Paper Group ANR 526
Toward Game Level Generation from Gameplay Videos. Grounding object perception in a naive agent’s sensorimotor experience. Using Social Networks to Aid Homeless Shelters: Dynamic Influence Maximization under Uncertainty - An Extended Version. Learning Kernels for Structured Prediction using Polynomial Kernel Transformations. Feature-based Recursive …
Toward Game Level Generation from Gameplay Videos
| Title | Toward Game Level Generation from Gameplay Videos |
| Authors | Matthew Guzdial, Mark Riedl |
| Abstract | Algorithms that generate computer game content require game design knowledge. We present an approach to automatically learn game design knowledge for level design from gameplay videos. We further demonstrate how the acquired design knowledge can be used to generate sections of game levels. Our approach involves parsing video of people playing a game to detect the appearance of patterns of sprites and utilizing machine learning to build a probabilistic model of sprite placement. We show how rich game design information can be automatically parsed from gameplay videos and represented as a set of generative probabilistic models. We use Super Mario Bros. as a proof of concept. We evaluate our approach on a measure of playability and stylistic similarity to the original levels as represented in the gameplay videos. |
| Tasks | |
| Published | 2016-02-23 |
| URL | http://arxiv.org/abs/1602.07721v1 |
| http://arxiv.org/pdf/1602.07721v1.pdf | |
| PWC | https://paperswithcode.com/paper/toward-game-level-generation-from-gameplay |
| Repo | |
| Framework | |
Grounding object perception in a naive agent’s sensorimotor experience
| Title | Grounding object perception in a naive agent’s sensorimotor experience |
| Authors | Alban Laflaquière, Nikolas Hemion |
| Abstract | Artificial object perception usually relies on a priori defined models and feature extraction algorithms. We study how the concept of object can be grounded in the sensorimotor experience of a naive agent. Without any knowledge about itself or the world it is immersed in, the agent explores its sensorimotor space and identifies objects as consistent networks of sensorimotor transitions, independent from their context. A fundamental drive for prediction is assumed to explain the emergence of such networks from a developmental standpoint. An algorithm is proposed and tested to illustrate the approach. |
| Tasks | |
| Published | 2016-09-26 |
| URL | http://arxiv.org/abs/1609.08009v1 |
| http://arxiv.org/pdf/1609.08009v1.pdf | |
| PWC | https://paperswithcode.com/paper/grounding-object-perception-in-a-naive-agents |
| Repo | |
| Framework | |
Using Social Networks to Aid Homeless Shelters: Dynamic Influence Maximization under Uncertainty - An Extended Version
| Title | Using Social Networks to Aid Homeless Shelters: Dynamic Influence Maximization under Uncertainty - An Extended Version |
| Authors | Amulya Yadav, Hau Chan, Albert Jiang, Haifeng Xu, Eric Rice, Milind Tambe |
| Abstract | This paper presents HEALER, a software agent that recommends sequential intervention plans for use by homeless shelters, who organize these interventions to raise awareness about HIV among homeless youth. HEALER’s sequential plans (built using knowledge of social networks of homeless youth) choose intervention participants strategically to maximize influence spread, while reasoning about uncertainties in the network. While previous work presents influence maximizing techniques to choose intervention participants, they do not address three real-world issues: (i) they completely fail to scale up to real-world sizes; (ii) they do not handle deviations in execution of intervention plans; (iii) constructing real-world social networks is an expensive process. HEALER handles these issues via four major contributions: (i) HEALER casts this influence maximization problem as a POMDP and solves it using a novel planner which scales up to previously unsolvable real-world sizes; (ii) HEALER allows shelter officials to modify its recommendations, and updates its future plans in a deviation-tolerant manner; (iii) HEALER constructs social networks of homeless youth at low cost, using a Facebook application. Finally, (iv) we show hardness results for the problem that HEALER solves. HEALER will be deployed in the real world in early Spring 2016 and is currently undergoing testing at a homeless shelter. |
| Tasks | |
| Published | 2016-01-30 |
| URL | http://arxiv.org/abs/1602.00165v1 |
| http://arxiv.org/pdf/1602.00165v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-social-networks-to-aid-homeless |
| Repo | |
| Framework | |
Learning Kernels for Structured Prediction using Polynomial Kernel Transformations
| Title | Learning Kernels for Structured Prediction using Polynomial Kernel Transformations |
| Authors | Chetan Tonde, Ahmed Elgammal |
| Abstract | Learning the kernel functions used in kernel methods has been a vastly explored area in machine learning. It is now widely accepted that to obtain ‘good’ performance, learning a kernel function is the key challenge. In this work we focus on learning kernel representations for structured regression. We propose use of polynomials expansion of kernels, referred to as Schoenberg transforms and Gegenbaur transforms, which arise from the seminal result of Schoenberg (1938). These kernels can be thought of as polynomial combination of input features in a high dimensional reproducing kernel Hilbert space (RKHS). We learn kernels over input and output for structured data, such that, dependency between kernel features is maximized. We use Hilbert-Schmidt Independence Criterion (HSIC) to measure this. We also give an efficient, matrix decomposition-based algorithm to learn these kernel transformations, and demonstrate state-of-the-art results on several real-world datasets. |
| Tasks | Structured Prediction |
| Published | 2016-01-07 |
| URL | http://arxiv.org/abs/1601.01411v1 |
| http://arxiv.org/pdf/1601.01411v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-kernels-for-structured-prediction |
| Repo | |
| Framework | |
Feature-based Recursive Observer Design for Homography Estimation
| Title | Feature-based Recursive Observer Design for Homography Estimation |
| Authors | Minh-Duc Hua, Jochen Trumpf, Tarek Hamel, Robert Mahony, Pascal Morin |
| Abstract | This paper presents a new algorithm for online estimation of a sequence of homographies applicable to image sequences obtained from robotic vehicles equipped with vision sensors. The approach taken exploits the underlying Special Linear group structure of the set of homographies along with gyroscope measurements and direct point-feature correspondences between images to develop temporal filter for the homography estimate. Theoretical analysis and experimental results are provided to demonstrate the robustness of the proposed algorithm. The experimental results show excellent performance even in the case of very fast camera motion (relative to frame rate), severe occlusion, and in the presence of specular reflections. |
| Tasks | Homography Estimation |
| Published | 2016-06-09 |
| URL | http://arxiv.org/abs/1606.03021v1 |
| http://arxiv.org/pdf/1606.03021v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-based-recursive-observer-design-for |
| Repo | |
| Framework | |
A Convolutional Neural Network Neutrino Event Classifier
| Title | A Convolutional Neural Network Neutrino Event Classifier |
| Authors | A. Aurisano, A. Radovic, D. Rocco, A. Himmel, M. D. Messier, E. Niner, G. Pawloski, F. Psihas, A. Sousa, P. Vahle |
| Abstract | Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration. |
| Tasks | |
| Published | 2016-04-05 |
| URL | http://arxiv.org/abs/1604.01444v3 |
| http://arxiv.org/pdf/1604.01444v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-convolutional-neural-network-neutrino-event |
| Repo | |
| Framework | |
Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization
| Title | Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization |
| Authors | Xiao Wang, Shiqian Ma, Donald Goldfarb, Wei Liu |
| Abstract | In this paper we study stochastic quasi-Newton methods for nonconvex stochastic optimization, where we assume that noisy information about the gradients of the objective function is available via a stochastic first-order oracle (SFO). We propose a general framework for such methods, for which we prove almost sure convergence to stationary points and analyze its worst-case iteration complexity. When a randomly chosen iterate is returned as the output of such an algorithm, we prove that in the worst-case, the SFO-calls complexity is $O(\epsilon^{-2})$ to ensure that the expectation of the squared norm of the gradient is smaller than the given accuracy tolerance $\epsilon$. We also propose a specific algorithm, namely a stochastic damped L-BFGS (SdLBFGS) method, that falls under the proposed framework. {Moreover, we incorporate the SVRG variance reduction technique into the proposed SdLBFGS method, and analyze its SFO-calls complexity. Numerical results on a nonconvex binary classification problem using SVM, and a multiclass classification problem using neural networks are reported. |
| Tasks | Stochastic Optimization |
| Published | 2016-07-05 |
| URL | http://arxiv.org/abs/1607.01231v4 |
| http://arxiv.org/pdf/1607.01231v4.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-quasi-newton-methods-for-nonconvex |
| Repo | |
| Framework | |
Effective Blind Source Separation Based on the Adam Algorithm
| Title | Effective Blind Source Separation Based on the Adam Algorithm |
| Authors | Michele Scarpiniti, Simone Scardapane, Danilo Comminiello, Raffaele Parisi, Aurelio Uncini |
| Abstract | In this paper, we derive a modified InfoMax algorithm for the solution of Blind Signal Separation (BSS) problems by using advanced stochastic methods. The proposed approach is based on a novel stochastic optimization approach known as the Adaptive Moment Estimation (Adam) algorithm. The proposed BSS solution can benefit from the excellent properties of the Adam approach. In order to derive the new learning rule, the Adam algorithm is introduced in the derivation of the cost function maximization in the standard InfoMax algorithm. The natural gradient adaptation is also considered. Finally, some experimental results show the effectiveness of the proposed approach. |
| Tasks | Stochastic Optimization |
| Published | 2016-05-25 |
| URL | http://arxiv.org/abs/1605.07833v2 |
| http://arxiv.org/pdf/1605.07833v2.pdf | |
| PWC | https://paperswithcode.com/paper/effective-blind-source-separation-based-on |
| Repo | |
| Framework | |
Learning to superoptimize programs - Workshop Version
| Title | Learning to superoptimize programs - Workshop Version |
| Authors | Rudy Bunel, Alban Desmaison, M. Pawan Kumar, Philip H. S. Torr, Pushmeet Kohli |
| Abstract | Superoptimization requires the estimation of the best program for a given computational task. In order to deal with large programs, superoptimization techniques perform a stochastic search. This involves proposing a modification of the current program, which is accepted or rejected based on the improvement achieved. The state of the art method uses uniform proposal distributions, which fails to exploit the problem structure to the fullest. To alleviate this deficiency, we learn a proposal distribution over possible modifications using Reinforcement Learning. We provide convincing results on the superoptimization of “Hacker’s Delight” programs. |
| Tasks | |
| Published | 2016-12-04 |
| URL | http://arxiv.org/abs/1612.01094v1 |
| http://arxiv.org/pdf/1612.01094v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-superoptimize-programs-workshop |
| Repo | |
| Framework | |
Inference rules for RDF(S) and OWL in N3Logic
| Title | Inference rules for RDF(S) and OWL in N3Logic |
| Authors | Dominik Tomaszuk |
| Abstract | This paper presents inference rules for Resource Description Framework (RDF), RDF Schema (RDFS) and Web Ontology Language (OWL). Our formalization is based on Notation 3 Logic, which extended RDF by logical symbols and created Semantic Web logic for deductive RDF graph stores. We also propose OWL-P that is a lightweight formalism of OWL and supports soft inferences by omitting complex language constructs. |
| Tasks | |
| Published | 2016-01-11 |
| URL | http://arxiv.org/abs/1601.02650v1 |
| http://arxiv.org/pdf/1601.02650v1.pdf | |
| PWC | https://paperswithcode.com/paper/inference-rules-for-rdfs-and-owl-in-n3logic |
| Repo | |
| Framework | |
Meta-learning within Projective Simulation
| Title | Meta-learning within Projective Simulation |
| Authors | Adi Makmal, Alexey A. Melnikov, Vedran Dunjko, Hans J. Briegel |
| Abstract | Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal, approach. Most non-trivial models thus require the adjustment of several to many learning parameters, which is often done on a case-by-case basis by an external party. Meta-learning refers to the ability of an agent to autonomously and dynamically adjust its own learning parameters, or meta-parameters. In this work we show how projective simulation, a recently developed model of artificial intelligence, can naturally be extended to account for meta-learning in reinforcement learning settings. The projective simulation approach is based on a random walk process over a network of clips. The suggested meta-learning scheme builds upon the same design and employs clip networks to monitor the agent’s performance and to adjust its meta-parameters “on the fly”. We distinguish between “reflexive adaptation” and “adaptation through learning”, and show the utility of both approaches. In addition, a trade-off between flexibility and learning-time is addressed. The extended model is examined on three different kinds of reinforcement learning tasks, in which the agent has different optimal values of the meta-parameters, and is shown to perform well, reaching near-optimal to optimal success rates in all of them, without ever needing to manually adjust any meta-parameter. |
| Tasks | Meta-Learning |
| Published | 2016-02-25 |
| URL | http://arxiv.org/abs/1602.08017v1 |
| http://arxiv.org/pdf/1602.08017v1.pdf | |
| PWC | https://paperswithcode.com/paper/meta-learning-within-projective-simulation |
| Repo | |
| Framework | |
Cross Domain Knowledge Transfer for Person Re-identification
| Title | Cross Domain Knowledge Transfer for Person Re-identification |
| Authors | Qiqi Xiao, Kelei Cao, Haonan Chen, Fangyue Peng, Chi Zhang |
| Abstract | Person Re-Identification (re-id) is a challenging task in computer vision, especially when there are limited training data from multiple camera views. In this paper, we pro- pose a deep learning based person re-identification method by transferring knowledge of mid-level attribute features and high-level classification features. Building on the idea that identity classification, attribute recognition and re- identification share the same mid-level semantic representations, they can be trained sequentially by fine-tuning one based on another. In our framework, we train identity classification and attribute recognition tasks from deep Convolutional Neural Network (dCNN) to learn person information. The information can be transferred to the person re-id task and improves its accuracy by a large margin. Further- more, a Long Short Term Memory(LSTM) based Recurrent Neural Network (RNN) component is extended by a spacial gate. This component is used in the re-id model to pay attention to certain spacial parts in each recurrent unit. Experimental results show that our method achieves 78.3% of rank-1 recognition accuracy on the CUHK03 benchmark. |
| Tasks | Person Re-Identification, Transfer Learning |
| Published | 2016-11-18 |
| URL | http://arxiv.org/abs/1611.06026v1 |
| http://arxiv.org/pdf/1611.06026v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-domain-knowledge-transfer-for-person-re |
| Repo | |
| Framework | |
A Motion Planning Strategy for the Active Vision-Based Mapping of Ground-Level Structures
| Title | A Motion Planning Strategy for the Active Vision-Based Mapping of Ground-Level Structures |
| Authors | Manikandasriram Srinivasan Ramanagopal, André Phu-Van Nguyen, Jerome Le Ny |
| Abstract | This paper presents a strategy to guide a mobile ground robot equipped with a camera or depth sensor, in order to autonomously map the visible part of a bounded three-dimensional structure. We describe motion planning algorithms that determine appropriate successive viewpoints and attempt to fill holes automatically in a point cloud produced by the sensing and perception layer. The emphasis is on accurately reconstructing a 3D model of a structure of moderate size rather than mapping large open environments, with applications for example in architecture, construction and inspection. The proposed algorithms do not require any initialization in the form of a mesh model or a bounding box, and the paths generated are well adapted to situations where the vision sensor is used simultaneously for mapping and for localizing the robot, in the absence of additional absolute positioning system. We analyze the coverage properties of our policy, and compare its performance to the classic frontier based exploration algorithm. We illustrate its efficacy for different structure sizes, levels of localization accuracy and range of the depth sensor, and validate our design on a real-world experiment. |
| Tasks | Motion Planning |
| Published | 2016-02-22 |
| URL | http://arxiv.org/abs/1602.06667v3 |
| http://arxiv.org/pdf/1602.06667v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-motion-planning-strategy-for-the-active |
| Repo | |
| Framework | |
Low-tubal-rank Tensor Completion using Alternating Minimization
| Title | Low-tubal-rank Tensor Completion using Alternating Minimization |
| Authors | Xiao-Yang Liu, Shuchin Aeron, Vaneet Aggarwal, Xiaodong Wang |
| Abstract | The low-tubal-rank tensor model has been recently proposed for real-world multidimensional data. In this paper, we study the low-tubal-rank tensor completion problem, i.e., to recover a third-order tensor by observing a subset of its elements selected uniformly at random. We propose a fast iterative algorithm, called {\em Tubal-Alt-Min}, that is inspired by a similar approach for low-rank matrix completion. The unknown low-tubal-rank tensor is represented as the product of two much smaller tensors with the low-tubal-rank property being automatically incorporated, and Tubal-Alt-Min alternates between estimating those two tensors using tensor least squares minimization. First, we note that tensor least squares minimization is different from its matrix counterpart and nontrivial as the circular convolution operator of the low-tubal-rank tensor model is intertwined with the sub-sampling operator. Second, the theoretical performance guarantee is challenging since Tubal-Alt-Min is iterative and nonconvex in nature. We prove that 1) Tubal-Alt-Min guarantees exponential convergence to the global optima, and 2) for an $n \times n \times k$ tensor with tubal-rank $r \ll n$, the required sampling complexity is $O(nr^2k \log^3 n)$ and the computational complexity is $O(n^2rk^2 \log^2 n)$. Third, on both synthetic data and real-world video data, evaluation results show that compared with tensor-nuclear norm minimization (TNN-ADMM), Tubal-Alt-Min improves the recovery error dramatically (by orders of magnitude). It is estimated that Tubal-Alt-Min converges at an exponential rate $10^{-0.4423 \text{Iter}}$ where $\text{Iter}$ denotes the number of iterations, which is much faster than TNN-ADMM’s $10^{-0.0332 \text{Iter}}$, and the running time can be accelerated by more than $5$ times for a $200 \times 200 \times 20$ tensor. |
| Tasks | Low-Rank Matrix Completion, Matrix Completion |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01690v1 |
| http://arxiv.org/pdf/1610.01690v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-tubal-rank-tensor-completion-using |
| Repo | |
| Framework | |
Fast and robust pushbroom hyperspectral imaging via DMD-based scanning
| Title | Fast and robust pushbroom hyperspectral imaging via DMD-based scanning |
| Authors | Reza Arablouei, Ethan Goan, Stephen Gensemer, Branislav Kusy |
| Abstract | We describe a new pushbroom hyperspectral imaging device that has no macro moving part. The main components of the proposed hyperspectral imager are a digital micromirror device (DMD), a CMOS image sensor with no filter as the spectral sensor, a CMOS color (RGB) image sensor as the auxiliary image sensor, and a diffraction grating. Using the image sensor pair, the device can simultaneously capture hyperspectral data as well as RGB images of the scene. The RGB images captured by the auxiliary image sensor can facilitate geometric co-registration of the hyperspectral image slices captured by the spectral sensor. In addition, the information discernible from the RGB images can lead to capturing the spectral data of only the regions of interest within the scene. The proposed hyperspectral imaging architecture is cost-effective, fast, and robust. It also enables a trade-off between resolution and speed. We have built an initial prototype based on the proposed design. The prototype can capture a hyperspectral image datacube with a spatial resolution of 192x192 pixels and a spectral resolution of 500 bands in less than thirty seconds. |
| Tasks | |
| Published | 2016-08-01 |
| URL | http://arxiv.org/abs/1608.00361v2 |
| http://arxiv.org/pdf/1608.00361v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-robust-pushbroom-hyperspectral |
| Repo | |
| Framework | |
