Paper Group ANR 553
A Tutorial on Deep Neural Networks for Intelligent Systems. Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data. Weighted Spectral Cluster Ensemble. Double-quantitative $γ^{\ast}-$fuzzy coverings approximation operators. Stuck in a What? Adventures in Weight Space. Towards Evidence-Based Ontology for Supporting Systemat …
A Tutorial on Deep Neural Networks for Intelligent Systems
| Title | A Tutorial on Deep Neural Networks for Intelligent Systems |
| Authors | Juan C. Cuevas-Tello, Manuel Valenzuela-Rendon, Juan A. Nolazco-Flores |
| Abstract | Developing Intelligent Systems involves artificial intelligence approaches including artificial neural networks. Here, we present a tutorial of Deep Neural Networks (DNNs), and some insights about the origin of the term “deep”; references to deep learning are also given. Restricted Boltzmann Machines, which are the core of DNNs, are discussed in detail. An example of a simple two-layer network, performing unsupervised learning for unlabeled data, is shown. Deep Belief Networks (DBNs), which are used to build networks with more than two layers, are also described. Moreover, examples for supervised learning with DNNs performing simple prediction and classification tasks, are presented and explained. This tutorial includes two intelligent pattern recognition applications: hand- written digits (benchmark known as MNIST) and speech recognition. |
| Tasks | Speech Recognition |
| Published | 2016-03-23 |
| URL | http://arxiv.org/abs/1603.07249v1 |
| http://arxiv.org/pdf/1603.07249v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-tutorial-on-deep-neural-networks-for |
| Repo | |
| Framework | |
Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data
| Title | Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data |
| Authors | Shikhar Sharma, Jing He, Kaheer Suleman, Hannes Schulz, Philip Bachman |
| Abstract | Natural language generation plays a critical role in spoken dialogue systems. We present a new approach to natural language generation for task-oriented dialogue using recurrent neural networks in an encoder-decoder framework. In contrast to previous work, our model uses both lexicalized and delexicalized components i.e. slot-value pairs for dialogue acts, with slots and corresponding values aligned together. This allows our model to learn from all available data including the slot-value pairing, rather than being restricted to delexicalized slots. We show that this helps our model generate more natural sentences with better grammar. We further improve our model’s performance by transferring weights learnt from a pretrained sentence auto-encoder. Human evaluation of our best-performing model indicates that it generates sentences which users find more appealing. |
| Tasks | Spoken Dialogue Systems, Text Generation |
| Published | 2016-06-11 |
| URL | http://arxiv.org/abs/1606.03632v3 |
| http://arxiv.org/pdf/1606.03632v3.pdf | |
| PWC | https://paperswithcode.com/paper/natural-language-generation-in-dialogue-using |
| Repo | |
| Framework | |
Weighted Spectral Cluster Ensemble
| Title | Weighted Spectral Cluster Ensemble |
| Authors | Muhammad Yousefnezhad, Daoqiang Zhang |
| Abstract | Clustering explores meaningful patterns in the non-labeled data sets. Cluster Ensemble Selection (CES) is a new approach, which can combine individual clustering results for increasing the performance of the final results. Although CES can achieve better final results in comparison with individual clustering algorithms and cluster ensemble methods, its performance can be dramatically affected by its consensus diversity metric and thresholding procedure. There are two problems in CES: 1) most of the diversity metrics is based on heuristic Shannon’s entropy and 2) estimating threshold values are really hard in practice. The main goal of this paper is proposing a robust approach for solving the above mentioned problems. Accordingly, this paper develops a novel framework for clustering problems, which is called Weighted Spectral Cluster Ensemble (WSCE), by exploiting some concepts from community detection arena and graph based clustering. Under this framework, a new version of spectral clustering, which is called Two Kernels Spectral Clustering, is used for generating graphs based individual clustering results. Further, by using modularity, which is a famous metric in the community detection, on the transformed graph representation of individual clustering results, our approach provides an effective diversity estimation for individual clustering results. Moreover, this paper introduces a new approach for combining the evaluated individual clustering results without the procedure of thresholding. Experimental study on varied data sets demonstrates that the prosed approach achieves superior performance to state-of-the-art methods. |
| Tasks | Community Detection |
| Published | 2016-04-25 |
| URL | http://arxiv.org/abs/1604.07178v1 |
| http://arxiv.org/pdf/1604.07178v1.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-spectral-cluster-ensemble |
| Repo | |
| Framework | |
Double-quantitative $γ^{\ast}-$fuzzy coverings approximation operators
| Title | Double-quantitative $γ^{\ast}-$fuzzy coverings approximation operators |
| Authors | Guangming Lang |
| Abstract | In digital-based information boom, the fuzzy covering rough set model is an important mathematical tool for artificial intelligence, and how to build the bridge between the fuzzy covering rough set theory and Pawlak’s model is becoming a hot research topic. In this paper, we first present the $\gamma-$fuzzy covering based probabilistic and grade approximation operators and double-quantitative approximation operators. We also study the relationships among the three types of $\gamma-$fuzzy covering based approximation operators. Second, we propose the $\gamma^{\ast}-$fuzzy coverings based multi-granulation probabilistic and grade lower and upper approximation operators and multi-granulation double-quantitative lower and upper approximation operators. We also investigate the relationships among these types of $\gamma-$fuzzy coverings based approximation operators. Finally, we employ several examples to illustrate how to construct the lower and upper approximations of fuzzy sets with the absolute and relative quantitative information. |
| Tasks | |
| Published | 2016-11-24 |
| URL | http://arxiv.org/abs/1611.08103v1 |
| http://arxiv.org/pdf/1611.08103v1.pdf | |
| PWC | https://paperswithcode.com/paper/double-quantitative-ast-fuzzy-coverings |
| Repo | |
| Framework | |
Stuck in a What? Adventures in Weight Space
| Title | Stuck in a What? Adventures in Weight Space |
| Authors | Zachary C. Lipton |
| Abstract | Deep learning researchers commonly suggest that converged models are stuck in local minima. More recently, some researchers observed that under reasonable assumptions, the vast majority of critical points are saddle points, not true minima. Both descriptions suggest that weights converge around a point in weight space, be it a local optima or merely a critical point. However, it’s possible that neither interpretation is accurate. As neural networks are typically over-complete, it’s easy to show the existence of vast continuous regions through weight space with equal loss. In this paper, we build on recent work empirically characterizing the error surfaces of neural networks. We analyze training paths through weight space, presenting evidence that apparent convergence of loss does not correspond to weights arriving at critical points, but instead to large movements through flat regions of weight space. While it’s trivial to show that neural network error surfaces are globally non-convex, we show that error surfaces are also locally non-convex, even after breaking symmetry with a random initialization and also after partial training. |
| Tasks | |
| Published | 2016-02-23 |
| URL | http://arxiv.org/abs/1602.07320v1 |
| http://arxiv.org/pdf/1602.07320v1.pdf | |
| PWC | https://paperswithcode.com/paper/stuck-in-a-what-adventures-in-weight-space |
| Repo | |
| Framework | |
Towards Evidence-Based Ontology for Supporting Systematic Literature Review
| Title | Towards Evidence-Based Ontology for Supporting Systematic Literature Review |
| Authors | Yueming Sun, Ye Yang, He Zhang, Wen Zhang, Qing Wang |
| Abstract | [Background]: Systematic Literature Review (SLR) has become an important software engineering research method but costs tremendous efforts. [Aim]: This paper proposes an approach to leverage on empirically evolved ontology to support automating key SLR activities. [Method]: First, we propose an ontology, SLRONT, built on SLR experiences and best practices as a groundwork to capture common terminologies and their relationships during SLR processes; second, we present an extended version of SLRONT, the COSONT and instantiate it with the knowledge and concepts extracted from structured abstracts. Case studies illustrate the details of applying it for supporting SLR steps. [Results]: Results show that through using COSONT, we acquire the same conclusion compared with sheer manual works, but the efforts involved is significantly reduced. [Conclusions]: The approach of using ontology could effectively and efficiently support the conducting of systematic literature review. |
| Tasks | |
| Published | 2016-09-22 |
| URL | http://arxiv.org/abs/1609.08049v1 |
| http://arxiv.org/pdf/1609.08049v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-evidence-based-ontology-for |
| Repo | |
| Framework | |
A stochastically verifiable autonomous control architecture with reasoning
| Title | A stochastically verifiable autonomous control architecture with reasoning |
| Authors | Paolo Izzo, Hongyang Qu, Sandor M. Veres |
| Abstract | A new agent architecture called Limited Instruction Set Agent (LISA) is introduced for autonomous control. The new architecture is based on previous implementations of AgentSpeak and it is structurally simpler than its predecessors with the aim of facilitating design-time and run-time verification methods. The process of abstracting the LISA system to two different types of discrete probabilistic models (DTMC and MDP) is investigated and illustrated. The LISA system provides a tool for complete modelling of the agent and the environment for probabilistic verification. The agent program can be automatically compiled into a DTMC or a MDP model for verification with Prism. The automatically generated Prism model can be used for both design-time and run-time verification. The run-time verification is investigated and illustrated in the LISA system as an internal modelling mechanism for prediction of future outcomes. |
| Tasks | |
| Published | 2016-11-10 |
| URL | http://arxiv.org/abs/1611.03372v1 |
| http://arxiv.org/pdf/1611.03372v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-stochastically-verifiable-autonomous |
| Repo | |
| Framework | |
Relations between assumption-based approaches in nonmonotonic logic and formal argumentation
| Title | Relations between assumption-based approaches in nonmonotonic logic and formal argumentation |
| Authors | Jesse Heyninck, Christian Straßer |
| Abstract | In this paper we make a contribution to the unification of formal models of defeasible reasoning. We present several translations between formal argumentation frameworks and nonmonotonic logics for reasoning with plausible assumptions. More specifically, we translate adaptive logics into assumption-based argumentation and ASPIC+, ASPIC+ into assumption-based argumentation and a fragment of assumption-based argumentation into adaptive logics. Adaptive logics are closely related to Makinson’s default assumptions and to a significant class of systems within the tradition of preferential semantics in the vein of KLM and Shoham. Thus, our results also provide close links between formal argumentation and the latter approaches. |
| Tasks | |
| Published | 2016-04-01 |
| URL | http://arxiv.org/abs/1604.00162v1 |
| http://arxiv.org/pdf/1604.00162v1.pdf | |
| PWC | https://paperswithcode.com/paper/relations-between-assumption-based-approaches |
| Repo | |
| Framework | |
Variable Computation in Recurrent Neural Networks
| Title | Variable Computation in Recurrent Neural Networks |
| Authors | Yacine Jernite, Edouard Grave, Armand Joulin, Tomas Mikolov |
| Abstract | Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the flexibility to capture complex statistics in the data, such as long range dependency or localized attention phenomena. However, while many sequential data (such as video, speech or language) can have highly variable information flow, most recurrent models still consume input features at a constant rate and perform a constant number of computations per time step, which can be detrimental to both speed and model capacity. In this paper, we explore a modification to existing recurrent units which allows them to learn to vary the amount of computation they perform at each step, without prior knowledge of the sequence’s time structure. We show experimentally that not only do our models require fewer operations, they also lead to better performance overall on evaluation tasks. |
| Tasks | |
| Published | 2016-11-18 |
| URL | http://arxiv.org/abs/1611.06188v2 |
| http://arxiv.org/pdf/1611.06188v2.pdf | |
| PWC | https://paperswithcode.com/paper/variable-computation-in-recurrent-neural |
| Repo | |
| Framework | |
Making a Case for Learning Motion Representations with Phase
| Title | Making a Case for Learning Motion Representations with Phase |
| Authors | S. L. Pintea, J. C. van Gemert |
| Abstract | This work advocates Eulerian motion representation learning over the current standard Lagrangian optical flow model. Eulerian motion is well captured by using phase, as obtained by decomposing the image through a complex-steerable pyramid. We discuss the gain of Eulerian motion in a set of practical use cases: (i) action recognition, (ii) motion prediction in static images, (iii) motion transfer in static images and, (iv) motion transfer in video. For each task we motivate the phase-based direction and provide a possible approach. |
| Tasks | motion prediction, Optical Flow Estimation, Representation Learning, Temporal Action Localization |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01693v2 |
| http://arxiv.org/pdf/1609.01693v2.pdf | |
| PWC | https://paperswithcode.com/paper/making-a-case-for-learning-motion |
| Repo | |
| Framework | |
Knowledge Transfer for Scene-specific Motion Prediction
| Title | Knowledge Transfer for Scene-specific Motion Prediction |
| Authors | Lamberto Ballan, Francesco Castaldo, Alexandre Alahi, Francesco Palmieri, Silvio Savarese |
| Abstract | When given a single frame of the video, humans can not only interpret the content of the scene, but also they are able to forecast the near future. This ability is mostly driven by their rich prior knowledge about the visual world, both in terms of (i) the dynamics of moving agents, as well as (ii) the semantic of the scene. In this work we exploit the interplay between these two key elements to predict scene-specific motion patterns. First, we extract patch descriptors encoding the probability of moving to the adjacent patches, and the probability of being in that particular patch or changing behavior. Then, we introduce a Dynamic Bayesian Network which exploits this scene specific knowledge for trajectory prediction. Experimental results demonstrate that our method is able to accurately predict trajectories and transfer predictions to a novel scene characterized by similar elements. |
| Tasks | motion prediction, Trajectory Prediction, Transfer Learning |
| Published | 2016-03-22 |
| URL | http://arxiv.org/abs/1603.06987v2 |
| http://arxiv.org/pdf/1603.06987v2.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-transfer-for-scene-specific-motion |
| Repo | |
| Framework | |
Phoenix: A Self-Optimizing Chess Engine
| Title | Phoenix: A Self-Optimizing Chess Engine |
| Authors | Rahul Aralikatte, G Srinivasaraghavan |
| Abstract | Since the advent of computers, many tasks which required humans to spend a lot of time and energy have been trivialized by the computers’ ability to perform repetitive tasks extremely quickly. Playing chess is one such task. It was one of the first games which was `solved’ using AI. With the advent of deep learning, chess playing agents can surpass human ability with relative ease. However algorithms using deep learning must learn millions of parameters. This work looks at the game of chess through the lens of genetic algorithms. We train a genetic player from scratch using only a handful of learnable parameters. We use Multi-Niche Crowding to optimize positional Value Tables (PVTs) which are used extensively in chess engines to evaluate the goodness of a position. With a very simple setup and after only 1000 generations of evolution, the player reaches the level of an International Master. | |
| Tasks | Game of Chess |
| Published | 2016-03-30 |
| URL | http://arxiv.org/abs/1603.09051v4 |
| http://arxiv.org/pdf/1603.09051v4.pdf | |
| PWC | https://paperswithcode.com/paper/phoenix-a-self-optimizing-chess-engine |
| Repo | |
| Framework | |
Semi-supervised Graph Embedding Approach to Dynamic Link Prediction
| Title | Semi-supervised Graph Embedding Approach to Dynamic Link Prediction |
| Authors | Ryohei Hisano |
| Abstract | We propose a simple discrete time semi-supervised graph embedding approach to link prediction in dynamic networks. The learned embedding reflects information from both the temporal and cross-sectional network structures, which is performed by defining the loss function as a weighted sum of the supervised loss from past dynamics and the unsupervised loss of predicting the neighborhood context in the current network. Our model is also capable of learning different embeddings for both formation and dissolution dynamics. These key aspects contributes to the predictive performance of our model and we provide experiments with three real–world dynamic networks showing that our method is comparable to state of the art methods in link formation prediction and outperforms state of the art baseline methods in link dissolution prediction. |
| Tasks | Dynamic Link Prediction, Graph Embedding, Link Prediction |
| Published | 2016-10-14 |
| URL | http://arxiv.org/abs/1610.04351v1 |
| http://arxiv.org/pdf/1610.04351v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-graph-embedding-approach-to |
| Repo | |
| Framework | |
Hand Gesture Recognition for Contactless Device Control in Operating Rooms
| Title | Hand Gesture Recognition for Contactless Device Control in Operating Rooms |
| Authors | Ebrahim Nasr-Esfahani, Nader Karimi, S. M. Reza Soroushmehr, M. Hossein Jafari, M. Amin Khorsandi, Shadrokh Samavi, Kayvan Najarian |
| Abstract | Hand gesture is one of the most important means of touchless communication between human and machines. There is a great interest for commanding electronic equipment in surgery rooms by hand gesture for reducing the time of surgery and the potential for infection. There are challenges in implementation of a hand gesture recognition system. It has to fulfill requirements such as high accuracy and fast response. In this paper we introduce a system of hand gesture recognition based on a deep learning approach. Deep learning is known as an accurate detection model, but its high complexity prevents it from being fabricated as an embedded system. To cope with this problem, we applied some changes in the structure of our work to achieve low complexity. As a result, the proposed method could be implemented on a naive embedded system. Our experiments show that the proposed system results in higher accuracy while having less complexity in comparison with the existing comparable methods. |
| Tasks | Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition |
| Published | 2016-11-13 |
| URL | http://arxiv.org/abs/1611.04138v1 |
| http://arxiv.org/pdf/1611.04138v1.pdf | |
| PWC | https://paperswithcode.com/paper/hand-gesture-recognition-for-contactless |
| Repo | |
| Framework | |
Argumentation Mining in User-Generated Web Discourse
| Title | Argumentation Mining in User-Generated Web Discourse |
| Authors | Ivan Habernal, Iryna Gurevych |
| Abstract | The goal of argumentation mining, an evolving research field in computational linguistics, is to design methods capable of analyzing people’s argumentation. In this article, we go beyond the state of the art in several ways. (i) We deal with actual Web data and take up the challenges given by the variety of registers, multiple domains, and unrestricted noisy user-generated Web discourse. (ii) We bridge the gap between normative argumentation theories and argumentation phenomena encountered in actual data by adapting an argumentation model tested in an extensive annotation study. (iii) We create a new gold standard corpus (90k tokens in 340 documents) and experiment with several machine learning methods to identify argument components. We offer the data, source codes, and annotation guidelines to the community under free licenses. Our findings show that argumentation mining in user-generated Web discourse is a feasible but challenging task. |
| Tasks | |
| Published | 2016-01-11 |
| URL | http://arxiv.org/abs/1601.02403v5 |
| http://arxiv.org/pdf/1601.02403v5.pdf | |
| PWC | https://paperswithcode.com/paper/argumentation-mining-in-user-generated-web |
| Repo | |
| Framework | |
