecting some, but not all, patterns
| Title | A convolutional neural network reaches optimal sensitivity for detecting some, but not all, patterns |
| Authors | Fabian Reith, Brian Wandell |
| Abstract | We investigate the performance of a convolutional neural network (CNN) at detecting a signal-known-exactly in Poisson noise. We compare the network performance with that of a Bayesian ideal observer (IO) that has the theoretical optimum in detection performance and a linear support vector machine (SVM). For several types of stimuli, including harmonics, faces, and certain regular patterns, the CNN performance asymptotes at the level of the IO. The SVM detection sensitivity is approximately 3-times lower. For other stimuli, including random patterns and certain cellular automata, the CNN sensitivity is significantly lower than that of the IO and the SVM. Finally, when the signal can appear in one of multiple locations, CNN sensitivity continues to match the ideal sensitivity. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.05055v2 |
| https://arxiv.org/pdf/1911.05055v2.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-pattern-sensitivity-of-a |
| Repo | |
| Framework | |
LexiPers: An ontology based sentiment lexicon for Persian
| Title | LexiPers: An ontology based sentiment lexicon for Persian |
| Authors | Behnam Sabeti, Pedram Hosseini, Gholamreza Ghassem-Sani, Seyed Abolghasem Mirroshandel |
| Abstract | Sentiment analysis refers to the use of natural language processing to identify and extract subjective information from textual resources. One approach for sentiment extraction is using a sentiment lexicon. A sentiment lexicon is a set of words associated with the sentiment orientation that they express. In this paper, we describe the process of generating a general purpose sentiment lexicon for Persian. A new graph-based method is introduced for seed selection and expansion based on an ontology. Sentiment lexicon generation is then mapped to a document classification problem. We used the K-nearest neighbors and nearest centroid methods for classification. These classifiers have been evaluated based on a set of hand labeled synsets. The final sentiment lexicon has been generated by the best classifier. The results show an acceptable performance in terms of accuracy and F-measure in the generated sentiment lexicon. |
| Tasks | Document Classification, Sentiment Analysis |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05263v1 |
| https://arxiv.org/pdf/1911.05263v1.pdf | |
| PWC | https://paperswithcode.com/paper/lexipers-an-ontology-based-sentiment-lexicon |
| Repo | |
| Framework | |
Design, Benchmarking and Explainability Analysis of a Game-Theoretic Framework towards Energy Efficiency in Smart Infrastructure
| Title | Design, Benchmarking and Explainability Analysis of a Game-Theoretic Framework towards Energy Efficiency in Smart Infrastructure |
| Authors | Ioannis C. Konstantakopoulos, Hari Prasanna Das, Andrew R. Barkan, Shiying He, Tanya Veeravalli, Huihan Liu, Aummul Baneen Manasawala, Yu-Wen Lin, Costas J. Spanos |
| Abstract | In this paper, we propose a gamification approach as a novel framework for smart building infrastructure with the goal of motivating human occupants to reconsider personal energy usage and to have positive effects on their environment. Human interaction in the context of cyber-physical systems is a core component and consideration in the implementation of any smart building technology. Research has shown that the adoption of human-centric building services and amenities leads to improvements in the operational efficiency of these cyber-physical systems directed towards controlling building energy usage. We introduce a strategy in form of a game-theoretic framework that incorporates humans-in-the-loop modeling by creating an interface to allow building managers to interact with occupants and potentially incentivize energy efficient behavior. Prior works on game theoretic analysis typically rely on the assumption that the utility function of each individual agent is known a priori. Instead, we propose novel utility learning framework for benchmarking that employs robust estimations of occupant actions towards energy efficiency. To improve forecasting performance, we extend the utility learning scheme by leveraging deep bi-directional recurrent neural networks. Using the proposed methods on data gathered from occupant actions for resources such as room lighting, we forecast patterns of energy resource usage to demonstrate the prediction performance of the methods. The results of our study show that we can achieve a highly accurate representation of the ground truth for occupant energy resource usage. We also demonstrate the explainable nature on human decision making towards energy usage inherent in the dataset using graphical lasso and granger causality algorithms. Finally, we open source the de-identified, high-dimensional data pertaining to the energy game-theoretic framework. |
| Tasks | Decision Making |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07899v1 |
| https://arxiv.org/pdf/1910.07899v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-benchmarking-and-explainability |
| Repo | |
| Framework | |
A Speech Test Set of Practice Business Presentations with Additional Relevant Texts
| Title | A Speech Test Set of Practice Business Presentations with Additional Relevant Texts |
| Authors | Dominik Macháček, Jonáš Kratochvíl, Tereza Vojtěchová, Ondřej Bojar |
| Abstract | We present a test corpus of audio recordings and transcriptions of presentations of students’ enterprises together with their slides and web-pages. The corpus is intended for evaluation of automatic speech recognition (ASR) systems, especially in conditions where the prior availability of in-domain vocabulary and named entities is benefitable. The corpus consists of 39 presentations in English, each up to 90 seconds long. The speakers are high school students from European countries with English as their second language. We benchmark three baseline ASR systems on the corpus and show their imperfection. |
| Tasks | Speech Recognition |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.00916v1 |
| https://arxiv.org/pdf/1908.00916v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-speech-test-set-of-practice-business |
| Repo | |
| Framework | |
MaD: Mapping and debugging framework for implementing deep neural network onto a neuromorphic chip with crossbar array of synapses
| Title | MaD: Mapping and debugging framework for implementing deep neural network onto a neuromorphic chip with crossbar array of synapses |
| Authors | Roshan Gopalakrishnan, Ashish Jith Sreejith Kumar, Yansong Chua |
| Abstract | Neuromorphic systems or dedicated hardware for neuromorphic computing is getting popular with the advancement in research on different device materials for synapses, especially in crossbar architecture and also algorithms specific or compatible to neuromorphic hardware. Hence, an automated mapping of any deep neural network onto the neuromorphic chip with crossbar array of synapses and an efficient debugging framework is very essential. Here, mapping is defined as the deployment of a section of deep neural network layer onto a neuromorphic core and the generation of connection lists among population of neurons to specify the connectivity between various neuromorphic cores on the neuromorphic chip. Debugging is the verification of computations performed on the neuromorphic chip during inferencing. Together the framework becomes Mapping and Debugging (MaD) framework. MaD framework is quite general in usage as it is a Python wrapper which can be integrated with almost every simulator tools for neuromorphic chips. This paper illustrates the MaD framework in detail, considering some optimizations while mapping onto a single neuromorphic core. A classification task on MNIST and CIFAR-10 datasets are considered for test case implementation of MaD framework. |
| Tasks | |
| Published | 2019-01-01 |
| URL | http://arxiv.org/abs/1901.00128v1 |
| http://arxiv.org/pdf/1901.00128v1.pdf | |
| PWC | https://paperswithcode.com/paper/mad-mapping-and-debugging-framework-for |
| Repo | |
| Framework | |
Classification of Single-lead Electrocardiograms: TDA Informed Machine Learning
| Title | Classification of Single-lead Electrocardiograms: TDA Informed Machine Learning |
| Authors | Paul Samuel Ignacio, David Uminsky, Christopher Dunstan, Esteban Escobar, Luke Trujillo |
| Abstract | Atrial Fibrillation is a heart condition characterized by erratic heart rhythms caused by chaotic propagation of electrical impulses in the atria, leading to numerous health complications. State-of-the-art models employ complex algorithms that extract expert-informed features to improve diagnosis. In this note, we demonstrate how topological features can be used to help accurately classify single lead electrocardiograms. Via delay embeddings, we map electrocardiograms onto high-dimensional point-clouds that convert periodic signals to algebraically computable topological signatures. We derive features from persistent signatures, input them to a simple machine learning algorithm, and benchmark its performance against winning entries in the 2017 Physionet Computing in Cardiology Challenge. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.12253v2 |
| https://arxiv.org/pdf/1911.12253v2.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-single-lead |
| Repo | |
| Framework | |
Minimum “Norm” Neural Networks are Splines
| Title | Minimum “Norm” Neural Networks are Splines |
| Authors | Rahul Parhi, Robert D. Nowak |
| Abstract | We develop a general framework based on splines to understand the interpolation properties of overparameterized neural networks. We prove that minimum “norm” two-layer neural networks (with appropriately chosen activation functions) that interpolate scattered data are minimal knot splines. Our results follow from understanding key relationships between notions of neural network “norms”, linear operators, and continuous-domain linear inverse problems. |
| Tasks | |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02333v1 |
| https://arxiv.org/pdf/1910.02333v1.pdf | |
| PWC | https://paperswithcode.com/paper/minimum-norm-neural-networks-are-splines |
| Repo | |
| Framework | |
Scalable and Differentially Private Distributed Aggregation in the Shuffled Model
| Title | Scalable and Differentially Private Distributed Aggregation in the Shuffled Model |
| Authors | Badih Ghazi, Rasmus Pagh, Ameya Velingker |
| Abstract | Federated learning promises to make machine learning feasible on distributed, private datasets by implementing gradient descent using secure aggregation methods. The idea is to compute a global weight update without revealing the contributions of individual users. Current practical protocols for secure aggregation work in an “honest but curious” setting where a curious adversary observing all communication to and from the server cannot learn any private information assuming the server is honest and follows the protocol. A more scalable and robust primitive for privacy-preserving protocols is shuffling of user data, so as to hide the origin of each data item. Highly scalable and secure protocols for shuffling, so-called mixnets, have been proposed as a primitive for privacy-preserving analytics in the Encode-Shuffle-Analyze framework by Bittau et al., which was later analytically studied by Erlingsson et al. and Cheu et al.. The recent papers by Cheu et al., and Balle et al. have given protocols for secure aggregation that achieve differential privacy guarantees in this “shuffled model”. Their protocols come at a cost, though: Either the expected aggregation error or the amount of communication per user scales as a polynomial $n^{\Omega(1)}$ in the number of users $n$. In this paper we propose simple and more efficient protocol for aggregation in the shuffled model, where communication as well as error increases only polylogarithmically in $n$. Our new technique is a conceptual “invisibility cloak” that makes users’ data almost indistinguishable from random noise while introducing zero distortion on the sum. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08320v3 |
| https://arxiv.org/pdf/1906.08320v3.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-and-differentially-private |
| Repo | |
| Framework | |
A hybrid neural network model based on improved PSO and SA for bankruptcy prediction
| Title | A hybrid neural network model based on improved PSO and SA for bankruptcy prediction |
| Authors | Fatima Zahra Azayite, Said Achchab |
| Abstract | Predicting firm’s failure is one of the most interesting subjects for investors and decision makers. In this paper, a bankruptcy prediction model is proposed based on Artificial Neural networks (ANN). Taking into consideration that the choice of variables to discriminate between bankrupt and non-bankrupt firms influences significantly the model’s accuracy and considering the problem of local minima, we propose a hybrid ANN based on variables selection techniques. Moreover, we evolve the convergence of Particle Swarm Optimization (PSO) by proposing a training algorithm based on an improved PSO and Simulated Annealing. A comparative performance study is reported, and the proposed hybrid model shows a high performance and convergence in the context of missing data. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.12179v1 |
| https://arxiv.org/pdf/1907.12179v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hybrid-neural-network-model-based-on |
| Repo | |
| Framework | |
Linguistic generalization and compositionality in modern artificial neural networks
| Title | Linguistic generalization and compositionality in modern artificial neural networks |
| Authors | Marco Baroni |
| Abstract | In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks. Given the high productivity of language, these models must possess effective generalization abilities. It is widely assumed that humans handle linguistic productivity by means of algebraic compositional rules: Are deep networks similarly compositional? After reviewing the main innovations characterizing current deep language processing networks, I discuss a set of studies suggesting that deep networks are capable of subtle grammar-dependent generalizations, but also that they do not rely on systematic compositional rules. I argue that the intriguing behaviour of these devices (still awaiting a full understanding) should be of interest to linguists and cognitive scientists, as it offers a new perspective on possible computational strategies to deal with linguistic productivity beyond rule-based compositionality, and it might lead to new insights into the less systematic generalization patterns that also appear in natural language. |
| Tasks | |
| Published | 2019-03-30 |
| URL | https://arxiv.org/abs/1904.00157v3 |
| https://arxiv.org/pdf/1904.00157v3.pdf | |
| PWC | https://paperswithcode.com/paper/linguistic-generalization-and |
| Repo | |
| Framework | |
