July 27, 2019

2889 words 14 mins read

Paper Group ANR 705

Humanoid Robots as Agents of Human Consciousness Expansion. A Berkeley View of Systems Challenges for AI. Universal Adversarial Perturbations Against Semantic Image Segmentation. Playtime Measurement with Survival Analysis. Toward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling. En …

Humanoid Robots as Agents of Human Consciousness Expansion


Title	Humanoid Robots as Agents of Human Consciousness Expansion
Authors	Ben Goertzel, Julia Mossbridge, Eddie Monroe, David Hanson, Gino Yu
Abstract	The “Loving AI” project involves developing software enabling humanoid robots to interact with people in loving and compassionate ways, and to promote people’ self-understanding and self-transcendence. Currently the project centers on the Hanson Robotics robot “Sophia” – specifically, on supplying Sophia with personality content and cognitive, linguistic, perceptual and behavioral content aimed at enabling loving interactions supportive of human self-transcendence. In September 2017 a small pilot study was conducted, involving the Sophia robot leading human subjects through dialogues and exercises focused on meditation, visualization and relaxation. The pilot was an apparent success, qualitatively demonstrating the viability of the approach and the ability of appropriate human-robot interaction to increase human well-being and advance human consciousness.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07791v1
PDF	http://arxiv.org/pdf/1709.07791v1.pdf
PWC	https://paperswithcode.com/paper/humanoid-robots-as-agents-of-human
Repo
Framework

A Berkeley View of Systems Challenges for AI


Title	A Berkeley View of Systems Challenges for AI
Authors	Ion Stoica, Dawn Song, Raluca Ada Popa, David Patterson, Michael W. Mahoney, Randy Katz, Anthony D. Joseph, Michael Jordan, Joseph M. Hellerstein, Joseph E. Gonzalez, Ken Goldberg, Ali Ghodsi, David Culler, Pieter Abbeel
Abstract	With the increasing commoditization of computer vision, speech recognition and machine translation systems and the widespread deployment of learning-based back-end technologies such as digital advertising and intelligent infrastructures, AI (Artificial Intelligence) has moved from research labs to production. These changes have been made possible by unprecedented levels of data and computation, by methodological advances in machine learning, by innovations in systems software and architectures, and by the broad accessibility of these technologies. The next generation of AI systems promises to accelerate these developments and increasingly impact our lives via frequent interactions and making (often mission-critical) decisions on our behalf, often in highly personalized contexts. Realizing this promise, however, raises daunting challenges. In particular, we need AI systems that make timely and safe decisions in unpredictable environments, that are robust against sophisticated adversaries, and that can process ever increasing amounts of data across organizations and individuals without compromising confidentiality. These challenges will be exacerbated by the end of the Moore’s Law, which will constrain the amount of data these technologies can store and process. In this paper, we propose several open research directions in systems, architectures, and security that can address these challenges and help unlock AI’s potential to improve lives and society.
Tasks	Machine Translation, Speech Recognition
Published	2017-12-15
URL	http://arxiv.org/abs/1712.05855v1
PDF	http://arxiv.org/pdf/1712.05855v1.pdf
PWC	https://paperswithcode.com/paper/a-berkeley-view-of-systems-challenges-for-ai
Repo
Framework

Universal Adversarial Perturbations Against Semantic Image Segmentation


Title	Universal Adversarial Perturbations Against Semantic Image Segmentation
Authors	Jan Hendrik Metzen, Mummadi Chaithanya Kumar, Thomas Brox, Volker Fischer
Abstract	While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the system while being quasi-imperceptible for humans. More severely, there even exist universal perturbations that are input-agnostic but fool the network on the majority of inputs. While recent work has focused on image classification, this work proposes attacks against semantic image segmentation: we present an approach for generating (universal) adversarial perturbations that make the network yield a desired target segmentation as output. We show empirically that there exist barely perceptible universal noise patterns which result in nearly the same predicted segmentation for arbitrary inputs. Furthermore, we also show the existence of universal noise which removes a target class (e.g., all pedestrians) from the segmentation while leaving the segmentation mostly unchanged otherwise.
Tasks	Image Classification, Semantic Segmentation
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05712v3
PDF	http://arxiv.org/pdf/1704.05712v3.pdf
PWC	https://paperswithcode.com/paper/universal-adversarial-perturbations-against
Repo
Framework

Playtime Measurement with Survival Analysis


Title	Playtime Measurement with Survival Analysis
Authors	Markus Viljanen, Antti Airola, Jukka Heikkonen, Tapio Pahikkala
Abstract	Maximizing product use is a central goal of many businesses, which makes retention and monetization two central analytics metrics in games. Player retention may refer to various duration variables quantifying product use: total playtime or session playtime are popular research targets, and active playtime is well-suited for subscription games. Such research often has the goal of increasing player retention or conversely decreasing player churn. Survival analysis is a framework of powerful tools well suited for retention type data. This paper contributes new methods to game analytics on how playtime can be analyzed using survival analysis without covariates. Survival and hazard estimates provide both a visual and an analytic interpretation of the playtime phenomena as a funnel type nonparametric estimate. Metrics based on the survival curve can be used to aggregate this playtime information into a single statistic. Comparison of survival curves between cohorts provides a scientific AB-test. All these methods work on censored data and enable computation of confidence intervals. This is especially important in time and sample limited data which occurs during game development. Throughout this paper, we illustrate the application of these methods to real world game development problems on the Hipster Sheep mobile game.
Tasks	Survival Analysis
Published	2017-01-04
URL	http://arxiv.org/abs/1701.02359v1
PDF	http://arxiv.org/pdf/1701.02359v1.pdf
PWC	https://paperswithcode.com/paper/playtime-measurement-with-survival-analysis
Repo
Framework

Toward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling


Title	Toward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling
Authors	Songxuan Lai, Lianwen Jin, Weixin Yang
Abstract	This paper presents an investigation of several techniques that increase the accuracy of online handwritten Chinese character recognition (HCCR). We propose a new training strategy named DropDistortion to train a deep convolutional neural network (DCNN) with distorted samples. DropDistortion gradually lowers the degree of character distortion during training, which allows the DCNN to better generalize. Path signature is used to extract effective features for online characters. Further improvement is achieved by employing spatial stochastic max-pooling as a method of feature map distortion and model averaging. Experiments were carried out on three publicly available datasets, namely CASIA-OLHWDB 1.0, CASIA-OLHWDB 1.1, and the ICDAR2013 online HCCR competition dataset. The proposed techniques yield state-of-the-art recognition accuracies of 97.67%, 97.30%, and 97.99%, respectively.
Tasks
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07508v1
PDF	http://arxiv.org/pdf/1702.07508v1.pdf
PWC	https://paperswithcode.com/paper/toward-high-performance-online-hccr-a-cnn
Repo
Framework

EnLLVM: Ensemble Based Nonlinear Bayesian Filtering Using Linear Latent Variable Models


Title	EnLLVM: Ensemble Based Nonlinear Bayesian Filtering Using Linear Latent Variable Models
Authors	Xiao Lin, Gabriel Terejanu
Abstract	Real-time nonlinear Bayesian filtering algorithms are overwhelmed by data volume, velocity and increasing complexity of computational models. In this paper, we propose a novel ensemble based nonlinear Bayesian filtering approach which only requires a small number of simulations and can be applied to high-dimensional systems in the presence of intractable likelihood functions. The proposed approach uses linear latent projections to estimate the joint probability distribution between states, parameters, and observables using a mixture of Gaussian components generated by the reconstruction error for each ensemble member. Since it leverages the computational machinery behind linear latent variable models, it can achieve fast implementations without the need to compute high-dimensional sample covariance matrices. The performance of the proposed approach is compared with the performance of ensemble Kalman filter on a high-dimensional Lorenz nonlinear dynamical system.
Tasks	Latent Variable Models
Published	2017-08-08
URL	https://arxiv.org/abs/1708.02340v2
PDF	https://arxiv.org/pdf/1708.02340v2.pdf
PWC	https://paperswithcode.com/paper/enllvm-ensemble-based-nonlinear-bayesian
Repo
Framework

E$^2$BoWs: An End-to-End Bag-of-Words Model via Deep Convolutional Neural Network


Title	E$^2$BoWs: An End-to-End Bag-of-Words Model via Deep Convolutional Neural Network
Authors	Xiaobin Liu, Shiliang Zhang, Tiejun Huang, Qi Tian
Abstract	Traditional Bag-of-visual Words (BoWs) model is commonly generated with many steps including local feature extraction, codebook generation, and feature quantization, etc. Those steps are relatively independent with each other and are hard to be jointly optimized. Moreover, the dependency on hand-crafted local feature makes BoWs model not effective in conveying high-level semantics. These issues largely hinder the performance of BoWs model in large-scale image applications. To conquer these issues, we propose an End-to-End BoWs (E$^2$BoWs) model based on Deep Convolutional Neural Network (DCNN). Our model takes an image as input, then identifies and separates the semantic objects in it, and finally outputs the visual words with high semantic discriminative power. Specifically, our model firstly generates Semantic Feature Maps (SFMs) corresponding to different object categories through convolutional layers, then introduces Bag-of-Words Layers (BoWL) to generate visual words for each individual feature map. We also introduce a novel learning algorithm to reinforce the sparsity of the generated E$^2$BoWs model, which further ensures the time and memory efficiency. We evaluate the proposed E$^2$BoWs model on several image search datasets including CIFAR-10, CIFAR-100, MIRFLICKR-25K and NUS-WIDE. Experimental results show that our method achieves promising accuracy and efficiency compared with recent deep learning based retrieval works.
Tasks	Image Retrieval, Quantization
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05903v2
PDF	http://arxiv.org/pdf/1709.05903v2.pdf
PWC	https://paperswithcode.com/paper/e2bows-an-end-to-end-bag-of-words-model-via
Repo
Framework

Designing a Safe Autonomous Artificial Intelligence Agent based on Human Self-Regulation


Title	Designing a Safe Autonomous Artificial Intelligence Agent based on Human Self-Regulation
Authors	Mark Muraven
Abstract	There is a growing focus on how to design safe artificial intelligent (AI) agents. As systems become more complex, poorly specified goals or control mechanisms may cause AI agents to engage in unwanted and harmful outcomes. Thus it is necessary to design AI agents that follow initial programming intentions as the program grows in complexity. How to specify these initial intentions has also been an obstacle to designing safe AI agents. Finally, there is a need for the AI agent to have redundant safety mechanisms to ensure that any programming errors do not cascade into major problems. Humans are autonomous intelligent agents that have avoided these problems and the present manuscript argues that by understanding human self-regulation and goal setting, we may be better able to design safe AI agents. Some general principles of human self-regulation are outlined and specific guidance for AI design is given.
Tasks
Published	2017-01-05
URL	http://arxiv.org/abs/1701.01487v1
PDF	http://arxiv.org/pdf/1701.01487v1.pdf
PWC	https://paperswithcode.com/paper/designing-a-safe-autonomous-artificial
Repo
Framework

Asymmetric Actor Critic for Image-Based Robot Learning


Title	Asymmetric Actor Critic for Image-Based Robot Learning
Authors	Lerrel Pinto, Marcin Andrychowicz, Peter Welinder, Wojciech Zaremba, Pieter Abbeel
Abstract	Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training on a physical system can be expensive and dangerous, which has sparked significant interest in learning control policies using a physics simulator. While several recent works have shown promising results in transferring policies trained in simulation to the real world, they often do not fully utilize the advantage of working with a simulator. In this work, we exploit the full state observability in the simulator to train better policies which take as input only partial observations (RGBD images). We do this by employing an actor-critic training algorithm in which the critic is trained on full states while the actor (or policy) gets rendered images as input. We show experimentally on a range of simulated tasks that using these asymmetric inputs significantly improves performance. Finally, we combine this method with domain randomization and show real robot experiments for several tasks like picking, pushing, and moving a block. We achieve this simulation to real world transfer without training on any real world data.
Tasks	Decision Making
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06542v1
PDF	http://arxiv.org/pdf/1710.06542v1.pdf
PWC	https://paperswithcode.com/paper/asymmetric-actor-critic-for-image-based-robot
Repo
Framework

Pruning variable selection ensembles


Title	Pruning variable selection ensembles
Authors	Chunxia Zhang, Yilei Wu, Mu Zhu
Abstract	In the context of variable selection, ensemble learning has gained increasing interest due to its great potential to improve selection accuracy and to reduce false discovery rate. A novel ordering-based selective ensemble learning strategy is designed in this paper to obtain smaller but more accurate ensembles. In particular, a greedy sorting strategy is proposed to rearrange the order by which the members are included into the integration process. Through stopping the fusion process early, a smaller subensemble with higher selection accuracy can be obtained. More importantly, the sequential inclusion criterion reveals the fundamental strength-diversity trade-off among ensemble members. By taking stability selection (abbreviated as StabSel) as an example, some experiments are conducted with both simulated and real-world data to examine the performance of the novel algorithm. Experimental results demonstrate that pruned StabSel generally achieves higher selection accuracy and lower false discovery rates than StabSel and several other benchmark methods.
Tasks
Published	2017-04-26
URL	http://arxiv.org/abs/1704.08265v1
PDF	http://arxiv.org/pdf/1704.08265v1.pdf
PWC	https://paperswithcode.com/paper/pruning-variable-selection-ensembles
Repo
Framework

A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization


Title	A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization
Authors	Zhiyuan Zha, Xin Yuan, Bihan Wen, Jiantao Zhou, Jiachao Zhang, Ce Zhu
Abstract	Sparse coding has achieved a great success in various image processing tasks. However, a benchmark to measure the sparsity of image patch/group is missing since sparse coding is essentially an NP-hard problem. This work attempts to fill the gap from the perspective of rank minimization. More details please see the manuscript….
Tasks	Dictionary Learning, Image Inpainting, Image Restoration
Published	2017-09-12
URL	https://arxiv.org/abs/1709.03979v5
PDF	https://arxiv.org/pdf/1709.03979v5.pdf
PWC	https://paperswithcode.com/paper/bridge-the-gap-between-group-sparse-coding
Repo
Framework

A wavelet frame coefficient total variational model for image restoration


Title	A wavelet frame coefficient total variational model for image restoration
Authors	Wei Wang, Xiang-Gen Xia, Shengli Zhang, Chuanjiang He
Abstract	In this paper, we propose a vector total variation (VTV) of feature image model for image restoration. The VTV imposes different smoothing powers on different features (e.g. edges and cartoons) based on choosing various regularization parameters. Thus, the model can simultaneously preserve edges and remove noises. Next, the existence of solution for the model is proved and the split Bregman algorithm is used to solve the model. At last, we use the wavelet filter banks to explicitly define the feature operator and present some experimental results to show its advantage over the related methods in both quality and efficiency.
Tasks	Image Restoration
Published	2017-08-25
URL	http://arxiv.org/abs/1708.07601v2
PDF	http://arxiv.org/pdf/1708.07601v2.pdf
PWC	https://paperswithcode.com/paper/a-wavelet-frame-coefficient-total-variational
Repo
Framework

Learning to Detect Violent Videos using Convolutional Long Short-Term Memory


Title	Learning to Detect Violent Videos using Convolutional Long Short-Term Memory
Authors	Swathikiran Sudhakaran, Oswald Lanz
Abstract	Developing a technique for the automatic analysis of surveillance videos in order to identify the presence of violence is of broad interest. In this work, we propose a deep neural network for the purpose of recognizing violent videos. A convolutional neural network is used to extract frame level features from a video. The frame level features are then aggregated using a variant of the long short term memory that uses convolutional gates. The convolutional neural network along with the convolutional long short term memory is capable of capturing localized spatio-temporal features which enables the analysis of local motion taking place in the video. We also propose to use adjacent frame differences as the input to the model thereby forcing it to encode the changes occurring in the video. The performance of the proposed feature extraction pipeline is evaluated on three standard benchmark datasets in terms of recognition accuracy. Comparison of the results obtained with the state of the art techniques revealed the promising capability of the proposed method in recognizing violent videos.
Tasks
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06531v1
PDF	http://arxiv.org/pdf/1709.06531v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-detect-violent-videos-using
Repo
Framework

Joint Geometrical and Statistical Alignment for Visual Domain Adaptation


Title	Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
Authors	Jing Zhang, Wanqing Li, Philip Ogunbona
Abstract	This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. We propose a unified framework that reduces the shift between domains both statistically and geometrically, referred to as Joint Geometrical and Statistical Alignment (JGSA). Specifically, we learn two coupled projections that project the source domain and target domain data into low dimensional subspaces where the geometrical shift and distribution shift are reduced simultaneously. The objective function can be solved efficiently in a closed form. Extensive experiments have verified that the proposed method significantly outperforms several state-of-the-art domain adaptation methods on a synthetic dataset and three different real world cross-domain visual recognition tasks.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05498v1
PDF	http://arxiv.org/pdf/1705.05498v1.pdf
PWC	https://paperswithcode.com/paper/joint-geometrical-and-statistical-alignment
Repo
Framework

Detection and Attention: Diagnosing Pulmonary Lung Cancer from CT by Imitating Physicians


Title	Detection and Attention: Diagnosing Pulmonary Lung Cancer from CT by Imitating Physicians
Authors	Ning Li, Haopeng Liu, Bin Qiu, Wei Guo, Shijun Zhao, Kungang Li, Jie He
Abstract	This paper proposes a novel and efficient method to build a Computer-Aided Diagnoses (CAD) system for lung nodule detection based on Computed Tomography (CT). This task was treated as an Object Detection on Video (VID) problem by imitating how a radiologist reads CT scans. A lung nodule detector was trained to automatically learn nodule features from still images to detect lung nodule candidates with both high recall and accuracy. Unlike previous work which used 3-dimensional information around the nodule to reduce false positives, we propose two simple but efficient methods, Multi-slice propagation (MSP) and Motionless-guide suppression (MLGS), which analyze sequence information of CT scans to reduce false negatives and suppress false positives. We evaluated our method in open-source LUNA16 dataset which contains 888 CT scans, and obtained state-of-the-art result (Free-Response Receiver Operating Characteristic score of 0.892) with detection speed (end to end within 20 seconds per patient on a single NVidia GTX 1080) much higher than existing methods.
Tasks	Computed Tomography (CT), Lung Nodule Detection, Object Detection
Published	2017-12-14
URL	http://arxiv.org/abs/1712.05114v1
PDF	http://arxiv.org/pdf/1712.05114v1.pdf
PWC	https://paperswithcode.com/paper/detection-and-attention-diagnosing-pulmonary
Repo
Framework