Paper Group ANR 405
Plausibility and probability in deductive reasoning. ENIGMA: Efficient Learning-based Inference Guiding Machine. Translating Terminological Expressions in Knowledge Bases with Neural Machine Translation. Image Patch Matching Using Convolutional Descriptors with Euclidean Distance. Training Spiking Neural Networks for Cognitive Tasks: A Versatile Fr …
Plausibility and probability in deductive reasoning
| Title | Plausibility and probability in deductive reasoning |
| Authors | Andrew MacFie |
| Abstract | We consider the problem of rational uncertainty about unproven mathematical statements, remarked on by G"odel and others. Using Bayesian-inspired arguments we build a normative model of fair bets under deductive uncertainty which draws from both probability and the theory of algorithms. We comment on connections to Zeilberger’s notion of “semi-rigorous proofs”, particularly that inherent subjectivity would be present. We also discuss a financial view with models of arbitrage where traders have limited computational resources. |
| Tasks | |
| Published | 2017-08-29 |
| URL | https://arxiv.org/abs/1708.09032v6 |
| https://arxiv.org/pdf/1708.09032v6.pdf | |
| PWC | https://paperswithcode.com/paper/plausibility-and-probability-in-deductive |
| Repo | |
| Framework | |
ENIGMA: Efficient Learning-based Inference Guiding Machine
| Title | ENIGMA: Efficient Learning-based Inference Guiding Machine |
| Authors | Jan Jakubův, Josef Urban |
| Abstract | ENIGMA is a learning-based method for guiding given clause selection in saturation-based theorem provers. Clauses from many proof searches are classified as positive and negative based on their participation in the proofs. An efficient classification model is trained on this data, using fast feature-based characterization of the clauses . The learned model is then tightly linked with the core prover and used as a basis of a new parameterized evaluation heuristic that provides fast ranking of all generated clauses. The approach is evaluated on the E prover and the CASC 2016 AIM benchmark, showing a large increase of E’s performance. |
| Tasks | |
| Published | 2017-01-23 |
| URL | http://arxiv.org/abs/1701.06532v1 |
| http://arxiv.org/pdf/1701.06532v1.pdf | |
| PWC | https://paperswithcode.com/paper/enigma-efficient-learning-based-inference |
| Repo | |
| Framework | |
Translating Terminological Expressions in Knowledge Bases with Neural Machine Translation
| Title | Translating Terminological Expressions in Knowledge Bases with Neural Machine Translation |
| Authors | Mihael Arcan, Daniel Torregrosa, Paul Buitelaar |
| Abstract | Our work presented in this paper focuses on the translation of terminological expressions represented in semantically structured resources, like ontologies or knowledge graphs. The challenge of translating ontology labels or terminological expressions documented in knowledge bases lies in the highly specific vocabulary and the lack of contextual information, which can guide a machine translation system to translate ambiguous words into the targeted domain. Due to these challenges, we evaluate the translation quality of domain-specific expressions in the medical and financial domain with statistical as well as with neural machine translation methods and experiment domain adaptation of the translation models with terminological expressions only. Furthermore, we perform experiments on the injection of external terminological expressions into the translation systems. Through these experiments, we observed a significant advantage in domain adaptation for the domain-specific resource in the medical and financial domain and the benefit of subword models over word-based neural machine translation models for terminology translation. |
| Tasks | Domain Adaptation, Knowledge Graphs, Machine Translation |
| Published | 2017-09-07 |
| URL | https://arxiv.org/abs/1709.02184v3 |
| https://arxiv.org/pdf/1709.02184v3.pdf | |
| PWC | https://paperswithcode.com/paper/translating-terminological-expressions-in |
| Repo | |
| Framework | |
Image Patch Matching Using Convolutional Descriptors with Euclidean Distance
| Title | Image Patch Matching Using Convolutional Descriptors with Euclidean Distance |
| Authors | Iaroslav Melekhov, Juho Kannala, Esa Rahtu |
| Abstract | In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is influenced by recent success of deep convolutional neural networks (CNNs) in object detection and classification tasks. We develop a model which maps the raw input patch to a low dimensional feature vector so that the distance between representations is small for similar patches and large otherwise. As a distance metric we utilize L2 norm, i.e. Euclidean distance, which is fast to evaluate and used in most popular hand-crafted descriptors, such as SIFT. According to the results, our approach outperforms state-of-the-art L2-based descriptors and can be considered as a direct replacement of SIFT. In addition, we conducted experiments with batch normalization and histogram equalization as a preprocessing method of the input data. The results confirm that these techniques further improve the performance of the proposed descriptor. Finally, we show promising preliminary results by appending our CNNs with recently proposed spatial transformer networks and provide a visualisation and interpretation of their impact. |
| Tasks | Object Detection |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11359v1 |
| http://arxiv.org/pdf/1710.11359v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-patch-matching-using-convolutional |
| Repo | |
| Framework | |
Training Spiking Neural Networks for Cognitive Tasks: A Versatile Framework Compatible to Various Temporal Codes
| Title | Training Spiking Neural Networks for Cognitive Tasks: A Versatile Framework Compatible to Various Temporal Codes |
| Authors | Chaofei Hong |
| Abstract | Conventional modeling approaches have found limitations in matching the increasingly detailed neural network structures and dynamics recorded in experiments to the diverse brain functionalities. On another approach, studies have demonstrated to train spiking neural networks for simple functions using supervised learning. Here, we introduce a modified SpikeProp learning algorithm, which achieved better learning stability in different activity states. In addition, we show biological realistic features such as lateral connections and sparse activities can be included in the network. We demonstrate the versatility of this framework by implementing three well-known temporal codes for different types of cognitive tasks, which are MNIST digits recognition, spatial coordinate transformation, and motor sequence generation. Moreover, we find several characteristic features have evolved alongside the task training, such as selective activity, excitatory-inhibitory balance, and weak pair-wise correlation. The coincidence between the self-evolved and experimentally observed features indicates their importance on the brain functionality. Our results suggest a unified setting in which diverse cognitive computations and mechanisms can be studied. |
| Tasks | |
| Published | 2017-09-02 |
| URL | http://arxiv.org/abs/1709.00583v1 |
| http://arxiv.org/pdf/1709.00583v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-spiking-neural-networks-for |
| Repo | |
| Framework | |
Learning to Price with Reference Effects
| Title | Learning to Price with Reference Effects |
| Authors | Abbas Kazerouni, Benjamin Van Roy |
| Abstract | As a firm varies the price of a product, consumers exhibit reference effects, making purchase decisions based not only on the prevailing price but also the product’s price history. We consider the problem of learning such behavioral patterns as a monopolist releases, markets, and prices products. This context calls for pricing decisions that intelligently trade off between maximizing revenue generated by a current product and probing to gain information for future benefit. Due to dependence on price history, realized demand can reflect delayed consequences of earlier pricing decisions. As such, inference entails attribution of outcomes to prior decisions and effective exploration requires planning price sequences that yield informative future outcomes. Despite the considerable complexity of this problem, we offer a tractable systematic approach. In particular, we frame the problem as one of reinforcement learning and leverage Thompson sampling. We also establish a regret bound that provides graceful guarantees on how performance improves as data is gathered and how this depends on the complexity of the demand model. We illustrate merits of the approach through simulations. |
| Tasks | |
| Published | 2017-08-29 |
| URL | http://arxiv.org/abs/1708.09020v1 |
| http://arxiv.org/pdf/1708.09020v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-price-with-reference-effects |
| Repo | |
| Framework | |
Introducing machine learning for power system operation support
| Title | Introducing machine learning for power system operation support |
| Authors | Benjamin Donnot, Isabelle Guyon, Marc Schoenauer, Patrick Panciatici, Antoine Marot |
| Abstract | We address the problem of assisting human dispatchers in operating power grids in today’s changing context using machine learning, with theaim of increasing security and reducing costs. Power networks are highly regulated systems, which at all times must meet varying demands of electricity with a complex production system, including conventional power plants, less predictable renewable energies (such as wind or solar power), and the possibility of buying/selling electricity on the international market with more and more actors involved at a Europeanscale. This problem is becoming ever more challenging in an aging network infrastructure. One of the primary goals of dispatchers is to protect equipment (e.g. avoid that transmission lines overheat) with few degrees of freedom: we are considering in this paper solely modifications in network topology, i.e. re-configuring the way in which lines, transformers, productions and loads are connected in sub-stations. Using years of historical data collected by the French Transmission Service Operator (TSO) “R'eseau de Transport d’Electricit'e” (RTE), we develop novel machine learning techniques (drawing on “deep learning”) to mimic human decisions to devise “remedial actions” to prevent any line to violate power flow limits (so-called “thermal limits”). The proposed technique is hybrid. It does not rely purely on machine learning: every action will be tested with actual simulators before being proposed to the dispatchers or implemented on the grid. |
| Tasks | |
| Published | 2017-09-27 |
| URL | http://arxiv.org/abs/1709.09527v1 |
| http://arxiv.org/pdf/1709.09527v1.pdf | |
| PWC | https://paperswithcode.com/paper/introducing-machine-learning-for-power-system |
| Repo | |
| Framework | |
Compression for Smooth Shape Analysis
| Title | Compression for Smooth Shape Analysis |
| Authors | V. Estellers, F. R. Schmidt, D. Cremers |
| Abstract | Most 3D shape analysis methods use triangular meshes to discretize both the shape and functions on it as piecewise linear functions. With this representation, shape analysis requires fine meshes to represent smooth shapes and geometric operators like normals, curvatures, or Laplace-Beltrami eigenfunctions at large computational and memory costs. We avoid this bottleneck with a compression technique that represents a smooth shape as subdivision surfaces and exploits the subdivision scheme to parametrize smooth functions on that shape with a few control parameters. This compression does not affect the accuracy of the Laplace-Beltrami operator and its eigenfunctions and allow us to compute shape descriptors and shape matchings at an accuracy comparable to triangular meshes but a fraction of the computational cost. Our framework can also compress surfaces represented by point clouds to do shape analysis of 3D scanning data. |
| Tasks | 3D Shape Analysis |
| Published | 2017-11-29 |
| URL | http://arxiv.org/abs/1711.10824v1 |
| http://arxiv.org/pdf/1711.10824v1.pdf | |
| PWC | https://paperswithcode.com/paper/compression-for-smooth-shape-analysis |
| Repo | |
| Framework | |
Kiefer Wolfowitz Algorithm is Asymptotically Optimal for a Class of Non-Stationary Bandit Problems
| Title | Kiefer Wolfowitz Algorithm is Asymptotically Optimal for a Class of Non-Stationary Bandit Problems |
| Authors | Rahul Singh, Taposh Banerjee |
| Abstract | We consider the problem of designing an allocation rule or an “online learning algorithm” for a class of bandit problems in which the set of control actions available at each time $s$ is a convex, compact subset of $\mathbb{R}^d$. Upon choosing an action $x$ at time $s$, the algorithm obtains a noisy value of the unknown and time-varying function $f_s$ evaluated at $x$. The “regret” of an algorithm is the gap between its expected reward, and the reward earned by a strategy which has the knowledge of the function $f_s$ at each time $s$ and hence chooses the action $x_s$ that maximizes $f_s$. For this non-stationary bandit problem set-up, we consider two variants of the Kiefer Wolfowitz (KW) algorithm i) KW with fixed step-size $\beta$, and ii) KW with sliding window of length $L$. We show that if the number of times that the function $f_s$ varies during time $T$ is $o(T)$, and if the learning rates of the proposed algorithms are chosen “optimally”, then the regret of the proposed algorithms is $o(T)$, and hence the algorithms are asymptotically efficient. |
| Tasks | |
| Published | 2017-02-26 |
| URL | http://arxiv.org/abs/1702.08000v2 |
| http://arxiv.org/pdf/1702.08000v2.pdf | |
| PWC | https://paperswithcode.com/paper/kiefer-wolfowitz-algorithm-is-asymptotically |
| Repo | |
| Framework | |
Bayesian Nonparametric Unmixing of Hyperspectral Images
| Title | Bayesian Nonparametric Unmixing of Hyperspectral Images |
| Authors | Jürgen Hahn, Abdelhak M. Zoubir |
| Abstract | Hyperspectral imaging is an important tool in remote sensing, allowing for accurate analysis of vast areas. Due to a low spatial resolution, a pixel of a hyperspectral image rarely represents a single material, but rather a mixture of different spectra. HSU aims at estimating the pure spectra present in the scene of interest, referred to as endmembers, and their fractions in each pixel, referred to as abundances. Today, many HSU algorithms have been proposed, based either on a geometrical or statistical model. While most methods assume that the number of endmembers present in the scene is known, there is only little work about estimating this number from the observed data. In this work, we propose a Bayesian nonparametric framework that jointly estimates the number of endmembers, the endmembers itself, and their abundances, by making use of the Indian Buffet Process as a prior for the endmembers. Simulation results and experiments on real data demonstrate the effectiveness of the proposed algorithm, yielding results comparable with state-of-the-art methods while being able to reliably infer the number of endmembers. In scenarios with strong noise, where other algorithms provide only poor results, the proposed approach tends to overestimate the number of endmembers slightly. The additional endmembers, however, often simply represent noisy replicas of present endmembers and could easily be merged in a post-processing step. |
| Tasks | |
| Published | 2017-02-26 |
| URL | http://arxiv.org/abs/1702.08007v1 |
| http://arxiv.org/pdf/1702.08007v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-nonparametric-unmixing-of |
| Repo | |
| Framework | |
Convolutional Sparse Coding with Overlapping Group Norms
| Title | Convolutional Sparse Coding with Overlapping Group Norms |
| Authors | Brendt Wohlberg |
| Abstract | The most widely used form of convolutional sparse coding uses an $\ell_1$ regularization term. While this approach has been successful in a variety of applications, a limitation of the $\ell_1$ penalty is that it is homogeneous across the spatial and filter index dimensions of the sparse representation array, so that sparsity cannot be separately controlled across these dimensions. The present paper considers the consequences of replacing the $\ell_1$ penalty with a mixed group norm, motivated by recent theoretical results for convolutional sparse representations. Algorithms are developed for solving the resulting problems, which are quite challenging, and the impact on the performance of the denoising problem is evaluated. The mixed group norms are found to perform very poorly in this application. While their performance is greatly improved by introducing a weighting strategy, such a strategy also improves the performance obtained from the much simpler and computationally cheaper $\ell_1$ norm. |
| Tasks | Denoising |
| Published | 2017-08-29 |
| URL | http://arxiv.org/abs/1708.09038v1 |
| http://arxiv.org/pdf/1708.09038v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-sparse-coding-with-overlapping |
| Repo | |
| Framework | |
Harvesting Multiple Views for Marker-less 3D Human Pose Annotations
| Title | Harvesting Multiple Views for Marker-less 3D Human Pose Annotations |
| Authors | Georgios Pavlakos, Xiaowei Zhou, Konstantinos G. Derpanis, Kostas Daniilidis |
| Abstract | Recent advances with Convolutional Networks (ConvNets) have shifted the bottleneck for many computer vision tasks to annotated data collection. In this paper, we present a geometry-driven approach to automatically collect annotations for human pose prediction tasks. Starting from a generic ConvNet for 2D human pose, and assuming a multi-view setup, we describe an automatic way to collect accurate 3D human pose annotations. We capitalize on constraints offered by the 3D geometry of the camera setup and the 3D structure of the human body to probabilistically combine per view 2D ConvNet predictions into a globally optimal 3D pose. This 3D pose is used as the basis for harvesting annotations. The benefit of the annotations produced automatically with our approach is demonstrated in two challenging settings: (i) fine-tuning a generic ConvNet-based 2D pose predictor to capture the discriminative aspects of a subject’s appearance (i.e.,“personalization”), and (ii) training a ConvNet from scratch for single view 3D human pose prediction without leveraging 3D pose groundtruth. The proposed multi-view pose estimator achieves state-of-the-art results on standard benchmarks, demonstrating the effectiveness of our method in exploiting the available multi-view information. |
| Tasks | 3D Human Pose Estimation, Pose Prediction |
| Published | 2017-04-16 |
| URL | http://arxiv.org/abs/1704.04793v1 |
| http://arxiv.org/pdf/1704.04793v1.pdf | |
| PWC | https://paperswithcode.com/paper/harvesting-multiple-views-for-marker-less-3d |
| Repo | |
| Framework | |
Modelling Protagonist Goals and Desires in First-Person Narrative
| Title | Modelling Protagonist Goals and Desires in First-Person Narrative |
| Authors | Elahe Rahimtoroghi, Jiaqi Wu, Ruimin Wang, Pranav Anand, Marilyn A Walker |
| Abstract | Many genres of natural language text are narratively structured, a testament to our predilection for organizing our experiences as narratives. There is broad consensus that understanding a narrative requires identifying and tracking the goals and desires of the characters and their narrative outcomes. However, to date, there has been limited work on computational models for this problem. We introduce a new dataset, DesireDB, which includes gold-standard labels for identifying statements of desire, textual evidence for desire fulfillment, and annotations for whether the stated desire is fulfilled given the evidence in the narrative context. We report experiments on tracking desire fulfillment using different methods, and show that LSTM Skip-Thought model achieves F-measure of 0.7 on our corpus. |
| Tasks | |
| Published | 2017-08-29 |
| URL | http://arxiv.org/abs/1708.09040v1 |
| http://arxiv.org/pdf/1708.09040v1.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-protagonist-goals-and-desires-in |
| Repo | |
| Framework | |
On the Compressive Power of Deep Rectifier Networks for High Resolution Representation of Class Boundaries
| Title | On the Compressive Power of Deep Rectifier Networks for High Resolution Representation of Class Boundaries |
| Authors | Senjian An, Mohammed Bennamoun, Farid Boussaid |
| Abstract | This paper provides a theoretical justification of the superior classification performance of deep rectifier networks over shallow rectifier networks from the geometrical perspective of piecewise linear (PWL) classifier boundaries. We show that, for a given threshold on the approximation error, the required number of boundary facets to approximate a general smooth boundary grows exponentially with the dimension of the data, and thus the number of boundary facets, referred to as boundary resolution, of a PWL classifier is an important quality measure that can be used to estimate a lower bound on the classification errors. However, learning naively an exponentially large number of boundary facets requires the determination of an exponentially large number of parameters and also requires an exponentially large number of training patterns. To overcome this issue of “curse of dimensionality”, compressive representations of high resolution classifier boundaries are required. To show the superior compressive power of deep rectifier networks over shallow rectifier networks, we prove that the maximum boundary resolution of a single hidden layer rectifier network classifier grows exponentially with the number of units when this number is smaller than the dimension of the patterns. When the number of units is larger than the dimension of the patterns, the growth rate is reduced to a polynomial order. Consequently, the capacity of generating a high resolution boundary will increase if the same large number of units are arranged in multiple layers instead of a single hidden layer. Taking high dimensional spherical boundaries as examples, we show how deep rectifier networks can utilize geometric symmetries to approximate a boundary with the same accuracy but with a significantly fewer number of parameters than single hidden layer nets. |
| Tasks | |
| Published | 2017-08-24 |
| URL | http://arxiv.org/abs/1708.07244v1 |
| http://arxiv.org/pdf/1708.07244v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-compressive-power-of-deep-rectifier |
| Repo | |
| Framework | |
Transfer Learning for Melanoma Detection: Participation in ISIC 2017 Skin Lesion Classification Challenge
| Title | Transfer Learning for Melanoma Detection: Participation in ISIC 2017 Skin Lesion Classification Challenge |
| Authors | Dennis H. Murphree, Che Ngufor |
| Abstract | This manuscript describes our participation in the International Skin Imaging Collaboration’s 2017 Skin Lesion Analysis Towards Melanoma Detection competition. We participated in Part 3: Lesion Classification. The two stated goals of this binary image classification challenge were to distinguish between (a) melanoma and (b) nevus and seborrheic keratosis, followed by distinguishing between (a) seborrheic keratosis and (b) nevus and melanoma. We chose a deep neural network approach with a transfer learning strategy, using a pre-trained Inception V3 network as both a feature extractor to provide input for a multi-layer perceptron as well as fine-tuning an augmented Inception network. This approach yielded validation set AUC’s of 0.84 on the second task and 0.76 on the first task, for an average AUC of 0.80. We joined the competition unfortunately late, and we look forward to improving on these results. |
| Tasks | Image Classification, Skin Lesion Classification, Transfer Learning |
| Published | 2017-03-15 |
| URL | http://arxiv.org/abs/1703.05235v1 |
| http://arxiv.org/pdf/1703.05235v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-for-melanoma-detection |
| Repo | |
| Framework | |
