Paper Group ANR 250
Building robust classifiers through generation of confident out of distribution examples. Estimating Rationally Inattentive Utility Functions with Deep Clustering for Framing - Applications in YouTube Engagement Dynamics. Iterative Potts minimization for the recovery of signals with discontinuities from indirect measurements – the multivariate cas …
Building robust classifiers through generation of confident out of distribution examples
| Title | Building robust classifiers through generation of confident out of distribution examples |
| Authors | Kumar Sricharan, Ashok Srivastava |
| Abstract | Deep learning models are known to be overconfident in their predictions on out of distribution inputs. There have been several pieces of work to address this issue, including a number of approaches for building Bayesian neural networks, as well as closely related work on detection of out of distribution samples. Recently, there has been work on building classifiers that are robust to out of distribution samples by adding a regularization term that maximizes the entropy of the classifier output on out of distribution data. To approximate out of distribution samples (which are not known apriori), a GAN was used for generation of samples at the edges of the training distribution. In this paper, we introduce an alternative GAN based approach for building a robust classifier, where the idea is to use the GAN to explicitly generate out of distribution samples that the classifier is confident on (low entropy), and have the classifier maximize the entropy for these samples. We showcase the effectiveness of our approach relative to state-of-the-art on hand-written characters as well as on a variety of natural image datasets. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://arxiv.org/abs/1812.00239v1 |
| http://arxiv.org/pdf/1812.00239v1.pdf | |
| PWC | https://paperswithcode.com/paper/building-robust-classifiers-through |
| Repo | |
| Framework | |
Estimating Rationally Inattentive Utility Functions with Deep Clustering for Framing - Applications in YouTube Engagement Dynamics
| Title | Estimating Rationally Inattentive Utility Functions with Deep Clustering for Framing - Applications in YouTube Engagement Dynamics |
| Authors | William Hoiles, Vikram Krishnamurthy |
| Abstract | We consider a framework involving behavioral economics and machine learning. Rationally inattentive Bayesian agents make decisions based on their posterior distribution, utility function and information acquisition cost Renyi divergence which generalizes Shannon mutual information). By observing these decisions, how can an observer estimate the utility function and information acquisition cost? Using deep learning, we estimate framing information (essential extrinsic features) that determines the agent’s attention strategy. Then we present a preference based inverse reinforcement learning algorithm to test for rational inattention: is the agent an utility maximizer, attention maximizer, and does an information cost function exist that rationalizes the data? The test imposes a Renyi mutual information constraint which impacts how the agent can select attention strategies to maximize their expected utility. The test provides constructive estimates of the utility function and information acquisition cost of the agent. We illustrate these methods on a massive YouTube dataset for characterizing the commenting behavior of users. |
| Tasks | |
| Published | 2018-12-23 |
| URL | http://arxiv.org/abs/1812.09640v1 |
| http://arxiv.org/pdf/1812.09640v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-rationally-inattentive-utility |
| Repo | |
| Framework | |
Iterative Potts minimization for the recovery of signals with discontinuities from indirect measurements – the multivariate case
| Title | Iterative Potts minimization for the recovery of signals with discontinuities from indirect measurements – the multivariate case |
| Authors | Lukas Kiefer, Martin Storath, Andreas Weinmann |
| Abstract | Signals and images with discontinuities appear in many problems in such diverse areas as biology, medicine, mechanics, and electrical engineering. The concrete data are often discrete, indirect and noisy measurements of some quantities describing the signal under consideration. A frequent task is to find the segments of the signal or image which corresponds to finding the discontinuities or jumps in the data. Methods based on minimizing the piecewise constant Mumford-Shah functional – whose discretized version is known as Potts functional – are advantageous in this scenario, in particular, in connection with segmentation. However, due to their non-convexity, minimization of such functionals is challenging. In this paper we propose a new iterative minimization strategy for the multivariate Potts functional dealing with indirect, noisy measurements. We provide a convergence analysis and underpin our findings with numerical experiments. |
| Tasks | |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.00862v1 |
| http://arxiv.org/pdf/1812.00862v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-potts-minimization-for-the-recovery |
| Repo | |
| Framework | |
Linking Artificial Intelligence Principles
| Title | Linking Artificial Intelligence Principles |
| Authors | Yi Zeng, Enmeng Lu, Cunqing Huangfu |
| Abstract | Artificial Intelligence principles define social and ethical considerations to develop future AI. They come from research institutes, government organizations and industries. All versions of AI principles are with different considerations covering different perspectives and making different emphasis. None of them can be considered as complete and can cover the rest AI principle proposals. Here we introduce LAIP, an effort and platform for linking and analyzing different Artificial Intelligence Principles. We want to explicitly establish the common topics and links among AI Principles proposed by different organizations and investigate on their uniqueness. Based on these efforts, for the long-term future of AI, instead of directly adopting any of the AI principles, we argue for the necessity of incorporating various AI Principles into a comprehensive framework and focusing on how they can interact and complete each other. |
| Tasks | |
| Published | 2018-12-12 |
| URL | http://arxiv.org/abs/1812.04814v1 |
| http://arxiv.org/pdf/1812.04814v1.pdf | |
| PWC | https://paperswithcode.com/paper/linking-artificial-intelligence-principles |
| Repo | |
| Framework | |
Improving width-based planning with compact policies
| Title | Improving width-based planning with compact policies |
| Authors | Miquel Junyent, Anders Jonsson, Vicenç Gómez |
| Abstract | Optimal action selection in decision problems characterized by sparse, delayed rewards is still an open challenge. For these problems, current deep reinforcement learning methods require enormous amounts of data to learn controllers that reach human-level performance. In this work, we propose a method that interleaves planning and learning to address this issue. The planning step hinges on the Iterated-Width (IW) planner, a state of the art planner that makes explicit use of the state representation to perform structured exploration. IW is able to scale up to problems independently of the size of the state space. From the state-actions visited by IW, the learning step estimates a compact policy, which in turn is used to guide the planning step. The type of exploration used by our method is radically different than the standard random exploration used in RL. We evaluate our method in simple problems where we show it to have superior performance than the state-of-the-art reinforcement learning algorithms A2C and Alpha Zero. Finally, we present preliminary results in a subset of the Atari games suite. |
| Tasks | Atari Games |
| Published | 2018-06-15 |
| URL | http://arxiv.org/abs/1806.05898v1 |
| http://arxiv.org/pdf/1806.05898v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-width-based-planning-with-compact |
| Repo | |
| Framework | |
Sparse Over-complete Patch Matching
| Title | Sparse Over-complete Patch Matching |
| Authors | Akila Pemasiri, Kien Nguyen, Sridha Sridharan, Clinton Fookes |
| Abstract | Image patch matching, which is the process of identifying corresponding patches across images, has been used as a subroutine for many computer vision and image processing tasks. State -of-the-art patch matching techniques take image patches as input to a convolutional neural network to extract the patch features and evaluate their similarity. Our aim in this paper is to improve on the state of the art patch matching techniques by observing the fact that a sparse-overcomplete representation of an image posses statistical properties of natural visual scenes which can be exploited for patch matching. We propose a new paradigm which encodes image patch details by encoding the patch and subsequently using this sparse representation as input to a neural network to compare the patches. As sparse coding is based on a generative model of natural image patches, it can represent the patch in terms of the fundamental visual components from which it has been composed of, leading to similar sparse codes for patches which are built from similar components. Once the sparse coded features are extracted, we employ a fully-connected neural network, which captures the non-linear relationships between features, for comparison. We have evaluated our approach using the Liberty and Notredame subsets of the popular UBC patch dataset and set a new benchmark outperforming all state-of-the-art patch matching techniques for these datasets. |
| Tasks | |
| Published | 2018-06-09 |
| URL | http://arxiv.org/abs/1806.03556v2 |
| http://arxiv.org/pdf/1806.03556v2.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-over-complete-patch-matching |
| Repo | |
| Framework | |
Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience
| Title | Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience |
| Authors | Yevgen Chebotar, Ankur Handa, Viktor Makoviychuk, Miles Macklin, Jan Issac, Nathan Ratliff, Dieter Fox |
| Abstract | We consider the problem of transferring policies to the real world by training on a distribution of simulated scenarios. Rather than manually tuning the randomization of simulations, we adapt the simulation parameter distribution using a few real world roll-outs interleaved with policy training. In doing so, we are able to change the distribution of simulations to improve the policy transfer by matching the policy behavior in simulation and the real world. We show that policies trained with our method are able to reliably transfer to different robots in two real world tasks: swing-peg-in-hole and opening a cabinet drawer. The video of our experiments can be found at https://sites.google.com/view/simopt |
| Tasks | |
| Published | 2018-10-12 |
| URL | http://arxiv.org/abs/1810.05687v4 |
| http://arxiv.org/pdf/1810.05687v4.pdf | |
| PWC | https://paperswithcode.com/paper/closing-the-sim-to-real-loop-adapting |
| Repo | |
| Framework | |
Logic Negation with Spiking Neural P Systems
| Title | Logic Negation with Spiking Neural P Systems |
| Authors | Daniel Rodríguez-Chavarría, Miguel A. Gutiérrez-Naranjo, Joaquín Borrego-Díaz |
| Abstract | Nowadays, the success of neural networks as reasoning systems is doubtless. Nonetheless, one of the drawbacks of such reasoning systems is that they work as black-boxes and the acquired knowledge is not human readable. In this paper, we present a new step in order to close the gap between connectionist and logic based reasoning systems. We show that two of the most used inference rules for obtaining negative information in rule based reasoning systems, the so-called Closed World Assumption and Negation as Finite Failure can be characterized by means of spiking neural P systems, a formal model of the third generation of neural networks born in the framework of membrane computing. |
| Tasks | |
| Published | 2018-10-18 |
| URL | https://arxiv.org/abs/1810.08170v2 |
| https://arxiv.org/pdf/1810.08170v2.pdf | |
| PWC | https://paperswithcode.com/paper/logic-negation-with-spiking-neural-p-systems |
| Repo | |
| Framework | |
Global optimization test problems based on random field composition
| Title | Global optimization test problems based on random field composition |
| Authors | Ramses Sala, Niccolò Baldanzini, Marco Pierini |
| Abstract | The development and identification of effective optimization algorithms for non-convex real-world problems is a challenge in global optimization. Because theoretical performance analysis is difficult, and problems based on models of real-world systems are often computationally expensive, several artificial performance test problems and test function generators have been proposed for empirical comparative assessment and analysis of metaheuristic optimization algorithms. These test problems however often lack the complex function structures and forthcoming difficulties that can appear in real-world problems. This communication presents a method to systematically build test problems with various types and degrees of difficulty. By weighted composition of parameterized random fields, challenging test functions with tunable function features such as, variance contribution distribution, interaction order, and nonlinearity can be constructed. The method is described, and its applicability to optimization performance analysis is described by means of a few basic examples. The method aims to set a step forward in the systematic generation of global optimization test problems, which could lead to a better understanding of the performance of optimization algorithms on problem types with particular characteristics. On request an introductive MATLAB implementation of a test function generator based on the presented method is available. |
| Tasks | |
| Published | 2018-07-13 |
| URL | http://arxiv.org/abs/1807.05096v1 |
| http://arxiv.org/pdf/1807.05096v1.pdf | |
| PWC | https://paperswithcode.com/paper/global-optimization-test-problems-based-on |
| Repo | |
| Framework | |
The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces
| Title | The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces |
| Authors | G. Zacharias Holland, Erin J. Talvitie, Michael Bowling |
| Abstract | Dyna is a fundamental approach to model-based reinforcement learning (MBRL) that interleaves planning, acting, and learning in an online setting. In the most typical application of Dyna, the dynamics model is used to generate one-step transitions from selected start states from the agent’s history, which are used to update the agent’s value function or policy as if they were real experiences. In this work, one-step Dyna was applied to several games from the Arcade Learning Environment (ALE). We found that the model-based updates offered surprisingly little benefit over simply performing more updates with the agent’s existing experience, even when using a perfect model. We hypothesize that to get the most from planning, the model must be used to generate unfamiliar experience. To test this, we experimented with the “shape” of planning in multiple different concrete instantiations of Dyna, performing fewer, longer rollouts, rather than many short rollouts. We found that planning shape has a profound impact on the efficacy of Dyna for both perfect and learned models. In addition to these findings regarding Dyna in general, our results represent, to our knowledge, the first time that a learned dynamics model has been successfully used for planning in the ALE, suggesting that Dyna may be a viable approach to MBRL in the ALE and other high-dimensional problems. |
| Tasks | Atari Games |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01825v3 |
| http://arxiv.org/pdf/1806.01825v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-effect-of-planning-shape-on-dyna-style |
| Repo | |
| Framework | |
First Experiments with Neural Translation of Informal to Formal Mathematics
| Title | First Experiments with Neural Translation of Informal to Formal Mathematics |
| Authors | Qingxiang Wang, Cezary Kaliszyk, Josef Urban |
| Abstract | We report on our experiments to train deep neural networks that automatically translate informalized LaTeX-written Mizar texts into the formal Mizar language. To the best of our knowledge, this is the first time when neural networks have been adopted in the formalization of mathematics. Using Luong et al.‘s neural machine translation model (NMT), we tested our aligned informal-formal corpora against various hyperparameters and evaluated their results. Our experiments show that our best performing model configurations are able to generate correct Mizar statements on 65.73% of the inference data, with the union of all models covering 79.17%. These results indicate that formalization through artificial neural network is a promising approach for automated formalization of mathematics. We present several case studies to illustrate our results. |
| Tasks | Machine Translation |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.06502v2 |
| http://arxiv.org/pdf/1805.06502v2.pdf | |
| PWC | https://paperswithcode.com/paper/first-experiments-with-neural-translation-of |
| Repo | |
| Framework | |
Deep Learning on Retina Images as Screening Tool for Diagnostic Decision Support
| Title | Deep Learning on Retina Images as Screening Tool for Diagnostic Decision Support |
| Authors | Maria Camila Alvarez Trivino, Jeremie Despraz, Jesus Alfonso Lopez Sotelo, Carlos Andres Pena |
| Abstract | In this project, we developed a deep learning system applied to human retina images for medical diagnostic decision support. The retina images were provided by EyePACS. These images were used in the framework of a Kaggle contest, whose purpose to identify diabetic retinopathy signs through an automatic detection system. Using as inspiration one of the solutions proposed in the contest, we implemented a model that successfully detects diabetic retinopathy from retina images. After a carefully designed preprocessing, the images were used as input to a deep convolutional neural network (CNN). The CNN performed a feature extraction process followed by a classification stage, which allowed the system to differentiate between healthy and ill patients using five categories. Our model was able to identify diabetic retinopathy in the patients with an agreement rate of 76.73% with respect to the medical expert’s labels for the test data. |
| Tasks | |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09232v1 |
| http://arxiv.org/pdf/1807.09232v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-on-retina-images-as-screening |
| Repo | |
| Framework | |
Efficient Entropy for Policy Gradient with Multidimensional Action Space
| Title | Efficient Entropy for Policy Gradient with Multidimensional Action Space |
| Authors | Yiming Zhang, Quan Ho Vuong, Kenny Song, Xiao-Yue Gong, Keith W. Ross |
| Abstract | In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve high-dimensional discrete action spaces as well as high-dimensional state spaces. This paper considers entropy bonus, which is used to encourage exploration in policy gradient. In the case of high-dimensional action spaces, calculating the entropy and its gradient requires enumerating all the actions in the action space and running forward and backpropagation for each action, which may be computationally infeasible. We develop several novel unbiased estimators for the entropy bonus and its gradient. We apply these estimators to several models for the parameterized policies, including Independent Sampling, CommNet, Autoregressive with Modified MDP, and Autoregressive with LSTM. Finally, we test our algorithms on two environments: a multi-hunter multi-rabbit grid game and a multi-agent multi-arm bandit problem. The results show that our entropy estimators substantially improve performance with marginal additional computational cost. |
| Tasks | Atari Games |
| Published | 2018-06-02 |
| URL | http://arxiv.org/abs/1806.00589v1 |
| http://arxiv.org/pdf/1806.00589v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-entropy-for-policy-gradient-with |
| Repo | |
| Framework | |
Predicting CEFRL levels in learner English on the basis of metrics and full texts
| Title | Predicting CEFRL levels in learner English on the basis of metrics and full texts |
| Authors | Taylor Arnold, Nicolas Ballier, Thomas Gaillat, Paula Lissòn |
| Abstract | This paper analyses the contribution of language metrics and, potentially, of linguistic structures, to classify French learners of English according to levels of the Common European Framework of Reference for Languages (CEFRL). The purpose is to build a model for the prediction of learner levels as a function of language complexity features. We used the EFCAMDAT corpus, a database of one million written assignments by learners. After applying language complexity metrics on the texts, we built a representation matching the language metrics of the texts to their assigned CEFRL levels. Lexical and syntactic metrics were computed with LCA, LSA, and koRpus. Several supervised learning models were built by using Gradient Boosted Trees and Keras Neural Network methods and by contrasting pairs of CEFRL levels. Results show that it is possible to implement pairwise distinctions, especially for levels ranging from A1 to B1 (A1=>A2: 0.916 AUC and A2=>B1: 0.904 AUC). Model explanation reveals significant linguistic features for the predictiveness in the corpus. Word tokens and word types appear to play a significant role in determining levels. This shows that levels are highly dependent on specific semantic profiles. |
| Tasks | |
| Published | 2018-06-28 |
| URL | http://arxiv.org/abs/1806.11099v1 |
| http://arxiv.org/pdf/1806.11099v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-cefrl-levels-in-learner-english-on |
| Repo | |
| Framework | |
AGIL: Learning Attention from Human for Visuomotor Tasks
| Title | AGIL: Learning Attention from Human for Visuomotor Tasks |
| Authors | Ruohan Zhang, Zhuode Liu, Luxin Zhang, Jake A. Whritner, Karl S. Muller, Mary M. Hayhoe, Dana H. Ballard |
| Abstract | When intelligent agents learn visuomotor behaviors from human demonstrations, they may benefit from knowing where the human is allocating visual attention, which can be inferred from their gaze. A wealth of information regarding intelligent decision making is conveyed by human gaze allocation; hence, exploiting such information has the potential to improve the agents’ performance. With this motivation, we propose the AGIL (Attention Guided Imitation Learning) framework. We collect high-quality human action and gaze data while playing Atari games in a carefully controlled experimental setting. Using these data, we first train a deep neural network that can predict human gaze positions and visual attention with high accuracy (the gaze network) and then train another network to predict human actions (the policy network). Incorporating the learned attention model from the gaze network into the policy network significantly improves the action prediction accuracy and task performance. |
| Tasks | Atari Games, Decision Making, Imitation Learning |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.03960v1 |
| http://arxiv.org/pdf/1806.03960v1.pdf | |
| PWC | https://paperswithcode.com/paper/agil-learning-attention-from-human-for |
| Repo | |
| Framework | |
