April 1, 2020

3400 words 16 mins read

Paper Group ANR 435

Optimal Options for Multi-Task Reinforcement Learning Under Time Constraints. RobustGCNs: Robust Norm Graph Convolutional Networks in the Presence of Node Missing Data and Large Noises. Erase and Restore: Simple, Accurate and Resilient Detection of $L_2$ Adversarial Examples. Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings. Action …

Optimal Options for Multi-Task Reinforcement Learning Under Time Constraints


Title	Optimal Options for Multi-Task Reinforcement Learning Under Time Constraints
Authors	Manuel Del Verme, Bruno Castro da Silva, Gianluca Baldassarre
Abstract	Reinforcement learning can greatly benefit from the use of options as a way of encoding recurring behaviours and to foster exploration. An important open problem is how can an agent autonomously learn useful options when solving particular distributions of related tasks. We investigate some of the conditions that influence optimality of options, in settings where agents have a limited time budget for learning each task and the task distribution might involve problems with different levels of similarity. We directly search for optimal option sets and show that the discovered options significantly differ depending on factors such as the available learning time budget and that the found options outperform popular option-generation heuristics.
Tasks
Published	2020-01-06
URL	https://arxiv.org/abs/2001.01620v1
PDF	https://arxiv.org/pdf/2001.01620v1.pdf
PWC	https://paperswithcode.com/paper/optimal-options-for-multi-task-reinforcement
Repo
Framework

RobustGCNs: Robust Norm Graph Convolutional Networks in the Presence of Node Missing Data and Large Noises


Title	RobustGCNs: Robust Norm Graph Convolutional Networks in the Presence of Node Missing Data and Large Noises
Authors	Bo Jiang, Ziyan Zhang
Abstract	Graph Convolutional Networks (GCNs) have been widely studied for attribute graph data representation and learning. In many applications, graph node attribute/feature may contain various kinds of noises, such as gross corruption, outliers and missing values. Existing graph convolutions (GCs) generally focus on feature propagation on structured graph which i) fail to address the graph data with missing values and ii) often perform susceptibility to the large feature errors/noises and outliers. To address this issue, in this paper, we propose to incorporate robust norm feature learning mechanism into graph convolution and present Robust Graph Convolutions (RGCs) for graph data in the presence of feature noises and missing values. Our RGCs is proposed based on the interpretation of GCs from a propagation function aspect of ‘data reconstruction on graph’. Based on it, we then derive our RGCs by exploiting robust norm based propagation functions into GCs. Finally, we incorporate the derived RGCs into an end-to-end network architecture and propose a kind of RobustGCNs for graph data learning. Experimental results on several noisy datasets demonstrate the effectiveness and robustness of the proposed RobustGCNs.
Tasks
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10130v1
PDF	https://arxiv.org/pdf/2003.10130v1.pdf
PWC	https://paperswithcode.com/paper/robustgcns-robust-norm-graph-convolutional
Repo
Framework

Erase and Restore: Simple, Accurate and Resilient Detection of $L_2$ Adversarial Examples


Title	Erase and Restore: Simple, Accurate and Resilient Detection of $L_2$ Adversarial Examples
Authors	Fei Zuo, Qiang Zeng
Abstract	By adding carefully crafted perturbations to input images, adversarial examples (AEs) can be generated to mislead neural-network-based image classifiers. $L_2$ adversarial perturbations by Carlini and Wagner (CW) are regarded as among the most effective attacks. While many countermeasures against AEs have been proposed, detection of adaptive CW $L_2$ AEs has been very inaccurate. Our observation is that those deliberately altered pixels in an $L_2$ AE, altogether, exert their malicious influence. By randomly erasing some pixels from an $L_2$ AE and then restoring it with an inpainting technique, such an AE, before and after the steps, tends to have different classification results, while a benign sample does not show this symptom. Based on this, we propose a novel AE detection technique, Erase and Restore (E&R), that exploits the limitation of $L_2$ attacks. On two popular image datasets, CIFAR-10 and ImageNet, our experiments show that the proposed technique is able to detect over 98% of the AEs generated by CW and other $L_2$ algorithms and has a very low false positive rate on benign images. Moreover, our approach demonstrate strong resilience to adaptive attacks. While adding noises and inpainting each have been well studied, by combining them together, we deliver a simple, accurate and resilient detection technique against adaptive $L_2$ AEs.
Tasks
Published	2020-01-01
URL	https://arxiv.org/abs/2001.00116v1
PDF	https://arxiv.org/pdf/2001.00116v1.pdf
PWC	https://paperswithcode.com/paper/erase-and-restore-simple-accurate-and
Repo
Framework

Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings


Title	Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings
Authors	Amy Zhao, Guha Balakrishnan, Kathleen M. Lewis, Frédo Durand, John V. Guttag, Adrian V. Dalca
Abstract	We introduce a new video synthesis task: synthesizing time lapse videos depicting how a given painting might have been created. Artists paint using unique combinations of brushes, strokes, colors, and layers. There are often many possible ways to create a given painting. Our goal is to learn to capture this rich range of possibilities. Creating distributions of long-term videos is a challenge for learning-based video synthesis methods. We present a probabilistic model that, given a single image of a completed painting, recurrently synthesizes steps of the painting process. We implement this model as a convolutional neural network, and introduce a training scheme to facilitate learning from a limited dataset of painting time lapses. We demonstrate that this model can be used to sample many time steps, enabling long-term stochastic video synthesis. We evaluate our method on digital and watercolor paintings collected from video websites, and show that human raters find our synthesized videos to be similar to time lapses produced by real artists.
Tasks
Published	2020-01-04
URL	https://arxiv.org/abs/2001.01026v1
PDF	https://arxiv.org/pdf/2001.01026v1.pdf
PWC	https://paperswithcode.com/paper/painting-many-pasts-synthesizing-time-lapse
Repo
Framework

Action for Better Prediction


Title	Action for Better Prediction
Authors	Bernadette Bucher, Karl Schmeckpeper, Nikolai Matni, Kostas Daniilidis
Abstract	Good prediction is necessary for autonomous robotics to make informed decisions in dynamic environments. Improvements can be made to the performance of a given data-driven prediction model by using better sampling strategies when collecting training data. Active learning approaches to optimal sampling have been combined with the mathematically general approaches to incentivizing exploration presented in the curiosity literature via model-based formulations of curiosity. We present an adversarial curiosity method which maximizes a score given by a discriminator network. This score gives a measure of prediction certainty enabling our approach to sample sequences of observations and actions which result in outcomes considered the least realistic by the discriminator. We demonstrate the ability of our active sampling method to achieve higher prediction performance and higher sample efficiency in a domain transfer problem for robotic manipulation tasks. We also present a validation dataset of action-conditioned video of robotic manipulation tasks on which we test the prediction performance of our trained models.
Tasks	Active Learning
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06082v1
PDF	https://arxiv.org/pdf/2003.06082v1.pdf
PWC	https://paperswithcode.com/paper/action-for-better-prediction
Repo
Framework

Data-driven surrogate modelling and benchmarking for process equipment


Title	Data-driven surrogate modelling and benchmarking for process equipment
Authors	Gabriel F. N. Gonçalves, Assen Batchvarov, Yuyi Liu, Yuxin Liu, Lachlan Mason, Indranil Pan, Omar K. Matar
Abstract	A suite of computational fluid dynamics (CFD) simulations geared towards chemical process equipment modelling has been developed and validated with experimental results from the literature. Various regression based active learning strategies are explored with these CFD simulators in-the-loop under the constraints of a limited function evaluation budget. Specifically, five different sampling strategies and five regression techniques are compared, considering a set of three test cases of industrial significance and varying complexity. Gaussian process regression was observed to have a consistently good performance for these applications. The present quantitative study outlines the pros and cons of the different available techniques and highlights the best practices for their adoption. The test cases and tools are available with an open-source license, to ensure reproducibility and engage the wider research community in contributing to both the CFD models and developing and benchmarking new improved algorithms tailored to this field.
Tasks	Active Learning
Published	2020-03-13
URL	https://arxiv.org/abs/2003.07701v1
PDF	https://arxiv.org/pdf/2003.07701v1.pdf
PWC	https://paperswithcode.com/paper/data-driven-surrogate-modelling-and
Repo
Framework

Automated discovery of a robust interatomic potential for aluminum


Title	Automated discovery of a robust interatomic potential for aluminum
Authors	Justin S. Smith, Benjamin Nebgen, Nithin Mathew, Jie Chen, Nicholas Lubbers, Leonid Burakovsky, Sergei Tretiak, Hai Ah Nam, Timothy Germann, Saryu Fensin, Kipton Barros
Abstract	Atomistic molecular dynamics simulation is an important tool for predicting materials properties. Accuracy depends crucially on the model for the interatomic potential. The gold standard would be quantum mechanics (QM) based force calculations, but such a first-principles approach becomes prohibitively expensive at large system sizes. Efficient machine learning models (ML) have become increasingly popular as surrogates for QM. Neural networks with many thousands of parameters excel in capturing structure within a large dataset, but may struggle to extrapolate beyond the scope of the available data. Here we present a highly automated active learning approach to iteratively collect new QM data that best resolves weaknesses in the existing ML model. We exemplify our approach by developing a general potential for elemental aluminum. At each active learning iteration, the method (1) trains an ANI-style neural network potential from the available data, (2) uses this potential to drive molecular dynamics simulations, and (3) collects new QM data whenever the neural network identifies an atomic configuration for which it cannot make a good prediction. All molecular dynamics simulations are initialized to a disordered configuration, and then driven according to randomized, time-varying temperatures. This nonequilibrium molecular dynamics forms a variety of crystalline and defected configurations. By training on all such automatically collected data, we produce ANI-Al, our new interatomic potential for aluminum. We demonstrate the remarkable transferability of ANI-Al by benchmarking against experimental data, e.g., the radial distribution function in melt, various properties of the stable face-centered cubic (FCC) crystal, and the coexistence curve between melt and FCC.
Tasks	Active Learning
Published	2020-03-10
URL	https://arxiv.org/abs/2003.04934v1
PDF	https://arxiv.org/pdf/2003.04934v1.pdf
PWC	https://paperswithcode.com/paper/automated-discovery-of-a-robust-interatomic
Repo
Framework

Modelling Human Active Search in Optimizing Black-box Functions


Title	Modelling Human Active Search in Optimizing Black-box Functions
Authors	Antonio Candelieri, Riccardo Perego, Ilaria Giordani, Andrea Ponti, Francesco Archetti
Abstract	Modelling human function learning has been the subject of in-tense research in cognitive sciences. The topic is relevant in black-box optimization where information about the objective and/or constraints is not available and must be learned through function evaluations. In this paper we focus on the relation between the behaviour of humans searching for the maximum and the probabilistic model used in Bayesian Optimization. As surrogate models of the unknown function both Gaussian Processes and Random Forest have been considered: the Bayesian learning paradigm is central in the development of active learning approaches balancing exploration/exploitation in uncertain conditions towards effective generalization in large decision spaces. In this paper we analyse experimentally how Bayesian Optimization compares to humans searching for the maximum of an unknown 2D function. A set of controlled experiments with 60 subjects, using both surrogate models, confirm that Bayesian Optimization provides a general model to represent individual patterns of active learning in humans
Tasks	Active Learning, Gaussian Processes
Published	2020-03-09
URL	https://arxiv.org/abs/2003.04275v1
PDF	https://arxiv.org/pdf/2003.04275v1.pdf
PWC	https://paperswithcode.com/paper/modelling-human-active-search-in-optimizing
Repo
Framework

Learning Hyperspectral Feature Extraction and Classification with ResNeXt Network


Title	Learning Hyperspectral Feature Extraction and Classification with ResNeXt Network
Authors	Divinah Nyasaka, Jing Wang, Haron Tinega
Abstract	The Hyperspectral image (HSI) classification is a standard remote sensing task, in which each image pixel is given a label indicating the physical land-cover on the earth’s surface. The achievements of image semantic segmentation and deep learning approaches on ordinary images have accelerated the research on hyperspectral image classification. Moreover, the utilization of both the spectral and spatial cues in hyperspectral images has shown improved classification accuracy in hyperspectral image classification. The use of only 3D Convolutional Neural Networks (3D-CNN) to extract both spatial and spectral cues from Hyperspectral images results in an explosion of parameters hence high computational cost. We propose network architecture called the MixedSN that utilizes the 3D convolutions to modeling spectral-spatial information in the early layers of the architecture and the 2D convolutions at the top layers which majorly deal with semantic abstraction. We constrain our architecture to ResNeXt block because of their performance and simplicity. Our model drastically reduced the number of parameters and achieved comparable classification performance with state-of-the-art methods on Indian Pine (IP) scene dataset, Pavia University scene (PU) dataset, Salinas (SA) Scene dataset, and Botswana (BW) dataset.
Tasks	Hyperspectral Image Classification, Image Classification, Semantic Segmentation
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02585v1
PDF	https://arxiv.org/pdf/2002.02585v1.pdf
PWC	https://paperswithcode.com/paper/learning-hyperspectral-feature-extraction-and
Repo
Framework

Spectral Pyramid Graph Attention Network for Hyperspectral Image Classification


Title	Spectral Pyramid Graph Attention Network for Hyperspectral Image Classification
Authors	Tinghuai Wang, Guangming Wang, Kuan Eeik Tan, Donghui Tan
Abstract	Convolutional neural networks (CNN) have made significant advances in hyperspectral image (HSI) classification. However, standard convolutional kernel neglects the intrinsic connections between data points, resulting in poor region delineation and small spurious predictions. Furthermore, HSIs have a unique continuous data distribution along the high dimensional spectrum domain - much remains to be addressed in characterizing the spectral contexts considering the prohibitively high dimensionality and improving reasoning capability in light of the limited amount of labelled data. This paper presents a novel architecture which explicitly addresses these two issues. Specifically, we design an architecture to encode the multiple spectral contextual information in the form of spectral pyramid of multiple embedding spaces. In each spectral embedding space, we propose graph attention mechanism to explicitly perform interpretable reasoning in the spatial domain based on the connection in spectral feature space. Experiments on three HSI datasets demonstrate that the proposed architecture can significantly improve the classification accuracy compared with the existing methods.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2020-01-20
URL	https://arxiv.org/abs/2001.07108v1
PDF	https://arxiv.org/pdf/2001.07108v1.pdf
PWC	https://paperswithcode.com/paper/spectral-pyramid-graph-attention-network-for
Repo
Framework

Emotion Recognition Using Speaker Cues


Title	Emotion Recognition Using Speaker Cues
Authors	Ismail Shahin
Abstract	This research aims at identifying the unknown emotion using speaker cues. In this study, we identify the unknown emotion using a two-stage framework. The first stage focuses on identifying the speaker who uttered the unknown emotion, while the next stage focuses on identifying the unknown emotion uttered by the recognized speaker in the prior stage. This proposed framework has been evaluated on an Arabic Emirati-accented speech database uttered by fifteen speakers per gender. Mel-Frequency Cepstral Coefficients (MFCCs) have been used as the extracted features and Hidden Markov Model (HMM) has been utilized as the classifier in this work. Our findings demonstrate that emotion recognition accuracy based on the two-stage framework is greater than that based on the one-stage approach and the state-of-the-art classifiers and models such as Gaussian Mixture Model (GMM), Support Vector Machine (SVM), and Vector Quantization (VQ). The average emotion recognition accuracy based on the two-stage approach is 67.5%, while the accuracy reaches to 61.4%, 63.3%, 64.5%, and 61.5%, based on the one-stage approach, GMM, SVM, and VQ, respectively. The achieved results based on the two-stage framework are very close to those attained in subjective assessment by human listeners.
Tasks	Emotion Recognition, Quantization
Published	2020-02-04
URL	https://arxiv.org/abs/2002.03566v1
PDF	https://arxiv.org/pdf/2002.03566v1.pdf
PWC	https://paperswithcode.com/paper/emotion-recognition-using-speaker-cues
Repo
Framework

Real-Time Object Detection and Recognition on Low-Compute Humanoid Robots using Deep Learning


Title	Real-Time Object Detection and Recognition on Low-Compute Humanoid Robots using Deep Learning
Authors	Sayantan Chatterjee, Faheem H. Zunjani, Souvik Sen, Gora C. Nandi
Abstract	We envision that in the near future, humanoid robots would share home space and assist us in our daily and routine activities through object manipulations. One of the fundamental technologies that need to be developed for robots is to enable them to detect objects and recognize them for effective manipulations and take real-time decisions involving those objects. In this paper, we describe a novel architecture that enables multiple low-compute NAO robots to perform real-time detection, recognition and localization of objects in its camera view and take programmable actions based on the detected objects. The proposed algorithm for object detection and localization is an empirical modification of YOLOv3, based on indoor experiments in multiple scenarios, with a smaller weight size and lesser computational requirements. Quantization of the weights and re-adjusting filter sizes and layer arrangements for convolutions improved the inference time for low-resolution images from the robot s camera feed. YOLOv3 was chosen after a comparative study of bounding box algorithms was performed with an objective to choose one that strikes the perfect balance among information retention, low inference time and high accuracy for real-time object detection and localization. The architecture also comprises of an effective end-to-end pipeline to feed the real-time frames from the camera feed to the neural net and use its results for guiding the robot with customizable actions corresponding to the detected class labels.
Tasks	Object Detection, Quantization, Real-Time Object Detection
Published	2020-01-20
URL	https://arxiv.org/abs/2002.03735v1
PDF	https://arxiv.org/pdf/2002.03735v1.pdf
PWC	https://paperswithcode.com/paper/real-time-object-detection-and-recognition-on
Repo
Framework

Learning to Walk: Spike Based Reinforcement Learning for Hexapod Robot Central Pattern Generation


Title	Learning to Walk: Spike Based Reinforcement Learning for Hexapod Robot Central Pattern Generation
Authors	Ashwin Sanjay Lele, Yan Fang, Justin Ting, Arijit Raychowdhury
Abstract	Learning to walk – i.e., learning locomotion under performance and energy constraints continues to be a challenge in legged robotics. Methods such as stochastic gradient, deep reinforcement learning (RL) have been explored for bipeds, quadrupeds and hexapods. These techniques are computationally intensive and often prohibitive for edge applications. These methods rely on complex sensors and pre-processing of data, which further increases energy and latency. Recent advances in spiking neural networks (SNNs) promise a significant reduction in computing owing to the sparse firing of neuros and has been shown to integrate reinforcement learning mechanisms with biologically observed spike time dependent plasticity (STDP). However, training a legged robot to walk by learning the synchronization patterns of central pattern generators (CPG) in an SNN framework has not been shown. This can marry the efficiency of SNNs with synchronized locomotion of CPG based systems providing breakthrough end-to-end learning in mobile robotics. In this paper, we propose a reinforcement based stochastic weight update technique for training a spiking CPG. The whole system is implemented on a lightweight raspberry pi platform with integrated sensors, thus opening up exciting new possibilities.
Tasks
Published	2020-03-22
URL	https://arxiv.org/abs/2003.10026v1
PDF	https://arxiv.org/pdf/2003.10026v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-walk-spike-based-reinforcement
Repo
Framework

NEW: A Generic Learning Model for Tie Strength Prediction in Networks


Title	NEW: A Generic Learning Model for Tie Strength Prediction in Networks
Authors	Zhen Liu, Hu li, Chao Wang
Abstract	Tie strength prediction, sometimes named weight prediction, is vital in exploring the diversity of connectivity pattern emerged in networks. Due to the fundamental significance, it has drawn much attention in the field of network analysis and mining. Some related works appeared in recent years have significantly advanced our understanding of how to predict the strong and weak ties in the social networks. However, most of the proposed approaches are scenario-aware methods heavily depending on some special contexts and even exclusively used in social networks. As a result, they are less applicable to various kinds of networks. In contrast to the prior studies, here we propose a new computational framework called Neighborhood Estimating Weight (NEW) which is purely driven by the basic structure information of the network and has the flexibility for adapting to diverse types of networks. In NEW, we design a novel index, i.e., connection inclination, to generate the representative features of the network, which is capable of capturing the actual distribution of the tie strength. In order to obtain the optimized prediction results, we also propose a parameterized regression model which approximately has a linear time complexity and thus is readily extended to the implementation in large-scale networks. The experimental results on six real-world networks demonstrate that our proposed predictive model outperforms the state of the art methods, which is powerful for predicting the missing tie strengths when only a part of the network’s tie strength information is available.
Tasks
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05283v1
PDF	https://arxiv.org/pdf/2001.05283v1.pdf
PWC	https://paperswithcode.com/paper/new-a-generic-learning-model-for-tie-strength
Repo
Framework

Ellipsoidal Subspace Support Vector Data Description


Title	Ellipsoidal Subspace Support Vector Data Description
Authors	Fahad Sohrab, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
Abstract	In this paper, we propose a novel method for transforming data into a low-dimensional space optimized for one-class classification. The proposed method iteratively transforms data into a new subspace optimized for ellipsoidal encapsulation of target class data. We provide both linear and non-linear formulations for the proposed method. The method takes into account the covariance of the data in the subspace; hence, it yields a more generalized solution as compared to Subspace Support Vector Data Description for a hypersphere. We propose different regularization terms expressing the class variance in the projected space. We compare the results with classic and recently proposed one-class classification methods and achieve better results in the majority of cases. The proposed method is also noticed to converge much faster than recently proposed Subspace Support Vector Data Description.
Tasks
Published	2020-03-20
URL	https://arxiv.org/abs/2003.09504v1
PDF	https://arxiv.org/pdf/2003.09504v1.pdf
PWC	https://paperswithcode.com/paper/ellipsoidal-subspace-support-vector-data
Repo
Framework