Paper Group ANR 219
A Description Logic Framework for Commonsense Conceptual Combination Integrating Typicality, Probabilities and Cognitive Heuristics. A Decomposition-Based Many-Objective Evolutionary Algorithm with Local Iterative Update. Analysis of adversarial attacks against CNN-based image forgery detectors. Sea surface temperature prediction and reconstruction …
A Description Logic Framework for Commonsense Conceptual Combination Integrating Typicality, Probabilities and Cognitive Heuristics
| Title | A Description Logic Framework for Commonsense Conceptual Combination Integrating Typicality, Probabilities and Cognitive Heuristics |
| Authors | Antonio Lieto, Gian Luca Pozzato |
| Abstract | We propose a nonmonotonic Description Logic of typicality able to account for the phenomenon of concept combination of prototypical concepts. The proposed logic relies on the logic of typicality ALC TR, whose semantics is based on the notion of rational closure, as well as on the distributed semantics of probabilistic Description Logics, and is equipped with a cognitive heuristic used by humans for concept composition. We first extend the logic of typicality ALC TR by typicality inclusions whose intuitive meaning is that “there is probability p about the fact that typical Cs are Ds”. As in the distributed semantics, we define different scenarios containing only some typicality inclusions, each one having a suitable probability. We then focus on those scenarios whose probabilities belong to a given and fixed range, and we exploit such scenarios in order to ascribe typical properties to a concept C obtained as the combination of two prototypical concepts. We also show that reasoning in the proposed Description Logic is EXPTIME-complete as for the underlying ALC. |
| Tasks | |
| Published | 2018-11-06 |
| URL | https://arxiv.org/abs/1811.02366v4 |
| https://arxiv.org/pdf/1811.02366v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-description-logic-framework-for-commonsense |
| Repo | |
| Framework | |
A Decomposition-Based Many-Objective Evolutionary Algorithm with Local Iterative Update
| Title | A Decomposition-Based Many-Objective Evolutionary Algorithm with Local Iterative Update |
| Authors | Yingyu Zhang, Bing Zeng |
| Abstract | Existing studies have shown that the conventional multi-objective evolutionary algorithms (MOEAs) based on decomposition may lose the population diversity when solving some many-objective optimization problems. In this paper, a simple decomposition-based MOEA with local iterative update (LIU) is proposed. The LIU strategy has two features that are expected to drive the population to approximate the Pareto Front with good distribution. One is that only the worst solution in the current neighborhood is swapped out by the newly generated offspring, preventing the population from being occupied by copies of a few individuals. The other is that its iterative process helps to assign better solutions to subproblems, which is beneficial to make full use of the similarity of solutions to neighboring subproblems and explore local areas in the search space. In addition, the time complexity of the proposed algorithm is the same as that of MOEA/D, and lower than that of other known MOEAs, since it considers only individuals within the current neighborhood at each update. The algorithm is compared with several of the best MOEAs on problems chosen from two famous test suites DTLZ and WFG. Experimental results demonstrate that only a handful of running instances of the algorithm on DTLZ4 lose their population diversity. What’s more, the algorithm wins in most of the test instances in terms of both running time and solution quality, indicating that it is very effective in solving MaOPs. |
| Tasks | |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10950v1 |
| http://arxiv.org/pdf/1806.10950v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-decomposition-based-many-objective |
| Repo | |
| Framework | |
Analysis of adversarial attacks against CNN-based image forgery detectors
| Title | Analysis of adversarial attacks against CNN-based image forgery detectors |
| Authors | Diego Gragnaniello, Francesco Marra, Giovanni Poggi, Luisa Verdoliva |
| Abstract | With the ubiquitous diffusion of social networks, images are becoming a dominant and powerful communication channel. Not surprisingly, they are also increasingly subject to manipulations aimed at distorting information and spreading fake news. In recent years, the scientific community has devoted major efforts to contrast this menace, and many image forgery detectors have been proposed. Currently, due to the success of deep learning in many multimedia processing tasks, there is high interest towards CNN-based detectors, and early results are already very promising. Recent studies in computer vision, however, have shown CNNs to be highly vulnerable to adversarial attacks, small perturbations of the input data which drive the network towards erroneous classification. In this paper we analyze the vulnerability of CNN-based image forensics methods to adversarial attacks, considering several detectors and several types of attack, and testing performance on a wide range of common manipulations, both easily and hardly detectable. |
| Tasks | |
| Published | 2018-08-25 |
| URL | http://arxiv.org/abs/1808.08426v1 |
| http://arxiv.org/pdf/1808.08426v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-adversarial-attacks-against-cnn |
| Repo | |
| Framework | |
Sea surface temperature prediction and reconstruction using patch-level neural network representations
| Title | Sea surface temperature prediction and reconstruction using patch-level neural network representations |
| Authors | Said Ouala, Cedric Herzet, Ronan Fablet |
| Abstract | The forecasting and reconstruction of ocean and atmosphere dynamics from satellite observation time series are key challenges. While model-driven representations remain the classic approaches, data-driven representations become more and more appealing to benefit from available large-scale observation and simulation datasets. In this work we investigate the relevance of recently introduced bilinear residual neural network representations, which mimic numerical integration schemes such as Runge-Kutta, for the forecasting and assimilation of geophysical fields from satellite-derived remote sensing data. As a case-study, we consider satellite-derived Sea Surface Temperature time series off South Africa, which involves intense and complex upper ocean dynamics. Our numerical experiments demonstrate that the proposed patch-level neural-network-based representations outperform other data-driven models, including analog schemes, both in terms of forecasting and missing data interpolation performance with a relative gain up to 50% for highly dynamic areas. |
| Tasks | Time Series |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.00144v1 |
| http://arxiv.org/pdf/1806.00144v1.pdf | |
| PWC | https://paperswithcode.com/paper/sea-surface-temperature-prediction-and |
| Repo | |
| Framework | |
Unsupervised Semantic Deep Hashing
| Title | Unsupervised Semantic Deep Hashing |
| Authors | Sheng Jin |
| Abstract | In recent years, deep hashing methods have been proved to be efficient since it employs convolutional neural network to learn features and hashing codes simultaneously. However, these methods are mostly supervised. In real-world application, it is a time-consuming and overloaded task for annotating a large number of images. In this paper, we propose a novel unsupervised deep hashing method for large-scale image retrieval. Our method, namely unsupervised semantic deep hashing (\textbf{USDH}), uses semantic information preserved in the CNN feature layer to guide the training of network. We enforce four criteria on hashing codes learning based on VGG-19 model: 1) preserving relevant information of feature space in hashing space; 2) minimizing quantization loss between binary-like codes and hashing codes; 3) improving the usage of each bit in hashing codes by using maximum information entropy, and 4) invariant to image rotation. Extensive experiments on CIFAR-10, NUSWIDE have demonstrated that \textbf{USDH} outperforms several state-of-the-art unsupervised hashing methods for image retrieval. We also conduct experiments on Oxford 17 datasets for fine-grained classification to verify its efficiency for other computer vision tasks. |
| Tasks | Image Retrieval, Quantization |
| Published | 2018-03-19 |
| URL | http://arxiv.org/abs/1803.06911v1 |
| http://arxiv.org/pdf/1803.06911v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-semantic-deep-hashing |
| Repo | |
| Framework | |
Recent Advances in Autoencoder-Based Representation Learning
| Title | Recent Advances in Autoencoder-Based Representation Learning |
| Authors | Michael Tschannen, Olivier Bachem, Mario Lucic |
| Abstract | Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize these results we make use of meta-priors believed useful for downstream tasks, such as disentanglement and hierarchical organization of features. In particular, we uncover three main mechanisms to enforce such properties, namely (i) regularizing the (approximate or aggregate) posterior distribution, (ii) factorizing the encoding and decoding distribution, or (iii) introducing a structured prior distribution. While there are some promising results, implicit or explicit supervision remains a key enabler and all current methods use strong inductive biases and modeling assumptions. Finally, we provide an analysis of autoencoder-based representation learning through the lens of rate-distortion theory and identify a clear tradeoff between the amount of prior knowledge available about the downstream tasks, and how useful the representation is for this task. |
| Tasks | Representation Learning |
| Published | 2018-12-12 |
| URL | http://arxiv.org/abs/1812.05069v1 |
| http://arxiv.org/pdf/1812.05069v1.pdf | |
| PWC | https://paperswithcode.com/paper/recent-advances-in-autoencoder-based |
| Repo | |
| Framework | |
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
| Title | SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference |
| Authors | Rowan Zellers, Yonatan Bisk, Roy Schwartz, Yejin Choi |
| Abstract | Given a partial description like “she opened the hood of the car,” humans can reason about the situation and anticipate what might come next (“then, she examined the engine”). In this paper, we introduce the task of grounded commonsense inference, unifying natural language inference and commonsense reasoning. We present SWAG, a new dataset with 113k multiple choice questions about a rich spectrum of grounded situations. To address the recurring challenges of the annotation artifacts and human biases found in many existing datasets, we propose Adversarial Filtering (AF), a novel procedure that constructs a de-biased dataset by iteratively training an ensemble of stylistic classifiers, and using them to filter the data. To account for the aggressive adversarial filtering, we use state-of-the-art language models to massively oversample a diverse set of potential counterfactuals. Empirical results demonstrate that while humans can solve the resulting inference problems with high accuracy (88%), various competitive models struggle on our task. We provide comprehensive analysis that indicates significant opportunities for future research. |
| Tasks | Common Sense Reasoning, Natural Language Inference, Question Answering |
| Published | 2018-08-16 |
| URL | http://arxiv.org/abs/1808.05326v1 |
| http://arxiv.org/pdf/1808.05326v1.pdf | |
| PWC | https://paperswithcode.com/paper/swag-a-large-scale-adversarial-dataset-for |
| Repo | |
| Framework | |
ProdSumNet: reducing model parameters in deep neural networks via product-of-sums matrix decompositions
| Title | ProdSumNet: reducing model parameters in deep neural networks via product-of-sums matrix decompositions |
| Authors | Chai Wah Wu |
| Abstract | We consider a general framework for reducing the number of trainable model parameters in deep learning networks by decomposing linear operators as a product of sums of simpler linear operators. Recently proposed deep learning architectures such as CNN, KFC, Dilated CNN, etc. are all subsumed in this framework and we illustrate other types of neural network architectures within this framework. We show that good accuracy on MNIST and Fashion MNIST can be obtained using a relatively small number of trainable parameters. In addition, since implementation of the convolutional layer is resource-heavy, we consider an approach in the transform domain that obviates the need for convolutional layers. One of the advantages of this general framework over prior approaches is that the number of trainable parameters is not fixed and can be varied arbitrarily. In particular, we illustrate the tradeoff of varying the number of trainable variables and the corresponding error rate. As an example, by using this decomposition on a reference CNN architecture for MNIST with over 3x10^6 trainable parameters, we are able to obtain an accuracy of 98.44% using only 3554 trainable parameters. |
| Tasks | |
| Published | 2018-09-06 |
| URL | https://arxiv.org/abs/1809.02209v2 |
| https://arxiv.org/pdf/1809.02209v2.pdf | |
| PWC | https://paperswithcode.com/paper/prodsumnet-reducing-model-parameters-in-deep |
| Repo | |
| Framework | |
DeepDPM: Dynamic Population Mapping via Deep Neural Network
| Title | DeepDPM: Dynamic Population Mapping via Deep Neural Network |
| Authors | Zefang Zong, Jie Feng, Kechun Liu, Hongzhi Shi, Yong Li |
| Abstract | Dynamic high resolution data on human population distribution is of great importance for a wide spectrum of activities and real-life applications, but is too difficult and expensive to obtain directly. Therefore, generating fine-scaled population distributions from coarse population data is of great significance. However, there are three major challenges: 1) the complexity in spatial relations between high and low resolution population; 2) the dependence of population distributions on other external information; 3) the difficulty in retrieving temporal distribution patterns. In this paper, we first propose the idea to generate dynamic population distributions in full-time series, then we design dynamic population mapping via deep neural network(DeepDPM), a model that describes both spatial and temporal patterns using coarse data and point of interest information. In DeepDPM, we utilize super-resolution convolutional neural network(SRCNN) based model to directly map coarse data into higher resolution data, and a time-embedded long short-term memory model to effectively capture the periodicity nature to smooth the finer-scaled results from the previous static SRCNN model. We perform extensive experiments on a real-life mobile dataset collected from Shanghai. Our results demonstrate that DeepDPM outperforms previous state-of-the-art methods and a suite of frequent data-mining approaches. Moreover, DeepDPM breaks through the limitation from previous works in time dimension so that dynamic predictions in all-day time slots can be obtained. |
| Tasks | Population Mapping, Super-Resolution, Time Series |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1811.02644v2 |
| http://arxiv.org/pdf/1811.02644v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepdpm-dynamic-population-mapping-via-deep |
| Repo | |
| Framework | |
Multi-modal Disease Classification in Incomplete Datasets Using Geometric Matrix Completion
| Title | Multi-modal Disease Classification in Incomplete Datasets Using Geometric Matrix Completion |
| Authors | Gerome Vivar, Andreas Zwergal, Nassir Navab, Seyed-Ahmad Ahmadi |
| Abstract | In large population-based studies and in clinical routine, tasks like disease diagnosis and progression prediction are inherently based on a rich set of multi-modal data, including imaging and other sensor data, clinical scores, phenotypes, labels and demographics. However, missing features, rater bias and inaccurate measurements are typical ailments of real-life medical datasets. Recently, it has been shown that deep learning with graph convolution neural networks (GCN) can outperform traditional machine learning in disease classification, but missing features remain an open problem. In this work, we follow up on the idea of modeling multi-modal disease classification as a matrix completion problem, with simultaneous classification and non-linear imputation of features. Compared to methods before, we arrange subjects in a graph-structure and solve classification through geometric matrix completion, which simulates a heat diffusion process that is learned and solved with a recurrent neural network. We demonstrate the potential of this method on the ADNI-based TADPOLE dataset and on the task of predicting the transition from MCI to Alzheimer’s disease. With an AUC of 0.950 and classification accuracy of 87%, our approach outperforms standard linear and non-linear classifiers, as well as several state-of-the-art results in related literature, including a recently proposed GCN-based approach. |
| Tasks | Imputation, Matrix Completion |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11550v1 |
| http://arxiv.org/pdf/1803.11550v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-disease-classification-in |
| Repo | |
| Framework | |
Stein Variational Gradient Descent as Moment Matching
| Title | Stein Variational Gradient Descent as Moment Matching |
| Authors | Qiang Liu, Dilin Wang |
| Abstract | Stein variational gradient descent (SVGD) is a non-parametric inference algorithm that evolves a set of particles to fit a given distribution of interest. We analyze the non-asymptotic properties of SVGD, showing that there exists a set of functions, which we call the Stein matching set, whose expectations are exactly estimated by any set of particles that satisfies the fixed point equation of SVGD. This set is the image of Stein operator applied on the feature maps of the positive definite kernel used in SVGD. Our results provide a theoretical framework for analyzing the properties of SVGD with different kernels, shedding insight into optimal kernel choice. In particular, we show that SVGD with linear kernels yields exact estimation of means and variances on Gaussian distributions, while random Fourier features enable probabilistic bounds for distributional approximation. Our results offer a refreshing view of the classical inference problem as fitting Stein’s identity or solving the Stein equation, which may motivate more efficient algorithms. |
| Tasks | |
| Published | 2018-10-27 |
| URL | http://arxiv.org/abs/1810.11693v1 |
| http://arxiv.org/pdf/1810.11693v1.pdf | |
| PWC | https://paperswithcode.com/paper/stein-variational-gradient-descent-as-moment |
| Repo | |
| Framework | |
Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goals
| Title | Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goals |
| Authors | Vikas Dhiman, Shurjo Banerjee, Jeffrey M. Siskind, Jason J. Corso |
| Abstract | Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for such tasks: model-free or model-based. Each of these approaches has limitations. Model-free RL struggles to transfer learned information when the goal location changes, but achieves high asymptotic accuracy in single goal tasks. Model-based RL can transfer learned information to new goal locations by retaining the explicitly learned state-dynamics, but is limited by the fact that small errors in modelling these dynamics accumulate over long-term planning. In this work, we improve upon the limitations of model-free RL in multi-goal domains. We do this by adapting the Floyd-Warshall algorithm for RL and call the adaptation Floyd-Warshall RL (FWRL). The proposed algorithm learns a goal-conditioned action-value function by constraining the value of the optimal path between any two states to be greater than or equal to the value of paths via intermediary states. Experimentally, we show that FWRL is more sample-efficient and learns higher reward strategies in multi-goal tasks as compared to Q-learning, model-based RL and other relevant baselines in a tabular domain. |
| Tasks | Q-Learning |
| Published | 2018-09-25 |
| URL | http://arxiv.org/abs/1809.09318v4 |
| http://arxiv.org/pdf/1809.09318v4.pdf | |
| PWC | https://paperswithcode.com/paper/floyd-warshall-reinforcement-learning |
| Repo | |
| Framework | |
All-Optical Machine Learning Using Diffractive Deep Neural Networks
| Title | All-Optical Machine Learning Using Diffractive Deep Neural Networks |
| Authors | Xing Lin, Yair Rivenson, Nezih T. Yardimci, Muhammed Veli, Mona Jarrahi, Aydogan Ozcan |
| Abstract | We introduce an all-optical Diffractive Deep Neural Network (D2NN) architecture that can learn to implement various functions after deep learning-based design of passive diffractive layers that work collectively. We experimentally demonstrated the success of this framework by creating 3D-printed D2NNs that learned to implement handwritten digit classification and the function of an imaging lens at terahertz spectrum. With the existing plethora of 3D-printing and other lithographic fabrication methods as well as spatial-light-modulators, this all-optical deep learning framework can perform, at the speed of light, various complex functions that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs. |
| Tasks | Object Classification |
| Published | 2018-04-14 |
| URL | http://arxiv.org/abs/1804.08711v2 |
| http://arxiv.org/pdf/1804.08711v2.pdf | |
| PWC | https://paperswithcode.com/paper/all-optical-machine-learning-using |
| Repo | |
| Framework | |
Transductive Boltzmann Machines
| Title | Transductive Boltzmann Machines |
| Authors | Mahito Sugiyama, Koji Tsuda, Hiroyuki Nakahara |
| Abstract | We present transductive Boltzmann machines (TBMs), which firstly achieve transductive learning of the Gibbs distribution. While exact learning of the Gibbs distribution is impossible by the family of existing Boltzmann machines due to combinatorial explosion of the sample space, TBMs overcome the problem by adaptively constructing the minimum required sample space from data to avoid unnecessary generalization. We theoretically provide bias-variance decomposition of the KL divergence in TBMs to analyze its learnability, and empirically demonstrate that TBMs are superior to the fully visible Boltzmann machines and popularly used restricted Boltzmann machines in terms of efficiency and effectiveness. |
| Tasks | |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.07938v1 |
| http://arxiv.org/pdf/1805.07938v1.pdf | |
| PWC | https://paperswithcode.com/paper/transductive-boltzmann-machines |
| Repo | |
| Framework | |
Robust Optimization through Neuroevolution
| Title | Robust Optimization through Neuroevolution |
| Authors | Paolo Pagliuca, Stefano Nolfi |
| Abstract | We propose a method for evolving solutions that are robust with respect to variations of the environmental conditions (i.e. that can operate effectively in new conditions immediately, without the need to adapt to variations). The obtained results show how the method proposed is effective and computational tractable. It permits to improve performance on an extended version of the double-pole balancing problem, to outperform the best available human-designed controllers on a car racing problem, and to generate rather effective solutions for a swarm robotic problem. The comparison of different algorithms indicates that the CMA-ES and xNES methods, that operate by optimizing a distribution of parameters, represent the best options for the evolution of robust neural network controllers. |
| Tasks | Car Racing |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01125v1 |
| http://arxiv.org/pdf/1810.01125v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-optimization-through-neuroevolution |
| Repo | |
| Framework | |
