October 20, 2019

3168 words 15 mins read

Paper Group AWR 309

SwishNet: A Fast Convolutional Neural Network for Speech, Music and Noise Classification and Segmentation. GAIN: Missing Data Imputation using Generative Adversarial Nets. Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization. Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simula …

SwishNet: A Fast Convolutional Neural Network for Speech, Music and Noise Classification and Segmentation


Title	SwishNet: A Fast Convolutional Neural Network for Speech, Music and Noise Classification and Segmentation
Authors	Md. Shamim Hussain, Mohammad Ariful Haque
Abstract	Speech, Music and Noise classification/segmentation is an important preprocessing step for audio processing/indexing. To this end, we propose a novel 1D Convolutional Neural Network (CNN) - SwishNet. It is a fast and lightweight architecture that operates on MFCC features which is suitable to be added to the front-end of an audio processing pipeline. We showed that the performance of our network can be improved by distilling knowledge from a 2D CNN, pretrained on ImageNet. We investigated the performance of our network on the MUSAN corpus - an openly available comprehensive collection of noise, music and speech samples, suitable for deep learning. The proposed network achieved high overall accuracy in clip (length of 0.5-2s) classification (>97% accuracy) and frame-wise segmentation (>93% accuracy) tasks with even higher accuracy (>99%) in speech/non-speech discrimination task. To verify the robustness of our model, we trained it on MUSAN and evaluated it on a different corpus - GTZAN and found good accuracy with very little fine-tuning. We also demonstrated that our model is fast on both CPU and GPU, consumes a low amount of memory and is suitable for implementation in embedded systems.
Tasks
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00149v1
PDF	http://arxiv.org/pdf/1812.00149v1.pdf
PWC	https://paperswithcode.com/paper/swishnet-a-fast-convolutional-neural-network
Repo	https://github.com/i7p9h9/swishnet
Framework	none

GAIN: Missing Data Imputation using Generative Adversarial Nets


Title	GAIN: Missing Data Imputation using Generative Adversarial Nets
Authors	Jinsung Yoon, James Jordon, Mihaela van der Schaar
Abstract	We propose a novel method for imputing missing data by adapting the well-known Generative Adversarial Nets (GAN) framework. Accordingly, we call our method Generative Adversarial Imputation Nets (GAIN). The generator (G) observes some components of a real data vector, imputes the missing components conditioned on what is actually observed, and outputs a completed vector. The discriminator (D) then takes a completed vector and attempts to determine which components were actually observed and which were imputed. To ensure that D forces G to learn the desired distribution, we provide D with some additional information in the form of a hint vector. The hint reveals to D partial information about the missingness of the original sample, which is used by D to focus its attention on the imputation quality of particular components. This hint ensures that G does in fact learn to generate according to the true data distribution. We tested our method on various datasets and found that GAIN significantly outperforms state-of-the-art imputation methods.
Tasks	Imputation, Multivariate Time Series Imputation
Published	2018-06-07
URL	http://arxiv.org/abs/1806.02920v1
PDF	http://arxiv.org/pdf/1806.02920v1.pdf
PWC	https://paperswithcode.com/paper/gain-missing-data-imputation-using-generative
Repo	https://github.com/dhanajitb/GAIN-Pytorch
Framework	pytorch

Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization


Title	Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization
Authors	Preksha Nema, Shreyas Shetty, Parag Jain, Anirban Laha, Karthik Sankaranarayanan, Mitesh M. Khapra
Abstract	In this work, we focus on the task of generating natural language descriptions from a structured table of facts containing fields (such as nationality, occupation, etc) and values (such as Indian, actor, director, etc). One simple choice is to treat the table as a sequence of fields and values and then use a standard seq2seq model for this task. However, such a model is too generic and does not exploit task-specific characteristics. For example, while generating descriptions from a table, a human would attend to information at two levels: (i) the fields (macro level) and (ii) the values within the field (micro level). Further, a human would continue attending to a field for a few timesteps till all the information from that field has been rendered and then never return back to this field (because there is nothing left to say about it). To capture this behavior we use (i) a fused bifocal attention mechanism which exploits and combines this micro and macro level information and (ii) a gated orthogonalization mechanism which tries to ensure that a field is remembered for a few time steps and then forgotten. We experiment with a recently released dataset which contains fact tables about people and their corresponding one line biographical descriptions in English. In addition, we also introduce two similar datasets for French and German. Our experiments show that the proposed model gives 21% relative improvement over a recently proposed state of the art method and 10% relative improvement over basic seq2seq models. The code and the datasets developed as a part of this work are publicly available.
Tasks
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07789v1
PDF	http://arxiv.org/pdf/1804.07789v1.pdf
PWC	https://paperswithcode.com/paper/generating-descriptions-from-structured-data
Repo	https://github.com/parajain/StructuredData_To_Descriptions
Framework	tf

Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation


Title	Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation
Authors	Matthew O’Kelly, Aman Sinha, Hongseok Namkoong, John Duchi, Russ Tedrake
Abstract	While recent developments in autonomous vehicle (AV) technology highlight substantial progress, we lack tools for rigorous and scalable testing. Real-world testing, the $\textit{de facto}$ evaluation environment, places the public in danger, and, due to the rare nature of accidents, will require billions of miles in order to statistically validate performance claims. We implement a simulation framework that can test an entire modern autonomous driving system, including, in particular, systems that employ deep-learning perception and control algorithms. Using adaptive importance-sampling methods to accelerate rare-event probability evaluation, we estimate the probability of an accident under a base distribution governing standard traffic behavior. We demonstrate our framework on a highway scenario, accelerating system evaluation by $2$-$20$ times over naive Monte Carlo sampling methods and $10$-$300 \mathsf{P}$ times (where $\mathsf{P}$ is the number of processors) over real-world testing.
Tasks	Autonomous Driving
Published	2018-10-31
URL	http://arxiv.org/abs/1811.00145v3
PDF	http://arxiv.org/pdf/1811.00145v3.pdf
PWC	https://paperswithcode.com/paper/scalable-end-to-end-autonomous-vehicle
Repo	https://github.com/SullyChen/Autopilot-TensorFlow
Framework	tf

ToriLLE: Learning Environment for Hand-to-Hand Combat


Title	ToriLLE: Learning Environment for Hand-to-Hand Combat
Authors	Anssi Kanervisto, Ville Hautamäki
Abstract	We present Toribash Learning Environment (ToriLLE), a learning environment for machine learning agents based on the video game Toribash. Toribash is a MuJoCo-like environment of two humanoid character fighting each other hand-to-hand, controlled by changing actuation modes of the joints. Competitive nature of Toribash as well its focused domain provide a platform for evaluating self-play methods, and evaluating machine learning agents against human players. In this paper we describe the environment with ToriLLE’s capabilities and limitations, and experimentally show its applicability as a learning environment. The source code of the environment and conducted experiments can be found at https://github.com/Miffyli/ToriLLE.
Tasks
Published	2018-07-26
URL	https://arxiv.org/abs/1807.10110v3
PDF	https://arxiv.org/pdf/1807.10110v3.pdf
PWC	https://paperswithcode.com/paper/torille-learning-environment-for-hand-to-hand
Repo	https://github.com/Miffyli/ToriLLE
Framework	none

Recognition of Acoustic Events Using Masked Conditional Neural Networks


Title	Recognition of Acoustic Events Using Masked Conditional Neural Networks
Authors	Fady Medhat, David Chesmore, John Robinson
Abstract	Automatic feature extraction using neural networks has accomplished remarkable success for images, but for sound recognition, these models are usually modified to fit the nature of the multi-dimensional temporal representation of the audio signal in spectrograms. This may not efficiently harness the time-frequency representation of the signal. The ConditionaL Neural Network (CLNN) takes into consideration the interrelation between the temporal frames, and the Masked ConditionaL Neural Network (MCLNN) extends upon the CLNN by forcing a systematic sparseness over the network’s weights using a binary mask. The masking allows the network to learn about frequency bands rather than bins, mimicking a filterbank used in signal transformations such as MFCC. Additionally, the Mask is designed to consider various combinations of features, which automates the feature hand-crafting process. We applied the MCLNN for the Environmental Sound Recognition problem using the Urbansound8k, YorNoise, ESC-10 and ESC-50 datasets. The MCLNN have achieved competitive performance compared to state-of-the-art Convolutional Neural Networks and hand-crafted attempts.
Tasks
Published	2018-02-07
URL	http://arxiv.org/abs/1802.02617v2
PDF	http://arxiv.org/pdf/1802.02617v2.pdf
PWC	https://paperswithcode.com/paper/recognition-of-acoustic-events-using-masked
Repo	https://github.com/fadymedhat/MCLNN
Framework	tf


Title	A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones
Authors	Daniele Palossi, Antonio Loquercio, Francesco Conti, Eric Flamand, Davide Scaramuzza, Luca Benini
Abstract	Fully-autonomous miniaturized robots (e.g., drones), with artificial intelligence (AI) based visual navigation capabilities are extremely challenging drivers of Internet-of-Things edge intelligence capabilities. Visual navigation based on AI approaches, such as deep neural networks (DNNs) are becoming pervasive for standard-size drones, but are considered out of reach for nanodrones with size of a few cm${}^\mathrm{2}$. In this work, we present the first (to the best of our knowledge) demonstration of a navigation engine for autonomous nano-drones capable of closed-loop end-to-end DNN-based visual navigation. To achieve this goal we developed a complete methodology for parallel execution of complex DNNs directly on-bard of resource-constrained milliwatt-scale nodes. Our system is based on GAP8, a novel parallel ultra-low-power computing platform, and a 27 g commercial, open-source CrazyFlie 2.0 nano-quadrotor. As part of our general methodology we discuss the software mapping techniques that enable the state-of-the-art deep convolutional neural network presented in [1] to be fully executed on-board within a strict 6 fps real-time constraint with no compromise in terms of flight results, while all processing is done with only 64 mW on average. Our navigation engine is flexible and can be used to span a wide performance range: at its peak performance corner it achieves 18 fps while still consuming on average just 3.5% of the power envelope of the deployed nano-aircraft.
Tasks	Autonomous Navigation, Visual Navigation
Published	2018-05-04
URL	https://arxiv.org/abs/1805.01831v4
PDF	https://arxiv.org/pdf/1805.01831v4.pdf
PWC	https://paperswithcode.com/paper/a-64mw-dnn-based-visual-navigation-engine-for
Repo	https://github.com/samjenks/AutonomousDrone
Framework	none

A Retrospective Analysis of the Fake News Challenge Stance Detection Task


Title	A Retrospective Analysis of the Fake News Challenge Stance Detection Task
Authors	Andreas Hanselowski, Avinesh PVS, Benjamin Schiller, Felix Caspelherr, Debanjan Chaudhuri, Christian M. Meyer, Iryna Gurevych
Abstract	The 2017 Fake News Challenge Stage 1 (FNC-1) shared task addressed a stance classification task as a crucial first step towards detecting fake news. To date, there is no in-depth analysis paper to critically discuss FNC-1’s experimental setup, reproduce the results, and draw conclusions for next-generation stance classification methods. In this paper, we provide such an in-depth analysis for the three top-performing systems. We first find that FNC-1’s proposed evaluation metric favors the majority class, which can be easily classified, and thus overestimates the true discriminative power of the methods. Therefore, we propose a new F1-based metric yielding a changed system ranking. Next, we compare the features and architectures used, which leads to a novel feature-rich stacked LSTM model that performs on par with the best systems, but is superior in predicting minority classes. To understand the methods’ ability to generalize, we derive a new dataset and perform both in-domain and cross-domain experiments. Our qualitative and quantitative study helps interpreting the original FNC-1 scores and understand which features help improving performance and why. Our new dataset and all source code used during the reproduction study are publicly available for future research.
Tasks	Stance Detection
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05180v1
PDF	http://arxiv.org/pdf/1806.05180v1.pdf
PWC	https://paperswithcode.com/paper/a-retrospective-analysis-of-the-fake-news-1
Repo	https://github.com/chimera-detector/Server
Framework	tf

DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking


Title	DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking
Authors	Mohamed H. Abdelpakey, Mohamed S. Shehata, Mostafa M. Mohamed
Abstract	Convolutional Siamese neural networks have been recently used to track objects using deep features. Siamese architecture can achieve real time speed, however it is still difficult to find a Siamese architecture that maintains the generalization capability, high accuracy and speed while decreasing the number of shared parameters especially when it is very deep. Furthermore, a conventional Siamese architecture usually processes one local neighborhood at a time, which makes the appearance model local and non-robust to appearance changes. To overcome these two problems, this paper proposes DensSiam, a novel convolutional Siamese architecture, which uses the concept of dense layers and connects each dense layer to all layers in a feed-forward fashion with a similarity-learning function. DensSiam also includes a Self-Attention mechanism to force the network to pay more attention to the non-local features during offline training. Extensive experiments are performed on four tracking benchmarks: OTB2013 and OTB2015 for validation set; and VOT2015, VOT2016 and VOT2017 for testing set. The obtained results show that DensSiam achieves superior results on these benchmarks compared to other current state-of-the-art methods.
Tasks	Object Tracking
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02714v1
PDF	http://arxiv.org/pdf/1809.02714v1.pdf
PWC	https://paperswithcode.com/paper/denssiam-end-to-end-densely-siamese-network
Repo	https://github.com/mrdoer/DSRPN_batch_pytorch
Framework	pytorch

The Mechanics of n-Player Differentiable Games


Title	The Mechanics of n-Player Differentiable Games
Authors	David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, Thore Graepel
Abstract	The cornerstone underpinning deep learning is the guarantee that gradient descent on an objective converges to local minima. Unfortunately, this guarantee fails in settings, such as generative adversarial nets, where there are multiple interacting losses. The behavior of gradient-based methods in games is not well understood – and is becoming increasingly important as adversarial and multi-objective architectures proliferate. In this paper, we develop new techniques to understand and control the dynamics in general games. The key result is to decompose the second-order dynamics into two components. The first is related to potential games, which reduce to gradient descent on an implicit function; the second relates to Hamiltonian games, a new class of games that obey a conservation law, akin to conservation laws in classical mechanical systems. The decomposition motivates Symplectic Gradient Adjustment (SGA), a new algorithm for finding stable fixed points in general games. Basic experiments show SGA is competitive with recently proposed algorithms for finding stable fixed points in GANs – whilst at the same time being applicable to – and having guarantees in – much more general games.
Tasks
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05642v2
PDF	http://arxiv.org/pdf/1802.05642v2.pdf
PWC	https://paperswithcode.com/paper/the-mechanics-of-n-player-differentiable
Repo	https://github.com/deepmind/symplectic-gradient-adjustment
Framework	none

Online Heart Rate Prediction using Acceleration from a Wrist Worn Wearable


Title	Online Heart Rate Prediction using Acceleration from a Wrist Worn Wearable
Authors	Ryan McConville, Gareth Archer, Ian Craddock, Herman ter Horst, Robert Piechocki, James Pope, Raul Santos-Rodriguez
Abstract	In this paper we study the prediction of heart rate from acceleration using a wrist worn wearable. Although existing photoplethysmography (PPG) heart rate sensors provide reliable measurements, they use considerably more energy than accelerometers and have a major impact on battery life of wearable devices. By using energy-efficient accelerometers to predict heart rate, significant energy savings can be made. Further, we are interested in understanding patient recovery after a heart rate intervention, where we expect a variation in heart rate over time. Therefore, we propose an online approach to tackle the concept as time passes. We evaluate the methods on approximately 4 weeks of free living data from three patients over a number of months. We show that our approach can achieve good predictive performance (e.g., 2.89 Mean Absolute Error) while using the PPG heart rate sensor infrequently (e.g., 20.25% of the samples).
Tasks	Photoplethysmography (PPG)
Published	2018-06-25
URL	http://arxiv.org/abs/1807.04667v1
PDF	http://arxiv.org/pdf/1807.04667v1.pdf
PWC	https://paperswithcode.com/paper/online-heart-rate-prediction-using
Repo	https://github.com/rymc/StreamingEnsembleRegressionForVeryTemporalConceptDriftingDataUsingActiveLearning
Framework	none

Variational Message Passing with Structured Inference Networks


Title	Variational Message Passing with Structured Inference Networks
Authors	Wu Lin, Nicolas Hubacher, Mohammad Emtiyaz Khan
Abstract	Recent efforts on combining deep models with probabilistic graphical models are promising in providing flexible models that are also easy to interpret. We propose a variational message-passing algorithm for variational inference in such models. We make three contributions. First, we propose structured inference networks that incorporate the structure of the graphical model in the inference network of variational auto-encoders (VAE). Second, we establish conditions under which such inference networks enable fast amortized inference similar to VAE. Finally, we derive a variational message passing algorithm to perform efficient natural-gradient inference while retaining the efficiency of the amortized inference. By simultaneously enabling structured, amortized, and natural-gradient inference for deep structured models, our method simplifies and generalizes existing methods.
Tasks
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05589v2
PDF	http://arxiv.org/pdf/1803.05589v2.pdf
PWC	https://paperswithcode.com/paper/variational-message-passing-with-structured
Repo	https://github.com/emtiyaz/vmp-for-svae
Framework	tf

A Simple and Effective Model-Based Variable Importance Measure


Title	A Simple and Effective Model-Based Variable Importance Measure
Authors	Brandon M. Greenwell, Bradley C. Boehmke, Andrew J. McCarthy
Abstract	In the era of “big data”, it is becoming more of a challenge to not only build state-of-the-art predictive models, but also gain an understanding of what’s really going on in the data. For example, it is often of interest to know which, if any, of the predictors in a fitted model are relatively influential on the predicted outcome. Some modern algorithms—like random forests and gradient boosted decision trees—have a natural way of quantifying the importance or relative influence of each feature. Other algorithms—like naive Bayes classifiers and support vector machines—are not capable of doing so and model-free approaches are generally used to measure each predictor’s importance. In this paper, we propose a standardized, model-based approach to measuring predictor importance across the growing spectrum of supervised learning algorithms. Our proposed method is illustrated through both simulated and real data examples. The R code to reproduce all of the figures in this paper is available in the supplementary materials.
Tasks
Published	2018-05-12
URL	http://arxiv.org/abs/1805.04755v1
PDF	http://arxiv.org/pdf/1805.04755v1.pdf
PWC	https://paperswithcode.com/paper/a-simple-and-effective-model-based-variable
Repo	https://github.com/koalaverse/vip
Framework	none

Improved robustness to adversarial examples using Lipschitz regularization of the loss


Title	Improved robustness to adversarial examples using Lipschitz regularization of the loss
Authors	Chris Finlay, Adam Oberman, Bilal Abbasi
Abstract	We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_2$ norm on CIFAR-10. We obtain verifiable average case and worst case robustness guarantees, based on the expected and maximum values of the norm of the gradient of the loss. We interpret adversarial training as Total Variation Regularization, which is a fundamental tool in mathematical image processing, and WCAT as Lipschitz regularization.
Tasks
Published	2018-10-01
URL	https://arxiv.org/abs/1810.00953v4
PDF	https://arxiv.org/pdf/1810.00953v4.pdf
PWC	https://paperswithcode.com/paper/improved-robustness-to-adversarial-examples
Repo	https://github.com/cfinlay/tulip
Framework	pytorch

Overarching Computation Model (OCM)


Title	Overarching Computation Model (OCM)
Authors	Henok Ghebrechristos, Drew Miller
Abstract	Existing models of computation, such as a Turing machine (hereafter, TM), do not consider the agent involved in interpreting the outcome of the computation. We argue that a TM, or any other computation model, has no significance if its output is not interpreted by some agent. Furthermore, we argue that including the interpreter in the model definition sheds light on some of the difficult problems faced in computation and mathematics. We provide an analytic process framework to address this limitation. The framework can be overlaid on existing concepts of computation to address many practical and philosophical concerns such as the P vs NP problem. In addition, we argue that the P vs NP problem is reminiscent of existing computation model which does not account for the person that initiates the computation and interprets the intermediate and final output. We utilize the observation that deterministic computational procedures lack fundamental capacity to fully simulate their non-deterministic variant to conclude that the set NP cannot be fully contained in P. Deterministic procedure can approximate non-deterministic variant to some degree. However, the logical implication of the fundamental differences between determinism and non-determinism is that equivalence of the two classes is impossible to establish.
Tasks
Published	2018-08-01
URL	http://arxiv.org/abs/1808.03598v2
PDF	http://arxiv.org/pdf/1808.03598v2.pdf
PWC	https://paperswithcode.com/paper/overarching-computation-model-ocm
Repo	https://github.com/h3nok/OCM
Framework	none