Paper Group ANR 406
Artificial Intelligence and its Role in Near Future. Studying the Difference Between Natural and Programming Language Corpora. Scalable language model adaptation for spoken dialogue systems. Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice. Clustering Time Series with Nonlinear Dynamics: A Bayesian Non-Parametric …
Artificial Intelligence and its Role in Near Future
Title | Artificial Intelligence and its Role in Near Future |
Authors | Jahanzaib Shabbir, Tarique Anwer |
Abstract | AI technology has a long history which is actively and constantly changing and growing. It focuses on intelligent agents, which contain devices that perceive the environment and based on which takes actions in order to maximize goal success chances. In this paper, we will explain the modern AI basics and various representative applications of AI. In the context of the modern digitalized world, AI is the property of machines, computer programs, and systems to perform the intellectual and creative functions of a person, independently find ways to solve problems, be able to draw conclusions and make decisions. Most artificial intelligence systems have the ability to learn, which allows people to improve their performance over time. The recent research on AI tools, including machine learning, deep learning and predictive analysis intended toward increasing the planning, learning, reasoning, thinking and action taking ability. Based on which, the proposed research intends towards exploring on how the human intelligence differs from the artificial intelligence. Moreover, we critically analyze what AI of today is capable of doing, why it still cannot reach human intelligence and what are the open challenges existing in front of AI to reach and outperform human level of intelligence. Furthermore, it will explore the future predictions for artificial intelligence and based on which potential solution will be recommended to solve it within next decades. |
Tasks | |
Published | 2018-04-01 |
URL | http://arxiv.org/abs/1804.01396v1 |
http://arxiv.org/pdf/1804.01396v1.pdf | |
PWC | https://paperswithcode.com/paper/artificial-intelligence-and-its-role-in-near |
Repo | |
Framework | |
Studying the Difference Between Natural and Programming Language Corpora
Title | Studying the Difference Between Natural and Programming Language Corpora |
Authors | Casey Casalnuovo, Kenji Sagae, Prem Devanbu |
Abstract | Code corpora, as observed in large software systems, are now known to be far more repetitive and predictable than natural language corpora. But why? Does the difference simply arise from the syntactic limitations of programming languages? Or does it arise from the differences in authoring decisions made by the writers of these natural and programming language texts? We conjecture that the differences are not entirely due to syntax, but also from the fact that reading and writing code is un-natural for humans, and requires substantial mental effort; so, people prefer to write code in ways that are familiar to both reader and writer. To support this argument, we present results from two sets of studies: 1) a first set aimed at attenuating the effects of syntax, and 2) a second, aimed at measuring repetitiveness of text written in other settings (e.g. second language, technical/specialized jargon), which are also effortful to write. We find find that this repetition in source code is not entirely the result of grammar constraints, and thus some repetition must result from human choice. While the evidence we find of similar repetitive behavior in technical and learner corpora does not conclusively show that such language is used by humans to mitigate difficulty, it is consistent with that theory. |
Tasks | |
Published | 2018-06-06 |
URL | http://arxiv.org/abs/1806.02437v1 |
http://arxiv.org/pdf/1806.02437v1.pdf | |
PWC | https://paperswithcode.com/paper/studying-the-difference-between-natural-and |
Repo | |
Framework | |
Scalable language model adaptation for spoken dialogue systems
Title | Scalable language model adaptation for spoken dialogue systems |
Authors | Ankur Gandhe, Ariya Rastrow, Bjorn Hoffmeister |
Abstract | Language models (LM) for interactive speech recognition systems are trained on large amounts of data and the model parameters are optimized on past user data. New application intents and interaction types are released for these systems over time, imposing challenges to adapt the LMs since the existing training data is no longer sufficient to model the future user interactions. It is unclear how to adapt LMs to new application intents without degrading the performance on existing applications. In this paper, we propose a solution to (a) estimate n-gram counts directly from the hand-written grammar for training LMs and (b) use constrained optimization to optimize the system parameters for future use cases, while not degrading the performance on past usage. We evaluated our approach on new applications intents for a personal assistant system and find that the adaptation improves the word error rate by up to 15% on new applications even when there is no adaptation data available for an application. |
Tasks | Language Modelling, Speech Recognition, Spoken Dialogue Systems |
Published | 2018-12-11 |
URL | http://arxiv.org/abs/1812.04647v1 |
http://arxiv.org/pdf/1812.04647v1.pdf | |
PWC | https://paperswithcode.com/paper/scalable-language-model-adaptation-for-spoken |
Repo | |
Framework | |
Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice
Title | Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice |
Authors | Amir Rasouli, John K. Tsotsos |
Abstract | One of the major challenges that autonomous cars are facing today is driving in urban environments. To make it a reality, autonomous vehicles require the ability to communicate with other road users and understand their intentions. Such interactions are essential between the vehicles and pedestrians as the most vulnerable road users. Understanding pedestrian behavior, however, is not intuitive and depends on various factors such as demographics of the pedestrians, traffic dynamics, environmental conditions, etc. In this paper, we identify these factors by surveying pedestrian behavior studies, both the classical works on pedestrian-driver interaction and the modern ones that involve autonomous vehicles. To this end, we will discuss various methods of studying pedestrian behavior, and analyze how the factors identified in the literature are interrelated. We will also review the practical applications aimed at solving the interaction problem including design approaches for autonomous vehicles that communicate with pedestrians and visual perception and reasoning algorithms tailored to understanding pedestrian intention. Based on our findings, we will discuss the open problems and propose future research directions. |
Tasks | Autonomous Vehicles |
Published | 2018-05-30 |
URL | http://arxiv.org/abs/1805.11773v1 |
http://arxiv.org/pdf/1805.11773v1.pdf | |
PWC | https://paperswithcode.com/paper/autonomous-vehicles-that-interact-with |
Repo | |
Framework | |
Clustering Time Series with Nonlinear Dynamics: A Bayesian Non-Parametric and Particle-Based Approach
Title | Clustering Time Series with Nonlinear Dynamics: A Bayesian Non-Parametric and Particle-Based Approach |
Authors | Alexander Lin, Yingzhuo Zhang, Jeremy Heng, Stephen A. Allsop, Kay M. Tye, Pierre E. Jacob, Demba Ba |
Abstract | We propose a general statistical framework for clustering multiple time series that exhibit nonlinear dynamics into an a-priori-unknown number of sub-groups. Our motivation comes from neuroscience, where an important problem is to identify, within a large assembly of neurons, subsets that respond similarly to a stimulus or contingency. Upon modeling the multiple time series as the output of a Dirichlet process mixture of nonlinear state-space models, we derive a Metropolis-within-Gibbs algorithm for full Bayesian inference that alternates between sampling cluster assignments and sampling parameter values that form the basis of the clustering. The Metropolis step employs recent innovations in particle-based methods. We apply the framework to clustering time series acquired from the prefrontal cortex of mice in an experiment designed to characterize the neural underpinnings of fear. |
Tasks | Bayesian Inference, Time Series |
Published | 2018-10-23 |
URL | http://arxiv.org/abs/1810.09920v4 |
http://arxiv.org/pdf/1810.09920v4.pdf | |
PWC | https://paperswithcode.com/paper/clustering-time-series-with-nonlinear |
Repo | |
Framework | |
Coevolutionary Neural Population Models
Title | Coevolutionary Neural Population Models |
Authors | Nick Moran, Jordan Pollack |
Abstract | We present a method for using neural networks to model evolutionary population dynamics, and draw parallels to recent deep learning advancements in which adversarially-trained neural networks engage in coevolutionary interactions. We conduct experiments which demonstrate that models from evolutionary game theory are capable of describing the behavior of these neural population systems. |
Tasks | |
Published | 2018-04-11 |
URL | http://arxiv.org/abs/1804.04187v1 |
http://arxiv.org/pdf/1804.04187v1.pdf | |
PWC | https://paperswithcode.com/paper/coevolutionary-neural-population-models |
Repo | |
Framework | |
Approximability of Discriminators Implies Diversity in GANs
Title | Approximability of Discriminators Implies Diversity in GANs |
Authors | Yu Bai, Tengyu Ma, Andrej Risteski |
Abstract | While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. The theoretical work of Arora et al. suggests a dilemma about GANs’ statistical properties: powerful discriminators cause overfitting, whereas weak discriminators cannot detect mode collapse. By contrast, we show in this paper that GANs can in principle learn distributions in Wasserstein distance (or KL-divergence in many cases) with polynomial sample complexity, if the discriminator class has strong distinguishing power against the particular generator class (instead of against all possible generators). For various generator classes such as mixture of Gaussians, exponential families, and invertible and injective neural networks generators, we design corresponding discriminators (which are often neural nets of specific architectures) such that the Integral Probability Metric (IPM) induced by the discriminators can provably approximate the Wasserstein distance and/or KL-divergence. This implies that if the training is successful, then the learned distribution is close to the true distribution in Wasserstein distance or KL divergence, and thus cannot drop modes. Our preliminary experiments show that on synthetic datasets the test IPM is well correlated with KL divergence or the Wasserstein distance, indicating that the lack of diversity in GANs may be caused by the sub-optimality in optimization instead of statistical inefficiency. |
Tasks | |
Published | 2018-06-27 |
URL | https://arxiv.org/abs/1806.10586v4 |
https://arxiv.org/pdf/1806.10586v4.pdf | |
PWC | https://paperswithcode.com/paper/approximability-of-discriminators-implies |
Repo | |
Framework | |
Detecting abnormal events in video using Narrowed Normality Clusters
Title | Detecting abnormal events in video using Narrowed Normality Clusters |
Authors | Radu Tudor Ionescu, Sorina Smeureanu, Marius Popescu, Bogdan Alexe |
Abstract | We formulate the abnormal event detection problem as an outlier detection task and we propose a two-stage algorithm based on k-means clustering and one-class Support Vector Machines (SVM) to eliminate outliers. In the feature extraction stage, we propose to augment spatio-temporal cubes with deep appearance features extracted from the last convolutional layer of a pre-trained neural network. After extracting motion and appearance features from the training video containing only normal events, we apply k-means clustering to find clusters representing different types of normal motion and appearance features. In the first stage, we consider that clusters with fewer samples (with respect to a given threshold) contain mostly outliers, and we eliminate these clusters altogether. In the second stage, we shrink the borders of the remaining clusters by training a one-class SVM model on each cluster. To detected abnormal events in the test video, we analyze each test sample and consider its maximum normality score provided by the trained one-class SVM models, based on the intuition that a test sample can belong to only one cluster of normality. If the test sample does not fit well in any narrowed normality cluster, then it is labeled as abnormal. We compare our method with several state-of-the-art methods on three benchmark data sets. The empirical results indicate that our abnormal event detection framework can achieve better results in most cases, while processing the test video in real-time at 24 frames per second on a single CPU. |
Tasks | Outlier Detection |
Published | 2018-01-12 |
URL | http://arxiv.org/abs/1801.05030v4 |
http://arxiv.org/pdf/1801.05030v4.pdf | |
PWC | https://paperswithcode.com/paper/detecting-abnormal-events-in-video-using |
Repo | |
Framework | |
PeRView: A Framework for Personalized Review Selection Using Micro-Reviews
Title | PeRView: A Framework for Personalized Review Selection Using Micro-Reviews |
Authors | Muhmmad Al-Khiza’ay, Noora Alallaq, Qusay Alanoz, Adil Al-Azzawi, N. Maheswari |
Abstract | In the contemporary era, social media has its influence on people in making decisions. The proliferation of online reviews with diversified and verbose content often causes problems inaccurate decision making. Since online reviews have an impact on people of all walks of life while taking decisions, choosing appropriate reviews based on the podsolization consisting is very important since it relies on using such micro-reviews consistency to evaluate the review set section. Micro-reviews are very concise and directly talk about product or service instead of having unnecessary verbose content. Thus, micro-reviews can help in choosing reviews based on their personalized consistency that is related to directly or indirectly to the main profile of the reviews. Personalized reviews selection that is highly relevant with high personalized coverage in terms of matching with micro-reviews is the main problem that is considered in this paper. Furthermore, personalization with user preferences while making review selection is also considered based on the personalized users’ profile. Towards this end, we proposed a framework known as PeRView for personalized review selection using micro-reviews based on the proposed evaluation metric approach which considering two main factors (personalized matching score and subset size). Personalized Review Selection Algorithm (PRSA) is proposed which makes use of multiple similarity measures merged to have highly efficient personalized reviews matching function for selection. The experimental results based on using reviews dataset which is collected from YELP.COM while micro-reviews dataset is obtained from Foursqure.COM. show that the personalized reviews selection is a very empirical case of study. |
Tasks | Decision Making |
Published | 2018-04-23 |
URL | http://arxiv.org/abs/1804.08234v1 |
http://arxiv.org/pdf/1804.08234v1.pdf | |
PWC | https://paperswithcode.com/paper/perview-a-framework-for-personalized-review |
Repo | |
Framework | |
A predictive processing model of perception and action for self-other distinction
Title | A predictive processing model of perception and action for self-other distinction |
Authors | Sebastian Kahl, Stefan Kopp |
Abstract | During interaction with others, we perceive and produce social actions in close temporal distance or even simultaneously. It has been argued that the motor system is involved in perception and action, playing a fundamental role in the handling of actions produced by oneself and by others. But how does it distinguish in this processing between self and other, thus contributing to self-other distinction? In this paper we propose a hierarchical model of sensorimotor coordination based on principles of perception-action coupling and predictive processing in which self-other distinction arises during action and perception. For this we draw on mechanisms assumed for the integration of cues for a sense of agency, i.e., the sense that an action is self-generated. We report results from simulations of different scenarios, showing that the model is not only able to minimize free energy during perception and action, but also showing that the model can correctly attribute sense of agency to own actions. |
Tasks | |
Published | 2018-10-23 |
URL | http://arxiv.org/abs/1810.09879v2 |
http://arxiv.org/pdf/1810.09879v2.pdf | |
PWC | https://paperswithcode.com/paper/a-predictive-processing-model-of-perception |
Repo | |
Framework | |
Fractional Wavelet Scattering Network and Applications
Title | Fractional Wavelet Scattering Network and Applications |
Authors | Li Liu, Jiasong Wu, Dengwang Li, Lotfi Senhadji, Huazhong Shu |
Abstract | Objective: The present study introduces a fractional wavelet scattering network (FrScatNet), which is a generalized translation invariant version of the classical wavelet scattering network (ScatNet). Methods: In our approach, the FrScatNet is constructed based on the fractional wavelet transform (FRWT). The fractional scattering coefficients are iteratively computed using FRWTs and modulus operators. The feature vectors constructed by fractional scattering coefficients are usually used for signal classification. In this work, an application example of FrScatNet is provided in order to assess its performance on pathological images. Firstly, the FrScatNet extracts feature vectors from patches of the original histological images under different orders. Then we classify those patches into target (benign or malignant) and background groups. And the FrScatNet property is analyzed by comparing error rates computed from different fractional orders respectively. Based on the above pathological image classification, a gland segmentation algorithm is proposed by combining the boundary information and the gland location. Results: The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is significantly improved in fractional scattering domain. We also compare the FrScatNet based gland segmentation method with those proposed in the 2015 MICCAI Gland Segmentation Challenge and our method achieves comparable results. Conclusion: The FrScatNet is shown to achieve accurate and robust results. More stable and discriminative fractional scattering coefficients are obtained by the FrScatNet in this work. Significance: The added fractional order parameter is able to analyze the image in the fractional scattering domain. |
Tasks | Image Classification |
Published | 2018-06-30 |
URL | http://arxiv.org/abs/1807.00141v1 |
http://arxiv.org/pdf/1807.00141v1.pdf | |
PWC | https://paperswithcode.com/paper/fractional-wavelet-scattering-network-and |
Repo | |
Framework | |
Learning Image Representations by Completing Damaged Jigsaw Puzzles
Title | Learning Image Representations by Completing Damaged Jigsaw Puzzles |
Authors | Dahun Kim, Donghyeon Cho, Donggeun Yoo, In So Kweon |
Abstract | In this paper, we explore methods of complicating self-supervised tasks for representation learning. That is, we do severe damage to data and encourage a network to recover them. First, we complicate each of three powerful self-supervised task candidates: jigsaw puzzle, inpainting, and colorization. In addition, we introduce a novel complicated self-supervised task called “Completing damaged jigsaw puzzles” which is puzzles with one piece missing and the other pieces without color. We train a convolutional neural network not only to solve the puzzles, but also generate the missing content and colorize the puzzles. The recovery of the aforementioned damage pushes the network to obtain robust and general-purpose representations. We demonstrate that complicating the self-supervised tasks improves their original versions and that our final task learns more robust and transferable representations compared to the previous methods, as well as the simple combination of our candidate tasks. Our approach achieves state-of-the-art performance in transfer learning on PASCAL classification and semantic segmentation. |
Tasks | Colorization, Representation Learning, Semantic Segmentation, Transfer Learning |
Published | 2018-02-06 |
URL | http://arxiv.org/abs/1802.01880v1 |
http://arxiv.org/pdf/1802.01880v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-image-representations-by-completing |
Repo | |
Framework | |
An LSTM Recurrent Network for Step Counting
Title | An LSTM Recurrent Network for Step Counting |
Authors | Ziyi Chen |
Abstract | Smartphones with sensors such as accelerometer and gyroscope can be used as pedometers and navigators. In this paper, we propose to use an LSTM recurrent network for counting the number of steps taken by both blind and sighted users, based on an annotated smartphone sensor dataset, WeAllWork. The models were trained separately for sighted people, blind people with a long cane or a guide dog for Leave-One-Out training modality. It achieved 5% overcount and undercount rate. |
Tasks | |
Published | 2018-02-10 |
URL | http://arxiv.org/abs/1802.03486v1 |
http://arxiv.org/pdf/1802.03486v1.pdf | |
PWC | https://paperswithcode.com/paper/an-lstm-recurrent-network-for-step-counting |
Repo | |
Framework | |
A large-scale evaluation framework for EEG deep learning architectures
Title | A large-scale evaluation framework for EEG deep learning architectures |
Authors | Felix A. Heilmeyer, Robin T. Schirrmeister, Lukas D. J. Fiederer, Martin Völker, Joos Behncke, Tonio Ball |
Abstract | EEG is the most common signal source for noninvasive BCI applications. For such applications, the EEG signal needs to be decoded and translated into appropriate actions. A recently emerging EEG decoding approach is deep learning with Convolutional or Recurrent Neural Networks (CNNs, RNNs) with many different architectures already published. Here we present a novel framework for the large-scale evaluation of different deep-learning architectures on different EEG datasets. This framework comprises (i) a collection of EEG datasets currently including 100 examples (recording sessions) from six different classification problems, (ii) a collection of different EEG decoding algorithms, and (iii) a wrapper linking the decoders to the data as well as handling structured documentation of all settings and (hyper-) parameters and statistics, designed to ensure transparency and reproducibility. As an applications example we used our framework by comparing three publicly available CNN architectures: the Braindecode Deep4 ConvNet, Braindecode Shallow ConvNet, and two versions of EEGNet. We also show how our framework can be used to study similarities and differences in the performance of different decoding methods across tasks. We argue that the deep learning EEG framework as described here could help to tap the full potential of deep learning for BCI applications. |
Tasks | EEG, Eeg Decoding |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.07741v2 |
http://arxiv.org/pdf/1806.07741v2.pdf | |
PWC | https://paperswithcode.com/paper/a-large-scale-evaluation-framework-for-eeg |
Repo | |
Framework | |
Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems
Title | Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems |
Authors | Richard Tomsett, Dave Braines, Dan Harborne, Alun Preece, Supriyo Chakraborty |
Abstract | Several researchers have argued that a machine learning system’s interpretability should be defined in relation to a specific agent or task: we should not ask if the system is interpretable, but to whom is it interpretable. We describe a model intended to help answer this question, by identifying different roles that agents can fulfill in relation to the machine learning system. We illustrate the use of our model in a variety of scenarios, exploring how an agent’s role influences its goals, and the implications for defining interpretability. Finally, we make suggestions for how our model could be useful to interpretability researchers, system developers, and regulatory bodies auditing machine learning systems. |
Tasks | Interpretable Machine Learning |
Published | 2018-06-20 |
URL | http://arxiv.org/abs/1806.07552v1 |
http://arxiv.org/pdf/1806.07552v1.pdf | |
PWC | https://paperswithcode.com/paper/interpretable-to-whom-a-role-based-model-for |
Repo | |
Framework | |