Paper Group ANR 518
Constrained Cohort Intelligence using Static and Dynamic Penalty Function Approach for Mechanical Components Design. A probabilistic model for the numerical solution of initial value problems. Multichannel Variable-Size Convolution for Sentence Classification. Graphical RNN Models. Hyperspectral Unmixing with Endmember Variability using Partial Mem …
Constrained Cohort Intelligence using Static and Dynamic Penalty Function Approach for Mechanical Components Design
| Title | Constrained Cohort Intelligence using Static and Dynamic Penalty Function Approach for Mechanical Components Design |
| Authors | Omkar Kulkarni, Ninad Kulkarni, Anand J Kulkarni, Ganesh Kakandikar |
| Abstract | Most of the metaheuristics can efficiently solve unconstrained problems; however, their performance may degenerate if the constraints are involved. This paper proposes two constraint handling approaches for an emerging metaheuristic of Cohort Intelligence (CI). More specifically CI with static penalty function approach (SCI) and CI with dynamic penalty function approach (DCI) are proposed. The approaches have been tested by solving several constrained test problems. The performance of the SCI and DCI have been compared with algorithms like GA, PSO, ABC, d-Ds. In addition, as well as three real world problems from mechanical engineering domain with improved solutions. The results were satisfactory and validated the applicability of CI methodology for solving real world problems. |
| Tasks | |
| Published | 2016-09-26 |
| URL | http://arxiv.org/abs/1610.06009v1 |
| http://arxiv.org/pdf/1610.06009v1.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-cohort-intelligence-using-static |
| Repo | |
| Framework | |
A probabilistic model for the numerical solution of initial value problems
| Title | A probabilistic model for the numerical solution of initial value problems |
| Authors | Michael Schober, Simo Särkkä, Philipp Hennig |
| Abstract | Like many numerical methods, solvers for initial value problems (IVPs) on ordinary differential equations estimate an analytically intractable quantity, using the results of tractable computations as inputs. This structure is closely connected to the notion of inference on latent variables in statistics. We describe a class of algorithms that formulate the solution to an IVP as inference on a latent path that is a draw from a Gaussian process probability measure (or equivalently, the solution of a linear stochastic differential equation). We then show that certain members of this class are connected precisely to generalized linear methods for ODEs, a number of Runge–Kutta methods, and Nordsieck methods. This probabilistic formulation of classic methods is valuable in two ways: analytically, it highlights implicit prior assumptions favoring certain approximate solutions to the IVP over others, and gives a precise meaning to the old observation that these methods act like filters. Practically, it endows the classic solvers with `docking points’ for notions of uncertainty and prior information about the initial value, the value of the ODE itself, and the solution of the problem. | |
| Tasks | |
| Published | 2016-10-17 |
| URL | http://arxiv.org/abs/1610.05261v3 |
| http://arxiv.org/pdf/1610.05261v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-probabilistic-model-for-the-numerical |
| Repo | |
| Framework | |
Multichannel Variable-Size Convolution for Sentence Classification
| Title | Multichannel Variable-Size Convolution for Sentence Classification |
| Authors | Wenpeng Yin, Hinrich Schütze |
| Abstract | We propose MVCNN, a convolution neural network (CNN) architecture for sentence classification. It (i) combines diverse versions of pretrained word embeddings and (ii) extracts features of multigranular phrases with variable-size convolution filters. We also show that pretraining MVCNN is critical for good performance. MVCNN achieves state-of-the-art performance on four tasks: on small-scale binary, small-scale multi-class and largescale Twitter sentiment prediction and on subjectivity classification. |
| Tasks | Sentence Classification, Word Embeddings |
| Published | 2016-03-15 |
| URL | http://arxiv.org/abs/1603.04513v1 |
| http://arxiv.org/pdf/1603.04513v1.pdf | |
| PWC | https://paperswithcode.com/paper/multichannel-variable-size-convolution-for |
| Repo | |
| Framework | |
Graphical RNN Models
| Title | Graphical RNN Models |
| Authors | Ashish Bora, Sugato Basu, Joydeep Ghosh |
| Abstract | Many time series are generated by a set of entities that interact with one another over time. This paper introduces a broad, flexible framework to learn from multiple inter-dependent time series generated by such entities. Our framework explicitly models the entities and their interactions through time. It achieves this by building on the capabilities of Recurrent Neural Networks, while also offering several ways to incorporate domain knowledge/constraints into the model architecture. The capabilities of our approach are showcased through an application to weather prediction, which shows gains over strong baselines. |
| Tasks | Time Series |
| Published | 2016-12-15 |
| URL | http://arxiv.org/abs/1612.05054v1 |
| http://arxiv.org/pdf/1612.05054v1.pdf | |
| PWC | https://paperswithcode.com/paper/graphical-rnn-models |
| Repo | |
| Framework | |
Hyperspectral Unmixing with Endmember Variability using Partial Membership Latent Dirichlet Allocation
| Title | Hyperspectral Unmixing with Endmember Variability using Partial Membership Latent Dirichlet Allocation |
| Authors | Sheng Zou, Alina Zare |
| Abstract | The application of Partial Membership Latent Dirichlet Allocation(PM-LDA) for hyperspectral endmember estimation and spectral unmixing is presented. PM-LDA provides a model for a hyperspectral image analysis that accounts for spectral variability and incorporates spatial information through the use of superpixel-based ‘documents.’ In our application of PM-LDA, we employ the Normal Compositional Model in which endmembers are represented as Normal distributions to account for spectral variability and proportion vectors are modeled as random variables governed by a Dirichlet distribution. The use of the Dirichlet distribution enforces positivity and sum-to-one constraints on the proportion values. Algorithm results on real hyperspectral data indicate that PM-LDA produces endmember distributions that represent the ground truth classes and their associated variability. |
| Tasks | Hyperspectral Unmixing |
| Published | 2016-09-12 |
| URL | http://arxiv.org/abs/1609.03500v1 |
| http://arxiv.org/pdf/1609.03500v1.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-unmixing-with-endmember-1 |
| Repo | |
| Framework | |
A Real-Time Deep Learning Pedestrian Detector for Robot Navigation
| Title | A Real-Time Deep Learning Pedestrian Detector for Robot Navigation |
| Authors | David Ribeiro, Andre Mateus, Pedro Miraldo, Jacinto C. Nascimento |
| Abstract | A real-time Deep Learning based method for Pedestrian Detection (PD) is applied to the Human-Aware robot navigation problem. The pedestrian detector combines the Aggregate Channel Features (ACF) detector with a deep Convolutional Neural Network (CNN) in order to obtain fast and accurate performance. Our solution is firstly evaluated using a set of real images taken from onboard and offboard cameras and, then, it is validated in a typical robot navigation environment with pedestrians (two distinct experiments are conducted). The results on both tests show that our pedestrian detector is robust and fast enough to be used on robot navigation applications. |
| Tasks | Pedestrian Detection, Robot Navigation |
| Published | 2016-07-15 |
| URL | http://arxiv.org/abs/1607.04436v2 |
| http://arxiv.org/pdf/1607.04436v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-real-time-deep-learning-pedestrian-detector |
| Repo | |
| Framework | |
Model Selection for Gaussian Process Regression by Approximation Set Coding
| Title | Model Selection for Gaussian Process Regression by Approximation Set Coding |
| Authors | Benjamin Fischer, Nico Gorbach, Stefan Bauer, Yatao Bian, Joachim M. Buhmann |
| Abstract | Gaussian processes are powerful, yet analytically tractable models for supervised learning. A Gaussian process is characterized by a mean function and a covariance function (kernel), which are determined by a model selection criterion. The functions to be compared do not just differ in their parametrization but in their fundamental structure. It is often not clear which function structure to choose, for instance to decide between a squared exponential and a rational quadratic kernel. Based on the principle of approximation set coding, we develop a framework for model selection to rank kernels for Gaussian process regression. In our experiments approximation set coding shows promise to become a model selection criterion competitive with maximum evidence (also called marginal likelihood) and leave-one-out cross-validation. |
| Tasks | Gaussian Processes, Model Selection |
| Published | 2016-10-04 |
| URL | http://arxiv.org/abs/1610.00907v1 |
| http://arxiv.org/pdf/1610.00907v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-selection-for-gaussian-process |
| Repo | |
| Framework | |
Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policies
| Title | Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policies |
| Authors | Daniel Hein, Alexander Hentschel, Thomas Runkler, Steffen Udluft |
| Abstract | Fuzzy controllers are efficient and interpretable system controllers for continuous state and action spaces. To date, such controllers have been constructed manually or trained automatically either using expert-generated problem-specific cost functions or incorporating detailed knowledge about the optimal control strategy. Both requirements for automatic training processes are not found in most real-world reinforcement learning (RL) problems. In such applications, online learning is often prohibited for safety reasons because online learning requires exploration of the problem’s dynamics during policy training. We introduce a fuzzy particle swarm reinforcement learning (FPSRL) approach that can construct fuzzy RL policies solely by training parameters on world models that simulate real system dynamics. These world models are created by employing an autonomous machine learning technique that uses previously generated transition samples of a real system. To the best of our knowledge, this approach is the first to relate self-organizing fuzzy controllers to model-based batch RL. Therefore, FPSRL is intended to solve problems in domains where online learning is prohibited, system dynamics are relatively easy to model from previously generated default policy transition samples, and it is expected that a relatively easily interpretable control policy exists. The efficiency of the proposed approach with problems from such domains is demonstrated using three standard RL benchmarks, i.e., mountain car, cart-pole balancing, and cart-pole swing-up. Our experimental results demonstrate high-performing, interpretable fuzzy policies. |
| Tasks | |
| Published | 2016-10-19 |
| URL | http://arxiv.org/abs/1610.05984v5 |
| http://arxiv.org/pdf/1610.05984v5.pdf | |
| PWC | https://paperswithcode.com/paper/particle-swarm-optimization-for-generating |
| Repo | |
| Framework | |
Comparative study and enhancement of Camera Tampering Detection algorithms
| Title | Comparative study and enhancement of Camera Tampering Detection algorithms |
| Authors | Mabrouka Hagui, Mohamed Ali Mahjoub, Ahmed Boukhris |
| Abstract | Recently the use of video surveillance systems is widely increasing. Different places are equipped by camera surveillances such as hospitals, schools, airports, museums and military places in order to ensure the safety and security of the persons and their property. Therefore it becomes significant to guarantee the proper working of these systems. Intelligent video surveillance systems equipped by sophisticated digital camera can analyze video information s and automatically detect doubtful actions. The camera tampering detection algorithms may indicate that accidental or suspicious activities have occurred and that causes the abnormality works of the video surveillance. Camera Tampering Detection uses several techniques based on image processing and computer vision. In this paper, comparative study of performance of three algorithms that can detect abnormal disturbance for video surveillance is presented. |
| Tasks | |
| Published | 2016-08-08 |
| URL | http://arxiv.org/abs/1608.02385v1 |
| http://arxiv.org/pdf/1608.02385v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-study-and-enhancement-of-camera |
| Repo | |
| Framework | |
Learning with Value-Ramp
| Title | Learning with Value-Ramp |
| Authors | Tom J. Ameloot, Jan Van den Bussche |
| Abstract | We study a learning principle based on the intuition of forming ramps. The agent tries to follow an increasing sequence of values until the agent meets a peak of reward. The resulting Value-Ramp algorithm is natural, easy to configure, and has a robust implementation with natural numbers. |
| Tasks | |
| Published | 2016-08-12 |
| URL | http://arxiv.org/abs/1608.03647v2 |
| http://arxiv.org/pdf/1608.03647v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-with-value-ramp |
| Repo | |
| Framework | |
Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenes
| Title | Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenes |
| Authors | Gordon Christie, Ankit Laddha, Aishwarya Agrawal, Stanislaw Antol, Yash Goyal, Kevin Kochersberger, Dhruv Batra |
| Abstract | We present an approach to simultaneously perform semantic segmentation and prepositional phrase attachment resolution for captioned images. Some ambiguities in language cannot be resolved without simultaneously reasoning about an associated image. If we consider the sentence “I shot an elephant in my pajamas”, looking at language alone (and not using common sense), it is unclear if it is the person or the elephant wearing the pajamas or both. Our approach produces a diverse set of plausible hypotheses for both semantic segmentation and prepositional phrase attachment resolution that are then jointly reranked to select the most consistent pair. We show that our semantic segmentation and prepositional phrase attachment resolution modules have complementary strengths, and that joint reasoning produces more accurate results than any module operating in isolation. Multiple hypotheses are also shown to be crucial to improved multiple-module reasoning. Our vision and language approach significantly outperforms the Stanford Parser (De Marneffe et al., 2006) by 17.91% (28.69% relative) and 12.83% (25.28% relative) in two different experiments. We also make small improvements over DeepLab-CRF (Chen et al., 2015). |
| Tasks | Common Sense Reasoning, Prepositional Phrase Attachment, Semantic Segmentation |
| Published | 2016-04-07 |
| URL | http://arxiv.org/abs/1604.02125v4 |
| http://arxiv.org/pdf/1604.02125v4.pdf | |
| PWC | https://paperswithcode.com/paper/resolving-language-and-vision-ambiguities |
| Repo | |
| Framework | |
A multinomial probabilistic model for movie genre predictions
| Title | A multinomial probabilistic model for movie genre predictions |
| Authors | Eric Makita, Artem Lenskiy |
| Abstract | This paper proposes a movie genre-prediction based on multinomial probability model. To the best of our knowledge, this problem has not been addressed yet in the field of recommender system. The prediction of a movie genre has many practical applications including complementing the items categories given by experts and providing a surprise effect in the recommendations given to a user. We employ mulitnomial event model to estimate a likelihood of a movie given genre and the Bayes rule to evaluate the posterior probability of a genre given a movie. Experiments with the MovieLens dataset validate our approach. We achieved 70% prediction rate using only 15% of the whole set for training. |
| Tasks | Recommendation Systems |
| Published | 2016-03-25 |
| URL | http://arxiv.org/abs/1603.07849v1 |
| http://arxiv.org/pdf/1603.07849v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-multinomial-probabilistic-model-for-movie |
| Repo | |
| Framework | |
Structured adaptive and random spinners for fast machine learning computations
| Title | Structured adaptive and random spinners for fast machine learning computations |
| Authors | Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Francois Fagan, Cedric Gouy-Pailler, Anne Morvan, Nourhan Sakr, Tamas Sarlos, Jamal Atif |
| Abstract | We consider an efficient computational framework for speeding up several machine learning algorithms with almost no loss of accuracy. The proposed framework relies on projections via structured matrices that we call Structured Spinners, which are formed as products of three structured matrix-blocks that incorporate rotations. The approach is highly generic, i.e. i) structured matrices under consideration can either be fully-randomized or learned, ii) our structured family contains as special cases all previously considered structured schemes, iii) the setting extends to the non-linear case where the projections are followed by non-linear functions, and iv) the method finds numerous applications including kernel approximations via random feature maps, dimensionality reduction algorithms, new fast cross-polytope LSH techniques, deep learning, convex optimization algorithms via Newton sketches, quantization with random projection trees, and more. The proposed framework comes with theoretical guarantees characterizing the capacity of the structured model in reference to its unstructured counterpart and is based on a general theoretical principle that we describe in the paper. As a consequence of our theoretical analysis, we provide the first theoretical guarantees for one of the most efficient existing LSH algorithms based on the HD3HD2HD1 structured matrix [Andoni et al., 2015]. The exhaustive experimental evaluation confirms the accuracy and efficiency of structured spinners for a variety of different applications. |
| Tasks | Dimensionality Reduction, Quantization |
| Published | 2016-10-19 |
| URL | http://arxiv.org/abs/1610.06209v3 |
| http://arxiv.org/pdf/1610.06209v3.pdf | |
| PWC | https://paperswithcode.com/paper/structured-adaptive-and-random-spinners-for |
| Repo | |
| Framework | |
The Curious Robot: Learning Visual Representations via Physical Interactions
| Title | The Curious Robot: Learning Visual Representations via Physical Interactions |
| Authors | Lerrel Pinto, Dhiraj Gandhi, Yuanfeng Han, Yong-Lae Park, Abhinav Gupta |
| Abstract | What is the right supervisory signal to train visual representations? Current approaches in computer vision use category labels from datasets such as ImageNet to train ConvNets. However, in case of biological agents, visual representation learning does not require millions of semantic labels. We argue that biological agents use physical interactions with the world to learn visual representations unlike current vision systems which just use passive observations (images and videos downloaded from web). For example, babies push objects, poke them, put them in their mouth and throw them to learn representations. Towards this goal, we build one of the first systems on a Baxter platform that pushes, pokes, grasps and observes objects in a tabletop environment. It uses four different types of physical interactions to collect more than 130K datapoints, with each datapoint providing supervision to a shared ConvNet architecture allowing us to learn visual representations. We show the quality of learned representations by observing neuron activations and performing nearest neighbor retrieval on this learned representation. Quantitatively, we evaluate our learned ConvNet on image classification tasks and show improvements compared to learning without external data. Finally, on the task of instance retrieval, our network outperforms the ImageNet network on recall@1 by 3% |
| Tasks | Image Classification, Representation Learning |
| Published | 2016-04-05 |
| URL | http://arxiv.org/abs/1604.01360v2 |
| http://arxiv.org/pdf/1604.01360v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-curious-robot-learning-visual |
| Repo | |
| Framework | |
Adobe-MIT submission to the DSTC 4 Spoken Language Understanding pilot task
| Title | Adobe-MIT submission to the DSTC 4 Spoken Language Understanding pilot task |
| Authors | Franck Dernoncourt, Ji Young Lee, Trung H. Bui, Hung H. Bui |
| Abstract | The Dialog State Tracking Challenge 4 (DSTC 4) proposes several pilot tasks. In this paper, we focus on the spoken language understanding pilot task, which consists of tagging a given utterance with speech acts and semantic slots. We compare different classifiers: the best system obtains 0.52 and 0.67 F1-scores on the test set for speech act recognition for the tourist and the guide respectively, and 0.52 F1-score for semantic tagging for both the guide and the tourist. |
| Tasks | Spoken Language Understanding |
| Published | 2016-05-07 |
| URL | http://arxiv.org/abs/1605.02129v1 |
| http://arxiv.org/pdf/1605.02129v1.pdf | |
| PWC | https://paperswithcode.com/paper/adobe-mit-submission-to-the-dstc-4-spoken |
| Repo | |
| Framework | |
