Paper Group ANR 814
Agent cognition through micro-simulations: Adaptive and tunable intelligence with NetLogo LevelSpace. Learning Confidence Sets using Support Vector Machines. Energy Efficient Hardware for On-Device CNN Inference via Transfer Learning. Self-organizing maps and generalization: an algorithmic description of Numerosity and Variability Effects. Eliminat …
Agent cognition through micro-simulations: Adaptive and tunable intelligence with NetLogo LevelSpace
| Title | Agent cognition through micro-simulations: Adaptive and tunable intelligence with NetLogo LevelSpace |
| Authors | Bryan Head, Uri Wilensky |
| Abstract | We present a method of endowing agents in an agent-based model (ABM) with sophisticated cognitive capabilities and a naturally tunable level of intelligence. Often, ABMs use random behavior or greedy algorithms for maximizing objectives (such as a predator always chasing after the closest prey). However, random behavior is too simplistic in many circumstances and greedy algorithms, as well as classic AI planning techniques, can be brittle in the context of the unpredictable and emergent situations in which agents may find themselves. Our method, called agent-centric Monte Carlo cognition (ACMCC), centers around using a separate agent-based model to represent the agents’ cognition. This model is then used by the agents in the primary model to predict the outcomes of their actions, and thus guide their behavior. To that end, we have implemented our method in the NetLogo agent-based modeling platform, using the recently released LevelSpace extension, which we developed to allow NetLogo models to interact with other NetLogo models. As an illustrative example, we extend the Wolf Sheep Predation model (included with NetLogo) by using ACMCC to guide animal behavior, and analyze the impact on agent performance and model dynamics. We find that ACMCC provides a reliable and understandable method of controlling agent intelligence, and has a large impact on agent performance and model dynamics even at low settings. |
| Tasks | |
| Published | 2018-07-27 |
| URL | http://arxiv.org/abs/1807.10847v1 |
| http://arxiv.org/pdf/1807.10847v1.pdf | |
| PWC | https://paperswithcode.com/paper/agent-cognition-through-micro-simulations |
| Repo | |
| Framework | |
Learning Confidence Sets using Support Vector Machines
| Title | Learning Confidence Sets using Support Vector Machines |
| Authors | Wenbo Wang, Xingye Qiao |
| Abstract | The goal of confidence-set learning in the binary classification setting is to construct two sets, each with a specific probability guarantee to cover a class. An observation outside the overlap of the two sets is deemed to be from one of the two classes, while the overlap is an ambiguity region which could belong to either class. Instead of plug-in approaches, we propose a support vector classifier to construct confidence sets in a flexible manner. Theoretically, we show that the proposed learner can control the non-coverage rates and minimize the ambiguity with high probability. Efficient algorithms are developed and numerical studies illustrate the effectiveness of the proposed method. |
| Tasks | |
| Published | 2018-09-28 |
| URL | http://arxiv.org/abs/1809.10818v1 |
| http://arxiv.org/pdf/1809.10818v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-confidence-sets-using-support-vector |
| Repo | |
| Framework | |
Energy Efficient Hardware for On-Device CNN Inference via Transfer Learning
| Title | Energy Efficient Hardware for On-Device CNN Inference via Transfer Learning |
| Authors | Paul Whatmough, Chuteng Zhou, Patrick Hansen, Matthew Mattina |
| Abstract | On-device CNN inference for real-time computer vision applications can result in computational demands that far exceed the energy budgets of mobile devices. This paper proposes FixyNN, a co-designed hardware accelerator platform which splits a CNN model into two parts: a set of layers that are fixed in the hardware platform as a front-end fixed-weight feature extractor, and the remaining layers which become a back-end classifier running on a conventional programmable CNN accelerator. The common front-end provides ubiquitous CNN features for all FixyNN models, while the back-end is programmable and specific to a given dataset. Image classification models for FixyNN are trained end-to-end via transfer learning, with front-end layers fixed for the shared feature extractor, and back-end layers fine-tuned for a specific task. Over a suite of six datasets, we trained models via transfer learning with an accuracy loss of <1%, resulting in a FixyNN hardware platform with nearly 2 times better energy efficiency than a conventional programmable CNN accelerator of the same silicon area (i.e. hardware cost). |
| Tasks | Image Classification, Transfer Learning |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01672v2 |
| http://arxiv.org/pdf/1812.01672v2.pdf | |
| PWC | https://paperswithcode.com/paper/energy-efficient-hardware-for-on-device-cnn |
| Repo | |
| Framework | |
Self-organizing maps and generalization: an algorithmic description of Numerosity and Variability Effects
| Title | Self-organizing maps and generalization: an algorithmic description of Numerosity and Variability Effects |
| Authors | Valentina Gliozzi, Kim Plunkett |
| Abstract | Category, or property generalization is a central function in the human cognition. It plays a crucial role in a variety of domains, such as learning, everyday reasoning, specialized reasoning, and decision making. Judging the content of a dish as edible, a hormone level as healthy, a building as belonging to the same architectural style as previously seen buildings, are examples of category generalization. In this paper, we propose self-organizing maps as candidates to explain the psychological mechanisms underlying category generalization. Self-organizing maps are psychologically and biologically plausible neural network models that learn after limited exposure to positive category examples, without any need of contrastive information. Just like humans. They reproduce human behavior in category generalization, in particular for what concerns the well-known Numerosity and Variability effects, which are usually explained with Bayesian tools. Where category generalization is concerned, self-organizing maps are good candidates to bridge the gap between the computational level of analysis in Marr’s hierarchy (where Bayesian models are situated) and the algorithmic level of aanalysis in Marr’s hierarchy (where Bayesian models are situated) and the algorithmic level of analysis in which plausible mechanisms are described. |
| Tasks | Decision Making |
| Published | 2018-02-26 |
| URL | http://arxiv.org/abs/1802.09442v1 |
| http://arxiv.org/pdf/1802.09442v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-organizing-maps-and-generalization-an |
| Repo | |
| Framework | |
Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking
| Title | Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking |
| Authors | Andrii Maksai, Pascal Fua |
| Abstract | Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to solve this problem but their training can be affected by biases that decrease their efficiency. In this paper, we introduce a new training procedure that confronts the algorithm to its own mistakes while explicitly attempting to minimize the number of switches, which results in better training. We propose an iterative scheme of building a rich training set and using it to learn a scoring function that is an explicit proxy for the target tracking metric. Whether using only simple geometric features or more sophisticated ones that also take appearance into account, our approach outperforms the state-of-the-art on several MOT benchmarks. |
| Tasks | Multiple Object Tracking, Object Tracking |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.10984v1 |
| http://arxiv.org/pdf/1811.10984v1.pdf | |
| PWC | https://paperswithcode.com/paper/eliminating-exposure-bias-and-loss-evaluation |
| Repo | |
| Framework | |
Multiplayer bandits without observing collision information
| Title | Multiplayer bandits without observing collision information |
| Authors | Gabor Lugosi, Abbas Mehrabian |
| Abstract | We study multiplayer stochastic multi-armed bandit problems in which the players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider two feedback models: a model in which the players can observe whether a collision has occurred, and a more difficult setup when no collision information is available. We give the first theoretical guarantees for the second model: an algorithm with a logarithmic regret, and an algorithm with a square-root regret type that does not depend on the gaps between the means. For the first model, we give the first square-root regret bounds that do not depend on the gaps. Building on these ideas, we also give an algorithm for reaching approximate Nash equilibria quickly in stochastic anti-coordination games. |
| Tasks | |
| Published | 2018-08-25 |
| URL | http://arxiv.org/abs/1808.08416v1 |
| http://arxiv.org/pdf/1808.08416v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiplayer-bandits-without-observing |
| Repo | |
| Framework | |
Kernel-Based Learning for Smart Inverter Control
| Title | Kernel-Based Learning for Smart Inverter Control |
| Authors | Aditie Garg, Mana Jalali, Vassilis Kekatos, Nikolaos Gatsis |
| Abstract | Distribution grids are currently challenged by frequent voltage excursions induced by intermittent solar generation. Smart inverters have been advocated as a fast-responding means to regulate voltage and minimize ohmic losses. Since optimal inverter coordination may be computationally challenging and preset local control rules are subpar, the approach of customized control rules designed in a quasi-static fashion features as a golden middle. Departing from affine control rules, this work puts forth non-linear inverter control policies. Drawing analogies to multi-task learning, reactive control is posed as a kernel-based regression task. Leveraging a linearized grid model and given anticipated data scenarios, inverter rules are jointly designed at the feeder level to minimize a convex combination of voltage deviations and ohmic losses via a linearly-constrained quadratic program. Numerical tests using real-world data on a benchmark feeder demonstrate that nonlinear control rules driven also by a few non-local readings can attain near-optimal performance. |
| Tasks | Multi-Task Learning |
| Published | 2018-07-10 |
| URL | http://arxiv.org/abs/1807.03769v1 |
| http://arxiv.org/pdf/1807.03769v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-based-learning-for-smart-inverter |
| Repo | |
| Framework | |
History Playground: A Tool for Discovering Temporal Trends in Massive Textual Corpora
| Title | History Playground: A Tool for Discovering Temporal Trends in Massive Textual Corpora |
| Authors | Thomas Lansdall-Welfare, Nello Cristianini |
| Abstract | Recent studies have shown that macroscopic patterns of continuity and change over the course of centuries can be detected through the analysis of time series extracted from massive textual corpora. Similar data-driven approaches have already revolutionised the natural sciences, and are widely believed to hold similar potential for the humanities and social sciences, driven by the mass-digitisation projects that are currently under way, and coupled with the ever-increasing number of documents which are “born digital”. As such, new interactive tools are required to discover and extract macroscopic patterns from these vast quantities of textual data. Here we present History Playground, an interactive web-based tool for discovering trends in massive textual corpora. The tool makes use of scalable algorithms to first extract trends from textual corpora, before making them available for real-time search and discovery, presenting users with an interface to explore the data. Included in the tool are algorithms for standardization, regression, change-point detection in the relative frequencies of ngrams, multi-term indices and comparison of trends across different corpora. |
| Tasks | Change Point Detection, Time Series |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01185v1 |
| http://arxiv.org/pdf/1806.01185v1.pdf | |
| PWC | https://paperswithcode.com/paper/history-playground-a-tool-for-discovering |
| Repo | |
| Framework | |
Towards Open-Set Identity Preserving Face Synthesis
| Title | Towards Open-Set Identity Preserving Face Synthesis |
| Authors | Jianmin Bao, Dong Chen, Fang Wen, Houqiang Li, Gang Hua |
| Abstract | We propose a framework based on Generative Adversarial Networks to disentangle the identity and attributes of faces, such that we can conveniently recombine different identities and attributes for identity preserving face synthesis in open domains. Previous identity preserving face synthesis processes are largely confined to synthesizing faces with known identities that are already in the training dataset. To synthesize a face with identity outside the training dataset, our framework requires one input image of that subject to produce an identity vector, and any other input face image to extract an attribute vector capturing, e.g., pose, emotion, illumination, and even the background. We then recombine the identity vector and the attribute vector to synthesize a new face of the subject with the extracted attribute. Our proposed framework does not need to annotate the attributes of faces in any way. It is trained with an asymmetric loss function to better preserve the identity and stabilize the training process. It can also effectively leverage large amounts of unlabeled training face images to further improve the fidelity of the synthesized faces for subjects that are not presented in the labeled training face dataset. Our experiments demonstrate the efficacy of the proposed framework. We also present its usage in a much broader set of applications including face frontalization, face attribute morphing, and face adversarial example detection. |
| Tasks | Face Generation |
| Published | 2018-03-29 |
| URL | http://arxiv.org/abs/1803.11182v2 |
| http://arxiv.org/pdf/1803.11182v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-open-set-identity-preserving-face |
| Repo | |
| Framework | |
Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit
| Title | Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit |
| Authors | Sreejith Kallummil, Sheetal Kalyani |
| Abstract | Orthogonal matching pursuit (OMP) is a widely used algorithm for recovering sparse high dimensional vectors in linear regression models. The optimal performance of OMP requires \textit{a priori} knowledge of either the sparsity of regression vector or noise statistics. Both these statistics are rarely known \textit{a priori} and are very difficult to estimate. In this paper, we present a novel technique called residual ratio thresholding (RRT) to operate OMP without any \textit{a priori} knowledge of sparsity and noise statistics and establish finite sample and large sample support recovery guarantees for the same. Both analytical results and numerical simulations in real and synthetic data sets indicate that RRT has a performance comparable to OMP with \textit{a priori} knowledge of sparsity and noise statistics. |
| Tasks | |
| Published | 2018-06-02 |
| URL | http://arxiv.org/abs/1806.00650v1 |
| http://arxiv.org/pdf/1806.00650v1.pdf | |
| PWC | https://paperswithcode.com/paper/signal-and-noise-statistics-oblivious |
| Repo | |
| Framework | |
Facade Segmentation in the Wild
| Title | Facade Segmentation in the Wild |
| Authors | John Femiani, Wamiq Reyaz Para, Niloy Mitra, Peter Wonka |
| Abstract | Urban facade segmentation from automatically acquired imagery, in contrast to traditional image segmentation, poses several unique challenges. 360-degree photospheres captured from vehicles are an effective way to capture a large number of images, but this data presents difficult-to-model warping and stitching artifacts. In addition, each pixel can belong to multiple facade elements, and different facade elements (e.g., window, balcony, sill, etc.) are correlated and vary wildly in their characteristics. In this paper, we propose three network architectures of varying complexity to achieve multilabel semantic segmentation of facade images while exploiting their unique characteristics. Specifically, we propose a MULTIFACSEGNET architecture to assign multiple labels to each pixel, a SEPARABLE architecture as a low-rank formulation that encourages extraction of rectangular elements, and a COMPATIBILITY network that simultaneously seeks segmentation across facade element types allowing the network to ‘see’ intermediate output probabilities of the various facade element classes. Our results on benchmark datasets show significant improvements over existing facade segmentation approaches for the typical facade elements. For example, on one commonly used dataset, the accuracy scores for window(the most important architectural element) increases from 0.91 to 0.97 percent compared to the best competing method, and comparable improvements on other element types. |
| Tasks | Semantic Segmentation |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.08634v1 |
| http://arxiv.org/pdf/1805.08634v1.pdf | |
| PWC | https://paperswithcode.com/paper/facade-segmentation-in-the-wild |
| Repo | |
| Framework | |
Measuring Similarity: Computationally Reproducing the Scholar’s Interests
| Title | Measuring Similarity: Computationally Reproducing the Scholar’s Interests |
| Authors | Ashley Lee, Jo Guldi, Andras Zsom |
| Abstract | Computerized document classification already orders the news articles that Apple’s “News” app or Google’s “personalized search” feature groups together to match a reader’s interests. The invisible and therefore illegible decisions that go into these tailored searches have been the subject of a critique by scholars who emphasize that our intelligence about documents is only as good as our ability to understand the criteria of search. This article will attempt to unpack the procedures used in computational classification of texts, translating them into term legible to humanists, and examining opportunities to render the computational text classification process subject to expert critique and improvement. |
| Tasks | Document Classification, Text Classification |
| Published | 2018-12-14 |
| URL | http://arxiv.org/abs/1812.05984v1 |
| http://arxiv.org/pdf/1812.05984v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-similarity-computationally |
| Repo | |
| Framework | |
In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization
| Title | In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization |
| Authors | Carlos Herranz-Perdiguero, Carolina Redondo-Cabrera, Roberto J. López-Sastre |
| Abstract | While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems from a bottom-up perspective, where we simply need a semantic segmentation of the scene as input. We employ the DeepLab architecture, based on the ResNet deep network, which leverages multi-scale inputs to later fuse their responses to perform a precise pixel labeling of the scene. This semantic segmentation mask is used to localize the objects and to recognize the scene, following two simple yet effective strategies. We evaluate the benefits of our solutions, performing a thorough experimental evaluation on the NYU Depth V2 dataset. Our approach achieves a performance that beats the leading results by a significant margin, defining the new state of the art in this benchmark for the three tasks comprising the scene understanding: semantic segmentation, object detection and scene categorization. |
| Tasks | Object Detection, Object Localization, Scene Classification, Scene Understanding, Semantic Segmentation |
| Published | 2018-07-19 |
| URL | http://arxiv.org/abs/1807.07284v1 |
| http://arxiv.org/pdf/1807.07284v1.pdf | |
| PWC | https://paperswithcode.com/paper/in-pixels-we-trust-from-pixel-labeling-to |
| Repo | |
| Framework | |
Neural Network Ensembles to Real-time Identification of Plug-level Appliance Measurements
| Title | Neural Network Ensembles to Real-time Identification of Plug-level Appliance Measurements |
| Authors | Karim Said Barsim, Lukas Mauch, Bin Yang |
| Abstract | The problem of identifying end-use electrical appliances from their individual consumption profiles, known as the appliance identification problem, is a primary stage in both Non-Intrusive Load Monitoring (NILM) and automated plug-wise metering. Therefore, appliance identification has received dedicated studies with various electric appliance signatures, classification models, and evaluation datasets. In this paper, we propose a neural network ensembles approach to address this problem using high resolution measurements. The models are trained on the raw current and voltage waveforms, and thus, eliminating the need for well engineered appliance signatures. We evaluate the proposed model on a publicly available appliance dataset from 55 residential buildings, 11 appliance categories, and over 1000 measurements. We further study the stability of the trained models with respect to training dataset, sampling frequency, and variations in the steady-state operation of appliances. |
| Tasks | Non-Intrusive Load Monitoring |
| Published | 2018-02-20 |
| URL | http://arxiv.org/abs/1802.06963v1 |
| http://arxiv.org/pdf/1802.06963v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-ensembles-to-real-time |
| Repo | |
| Framework | |
Bayesian Deconvolution of Scanning Electron Microscopy Images Using Point-spread Function Estimation and Non-local Regularization
| Title | Bayesian Deconvolution of Scanning Electron Microscopy Images Using Point-spread Function Estimation and Non-local Regularization |
| Authors | Joris Roels, Jan Aelterman, Jonas De Vylder, Hiep Luong, Yvan Saeys, Wilfried Philips |
| Abstract | Microscopy is one of the most essential imaging techniques in life sciences. High-quality images are required in order to solve (potentially life-saving) biomedical research problems. Many microscopy techniques do not achieve sufficient resolution for these purposes, being limited by physical diffraction and hardware deficiencies. Electron microscopy addresses optical diffraction by measuring emitted or transmitted electrons instead of photons, yielding nanometer resolution. Despite pushing back the diffraction limit, blur should still be taken into account because of practical hardware imperfections and remaining electron diffraction. Deconvolution algorithms can remove some of the blur in post-processing but they depend on knowledge of the point-spread function (PSF) and should accurately regularize noise. Any errors in the estimated PSF or noise model will reduce their effectiveness. This paper proposes a new procedure to estimate the lateral component of the point spread function of a 3D scanning electron microscope more accurately. We also propose a Bayesian maximum a posteriori deconvolution algorithm with a non-local image prior which employs this PSF estimate and previously developed noise statistics. We demonstrate visual quality improvements and show that applying our method improves the quality of subsequent segmentation steps. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.09739v1 |
| http://arxiv.org/pdf/1810.09739v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-deconvolution-of-scanning-electron |
| Repo | |
| Framework | |
