Paper Group ANR 290
A Parameter-Free Learning Automaton Scheme. Rapid Probabilistic Interest Learning from Domain-Specific Pairwise Image Comparisons. Neural Graph Machines: Learning Neural Networks Using Graphs. Lower Bound On the Computational Complexity of Discounted Markov Decision Problems. Path-Based Attention Neural Model for Fine-Grained Entity Typing. Exploit …
A Parameter-Free Learning Automaton Scheme
| Title | A Parameter-Free Learning Automaton Scheme |
| Authors | Hao Ge |
| Abstract | For a learning automaton, a proper configuration of its learning parameters, which are crucial for the automaton’s performance, is relatively difficult due to the necessity of a manual parameter tuning before real applications. To ensure a stable and reliable performance in stochastic environments, parameter tuning can be a time-consuming and interaction-costing procedure in the field of LA. Especially, it is a fatal limitation for LA-based applications where the interactions with environments are expensive. In this paper, we propose a parameter-free learning automaton scheme to avoid parameter tuning by a Bayesian inference method. In contrast to existing schemes where the parameters should be carefully tuned according to the environment, the performance of this scheme is not sensitive to external environments because a set of parameters can be consistently applied to various environments, which dramatically reduce the difficulty of applying a learning automaton to an unknown stochastic environment. A rigorous proof of $\epsilon$-optimality for the proposed scheme is provided and numeric experiments are carried out on benchmark environments to verify its effectiveness. The results show that, without any parameter tuning cost, the proposed parameter-free learning automaton (PFLA) can achieve a competitive performance compared with other well-tuned schemes and outperform untuned schemes on consistency of performance. |
| Tasks | Bayesian Inference |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10111v1 |
| http://arxiv.org/pdf/1711.10111v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-parameter-free-learning-automaton-scheme |
| Repo | |
| Framework | |
Rapid Probabilistic Interest Learning from Domain-Specific Pairwise Image Comparisons
| Title | Rapid Probabilistic Interest Learning from Domain-Specific Pairwise Image Comparisons |
| Authors | Michael Burke |
| Abstract | A great deal of work aims to discover general purpose models of image interest or memorability for visual search and information retrieval. This paper argues that image interest is often domain and user specific, and that mechanisms for learning about this domain-specific image interest as quickly as possible, while limiting the amount of data-labelling required, are often more useful to end-users. Specifically, this paper is concerned with the small to medium-sized data regime regularly faced by practising data scientists, who are often required to build turnkey models for end-users with domain-specific challenges. This work uses pairwise image comparisons to reduce the labelling burden on these users, and shows that Gaussian process smoothing in image feature space can be used to build probabilistic models of image interest extremely quickly for a wide range of problems, and performs similarly to recent deep learning approaches trained using pairwise ranking losses. The Gaussian process model used in this work interpolates image interest inferred using a Bayesian ranking approach over image features extracted using a pre-trained convolutional neural network. This probabilistic approach produces image interests paired with uncertainties that can be used to identify images for which additional labelling is required and measure inference convergence. Results obtained on five distinct datasets reinforce recent findings that pre-trained convolutional neural networks can be used to extract useful representations applicable across multiple domains, and highlight the fact that domain-specific image interest does not always correlate with concepts like image memorability. |
| Tasks | Information Retrieval |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.05850v2 |
| http://arxiv.org/pdf/1706.05850v2.pdf | |
| PWC | https://paperswithcode.com/paper/user-driven-mobile-robot-storyboarding |
| Repo | |
| Framework | |
Neural Graph Machines: Learning Neural Networks Using Graphs
| Title | Neural Graph Machines: Learning Neural Networks Using Graphs |
| Authors | Thang D. Bui, Sujith Ravi, Vivek Ramavajjala |
| Abstract | Label propagation is a powerful and flexible semi-supervised learning technique on graphs. Neural networks, on the other hand, have proven track records in many supervised learning tasks. In this work, we propose a training framework with a graph-regularised objective, namely “Neural Graph Machines”, that can combine the power of neural networks and label propagation. This work generalises previous literature on graph-augmented training of neural networks, enabling it to be applied to multiple neural architectures (Feed-forward NNs, CNNs and LSTM RNNs) and a wide range of graphs. The new objective allows the neural networks to harness both labeled and unlabeled data by: (a) allowing the network to train using labeled data as in the supervised setting, (b) biasing the network to learn similar hidden representations for neighboring nodes on a graph, in the same vein as label propagation. Such architectures with the proposed objective can be trained efficiently using stochastic gradient descent and scaled to large graphs, with a runtime that is linear in the number of edges. The proposed joint training approach convincingly outperforms many existing methods on a wide range of tasks (multi-label classification on social graphs, news categorization, document classification and semantic intent classification), with multiple forms of graph inputs (including graphs with and without node-level features) and using different types of neural networks. |
| Tasks | Document Classification, Intent Classification, Multi-Label Classification |
| Published | 2017-03-14 |
| URL | http://arxiv.org/abs/1703.04818v1 |
| http://arxiv.org/pdf/1703.04818v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-graph-machines-learning-neural |
| Repo | |
| Framework | |
Lower Bound On the Computational Complexity of Discounted Markov Decision Problems
| Title | Lower Bound On the Computational Complexity of Discounted Markov Decision Problems |
| Authors | Yichen Chen, Mengdi Wang |
| Abstract | We study the computational complexity of the infinite-horizon discounted-reward Markov Decision Problem (MDP) with a finite state space $\mathcal{S}$ and a finite action space $\mathcal{A}$. We show that any randomized algorithm needs a running time at least $\Omega(\mathcal{S}^2\mathcal{A})$ to compute an $\epsilon$-optimal policy with high probability. We consider two variants of the MDP where the input is given in specific data structures, including arrays of cumulative probabilities and binary trees of transition probabilities. For these cases, we show that the complexity lower bound reduces to $\Omega\left( \frac{\mathcal{S} \mathcal{A}}{\epsilon} \right)$. These results reveal a surprising observation that the computational complexity of the MDP depends on the data structure of input. |
| Tasks | |
| Published | 2017-05-20 |
| URL | http://arxiv.org/abs/1705.07312v1 |
| http://arxiv.org/pdf/1705.07312v1.pdf | |
| PWC | https://paperswithcode.com/paper/lower-bound-on-the-computational-complexity |
| Repo | |
| Framework | |
Path-Based Attention Neural Model for Fine-Grained Entity Typing
| Title | Path-Based Attention Neural Model for Fine-Grained Entity Typing |
| Authors | Denghui Zhang, Pengshan Cai, Yantao Jia, Manling Li, Yuanzhuo Wang, Xueqi Cheng |
| Abstract | Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure. Traditional distant supervision based methods employ a structured data source as a weak supervision and do not need hand-labeled data, but they neglect the label noise in the automatically labeled training corpus. Although recent studies use many features to prune wrong data ahead of training, they suffer from error propagation and bring much complexity. In this paper, we propose an end-to-end typing model, called the path-based attention neural model (PAN), to learn a noise- robust performance by leveraging the hierarchical structure of types. Experiments demonstrate its effectiveness. |
| Tasks | Entity Typing |
| Published | 2017-10-29 |
| URL | http://arxiv.org/abs/1710.10585v2 |
| http://arxiv.org/pdf/1710.10585v2.pdf | |
| PWC | https://paperswithcode.com/paper/path-based-attention-neural-model-for-fine |
| Repo | |
| Framework | |
Exploiting Restricted Boltzmann Machines and Deep Belief Networks in Compressed Sensing
| Title | Exploiting Restricted Boltzmann Machines and Deep Belief Networks in Compressed Sensing |
| Authors | Luisa F. Polania, Kenneth E. Barner |
| Abstract | This paper proposes a CS scheme that exploits the representational power of restricted Boltzmann machines and deep learning architectures to model the prior distribution of the sparsity pattern of signals belonging to the same class. The determined probability distribution is then used in a maximum a posteriori (MAP) approach for the reconstruction. The parameters of the prior distribution are learned from training data. The motivation behind this approach is to model the higher-order statistical dependencies between the coefficients of the sparse representation, with the final goal of improving the reconstruction. The performance of the proposed method is validated on the Berkeley Segmentation Dataset and the MNIST Database of handwritten digits. |
| Tasks | |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10500v1 |
| http://arxiv.org/pdf/1705.10500v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-restricted-boltzmann-machines-and |
| Repo | |
| Framework | |
Systèmes du LIA à DEFT’13
| Title | Systèmes du LIA à DEFT’13 |
| Authors | Xavier Bost, Ilaria Brunetti, Luis Adrián Cabrera-Diego, Jean-Valère Cossu, Andréa Linhares, Mohamed Morchid, Juan-Manuel Torres-Moreno, Marc El-Bèze, Richard Dufour |
| Abstract | The 2013 D'efi de Fouille de Textes (DEFT) campaign is interested in two types of language analysis tasks, the document classification and the information extraction in the specialized domain of cuisine recipes. We present the systems that the LIA has used in DEFT 2013. Our systems show interesting results, even though the complexity of the proposed tasks. |
| Tasks | Document Classification |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06478v1 |
| http://arxiv.org/pdf/1702.06478v1.pdf | |
| PWC | https://paperswithcode.com/paper/systemes-du-lia-a-deft13 |
| Repo | |
| Framework | |
Semantic classifier approach to document classification
| Title | Semantic classifier approach to document classification |
| Authors | Piotr Borkowski, Krzysztof Ciesielski, Mieczysław A. Kłopotek |
| Abstract | In this paper we propose a new document classification method, bridging discrepancies (so-called semantic gap) between the training set and the application sets of textual data. We demonstrate its superiority over classical text classification approaches, including traditional classifier ensembles. The method consists in combining a document categorization technique with a single classifier or a classifier ensemble (SEMCOM algorithm - Committee with Semantic Categorizer). |
| Tasks | Document Classification, Text Classification |
| Published | 2017-01-16 |
| URL | http://arxiv.org/abs/1701.04292v1 |
| http://arxiv.org/pdf/1701.04292v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-classifier-approach-to-document |
| Repo | |
| Framework | |
Semantic Visual Localization
| Title | Semantic Visual Localization |
| Authors | Johannes L. Schönberger, Marc Pollefeys, Andreas Geiger, Torsten Sattler |
| Abstract | Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, e.g., in the context of life-long localization for augmented reality or autonomous robots. In this paper, we propose a novel approach based on a joint 3D geometric and semantic understanding of the world, enabling it to succeed under conditions where previous approaches failed. Our method leverages a novel generative model for descriptor learning, trained on semantic scene completion as an auxiliary task. The resulting 3D descriptors are robust to missing observations by encoding high-level 3D geometric and semantic information. Experiments on several challenging large-scale localization datasets demonstrate reliable localization under extreme viewpoint, illumination, and geometry changes. |
| Tasks | Visual Localization |
| Published | 2017-12-15 |
| URL | http://arxiv.org/abs/1712.05773v2 |
| http://arxiv.org/pdf/1712.05773v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-visual-localization |
| Repo | |
| Framework | |
Deep learning with spatiotemporal consistency for nerve segmentation in ultrasound images
| Title | Deep learning with spatiotemporal consistency for nerve segmentation in ultrasound images |
| Authors | Adel Hafiane, Pierre Vieyres, Alain Delbos |
| Abstract | Ultrasound-Guided Regional Anesthesia (UGRA) has been gaining importance in the last few years, offering numerous advantages over alternative methods of nerve localization (neurostimulation or paraesthesia). However, nerve detection is one of the most tasks that anaesthetists can encounter in the UGRA procedure. Computer aided system that can detect automatically region of nerve, would help practitioner to concentrate more in anaesthetic delivery. In this paper we propose a new method based on deep learning combined with spatiotemporal information to robustly segment the nerve region. The proposed method is based on two phases, localisation and segmentation. The first phase, consists in using convolutional neural network combined with spatial and temporal consistency to detect the nerve zone. The second phase utilises active contour model to delineate the region of interest. Obtained results show the validity of the proposed approach and its robustness. |
| Tasks | |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.05870v1 |
| http://arxiv.org/pdf/1706.05870v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-with-spatiotemporal-consistency |
| Repo | |
| Framework | |
The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously
| Title | The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously |
| Authors | Serkan Cabi, Sergio Gómez Colmenarejo, Matthew W. Hoffman, Misha Denil, Ziyu Wang, Nando de Freitas |
| Abstract | This paper introduces the Intentional Unintentional (IU) agent. This agent endows the deep deterministic policy gradients (DDPG) agent for continuous control with the ability to solve several tasks simultaneously. Learning to solve many tasks simultaneously has been a long-standing, core goal of artificial intelligence, inspired by infant development and motivated by the desire to build flexible robot manipulators capable of many diverse behaviours. We show that the IU agent not only learns to solve many tasks simultaneously but it also learns faster than agents that target a single task at-a-time. In some cases, where the single task DDPG method completely fails, the IU agent successfully solves the task. To demonstrate this, we build a playroom environment using the MuJoCo physics engine, and introduce a grounded formal language to automatically generate tasks. |
| Tasks | Continuous Control |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03300v1 |
| http://arxiv.org/pdf/1707.03300v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-intentional-unintentional-agent-learning |
| Repo | |
| Framework | |
Implications of Decentralized Q-learning Resource Allocation in Wireless Networks
| Title | Implications of Decentralized Q-learning Resource Allocation in Wireless Networks |
| Authors | Francesc Wilhelmi, Boris Bellalta, Cristina Cano, Anders Jonsson |
| Abstract | Reinforcement Learning is gaining attention by the wireless networking community due to its potential to learn good-performing configurations only from the observed results. In this work we propose a stateless variation of Q-learning, which we apply to exploit spatial reuse in a wireless network. In particular, we allow networks to modify both their transmission power and the channel used solely based on the experienced throughput. We concentrate in a completely decentralized scenario in which no information about neighbouring nodes is available to the learners. Our results show that although the algorithm is able to find the best-performing actions to enhance aggregate throughput, there is high variability in the throughput experienced by the individual networks. We identify the cause of this variability as the adversarial setting of our setup, in which the most played actions provide intermittent good/poor performance depending on the neighbouring decisions. We also evaluate the effect of the intrinsic learning parameters of the algorithm on this variability. |
| Tasks | Q-Learning |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10508v2 |
| http://arxiv.org/pdf/1705.10508v2.pdf | |
| PWC | https://paperswithcode.com/paper/implications-of-decentralized-q-learning |
| Repo | |
| Framework | |
Unsupervised Latent Behavior Manifold Learning from Acoustic Features: audio2behavior
| Title | Unsupervised Latent Behavior Manifold Learning from Acoustic Features: audio2behavior |
| Authors | Haoqi Li, Brian Baucom, Panayiotis Georgiou |
| Abstract | Behavioral annotation using signal processing and machine learning is highly dependent on training data and manual annotations of behavioral labels. Previous studies have shown that speech information encodes significant behavioral information and be used in a variety of automated behavior recognition tasks. However, extracting behavior information from speech is still a difficult task due to the sparseness of training data coupled with the complex, high-dimensionality of speech, and the complex and multiple information streams it encodes. In this work we exploit the slow varying properties of human behavior. We hypothesize that nearby segments of speech share the same behavioral context and hence share a similar underlying representation in a latent space. Specifically, we propose a Deep Neural Network (DNN) model to connect behavioral context and derive the behavioral manifold in an unsupervised manner. We evaluate the proposed manifold in the couples therapy domain and also provide examples from publicly available data (e.g. stand-up comedy). We further investigate training within the couples’ therapy domain and from movie data. The results are extremely encouraging and promise improved behavioral quantification in an unsupervised manner and warrants further investigation in a range of applications. |
| Tasks | |
| Published | 2017-01-12 |
| URL | http://arxiv.org/abs/1701.03198v1 |
| http://arxiv.org/pdf/1701.03198v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-latent-behavior-manifold |
| Repo | |
| Framework | |
Attention-based Mixture Density Recurrent Networks for History-based Recommendation
| Title | Attention-based Mixture Density Recurrent Networks for History-based Recommendation |
| Authors | Tian Wang, Kyunghyun Cho |
| Abstract | The goal of personalized history-based recommendation is to automatically output a distribution over all the items given a sequence of previous purchases of a user. In this work, we present a novel approach that uses a recurrent network for summarizing the history of purchases, continuous vectors representing items for scalability, and a novel attention-based recurrent mixture density network, which outputs each component in a mixture sequentially, for modelling a multi-modal conditional distribution. We evaluate the proposed approach on two publicly available datasets, MovieLens-20M and RecSys15. The experiments show that the proposed approach, which explicitly models the multi-modal nature of the predictive distribution, is able to improve the performance over various baselines in terms of precision, recall and nDCG. |
| Tasks | |
| Published | 2017-09-22 |
| URL | http://arxiv.org/abs/1709.07545v1 |
| http://arxiv.org/pdf/1709.07545v1.pdf | |
| PWC | https://paperswithcode.com/paper/attention-based-mixture-density-recurrent |
| Repo | |
| Framework | |
Generating OWA weights using truncated distributions
| Title | Generating OWA weights using truncated distributions |
| Authors | Maxime Lenormand |
| Abstract | Ordered weighted averaging (OWA) operators have been widely used in decision making these past few years. An important issue facing the OWA operators’ users is the determination of the OWA weights. This paper introduces an OWA determination method based on truncated distributions that enables intuitive generation of OWA weights according to a certain level of risk and trade-off. These two dimensions are represented by the two first moments of the truncated distribution. We illustrate our approach with the well-know normal distribution and the definition of a continuous parabolic decision-strategy space. We finally study the impact of the number of criteria on the results. |
| Tasks | Decision Making |
| Published | 2017-09-13 |
| URL | http://arxiv.org/abs/1709.04328v2 |
| http://arxiv.org/pdf/1709.04328v2.pdf | |
| PWC | https://paperswithcode.com/paper/generating-owa-weights-using-truncated |
| Repo | |
| Framework | |
