Paper Group ANR 539
Quantification of Lung Abnormalities in Cystic Fibrosis using Deep Networks. Distributed NLP. Private Text Classification. Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness. Open-endedness in AI systems, cellular evolution and intellectual discussions. A Face-to-Face Neural Conversation Model. Understanding an …
Quantification of Lung Abnormalities in Cystic Fibrosis using Deep Networks
| Title | Quantification of Lung Abnormalities in Cystic Fibrosis using Deep Networks |
| Authors | Filipe Marques, Florian Dubost, Mariette Kemner-van de Corput, Harm A. W. Tiddens, Marleen de Bruijne |
| Abstract | Cystic fibrosis is a genetic disease which may appear in early life with structural abnormalities in lung tissues. We propose to detect these abnormalities using a texture classification approach. Our method is a cascade of two convolutional neural networks. The first network detects the presence of abnormal tissues. The second network identifies the type of the structural abnormalities: bronchiectasis, atelectasis or mucus plugging.We also propose a network computing pixel-wise heatmaps of abnormality presence learning only from the patch-wise annotations. Our database consists of CT scans of 194 subjects. We use 154 subjects to train our algorithms and the 40 remaining ones as a test set. We compare our method with random forest and a single neural network approach. The first network reaches an accuracy of 0,94 for disease detection, 0,18 higher than the random forest classifier and 0,37 higher than the single neural network. Our cascade approach yields a final class-averaged F1-score of 0,33, outperforming the baseline method and the single network by 0,10 and 0,12. |
| Tasks | Texture Classification |
| Published | 2018-03-21 |
| URL | http://arxiv.org/abs/1803.07991v1 |
| http://arxiv.org/pdf/1803.07991v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantification-of-lung-abnormalities-in |
| Repo | |
| Framework | |
Distributed NLP
| Title | Distributed NLP |
| Authors | Galip Aydin, Ibrahim Riza Hallac |
| Abstract | In this paper we present the performance of parallel text processing with Map Reduce on a cloud platform. Scientific papers in Turkish language are processed using Zemberek NLP library. Experiments were run on a Hadoop cluster and compared with the single machines performance. |
| Tasks | |
| Published | 2018-02-10 |
| URL | http://arxiv.org/abs/1802.03606v1 |
| http://arxiv.org/pdf/1802.03606v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-nlp |
| Repo | |
| Framework | |
Private Text Classification
| Title | Private Text Classification |
| Authors | Leif W. Hanlen, Richard Nock, Hanna Suominen, Neil Bacon |
| Abstract | Confidential text corpora exist in many forms, but do not allow arbitrary sharing. We explore how to use such private corpora using privacy preserving text analytics. We construct typical text processing applications using appropriate privacy preservation techniques (including homomorphic encryption, Rademacher operators and secure computation). We set out the preliminary materials from Rademacher operators for binary classifiers, and then construct basic text processing approaches to match those binary classifiers. |
| Tasks | Text Classification |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.06998v1 |
| http://arxiv.org/pdf/1806.06998v1.pdf | |
| PWC | https://paperswithcode.com/paper/private-text-classification |
| Repo | |
| Framework | |
Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness
| Title | Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness |
| Authors | Carlos Eduardo Rosar Kos Lassance, Vincent Gripon, Antonio Ortega |
| Abstract | For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance. As a matter of fact, in sensitive settings misclassification can lead to dramatic consequences. Such misclassifications are likely to occur when facing adversarial attacks, hardware failures or limitations, and imperfect signal acquisition. To address this question, authors have proposed different approaches aiming at increasing the robustness of DNNs, such as adding regularizers or training using noisy examples. In this paper we propose a new regularizer built upon the Laplacian of similarity graphs obtained from the representation of training data at each layer of the DNN architecture. This regularizer penalizes large changes (across consecutive layers in the architecture) in the distance between examples of different classes, and as such enforces smooth variations of the class boundaries. Since it is agnostic to the type of deformations that are expected when predicting with the DNN, the proposed regularizer can be combined with existing ad-hoc methods. We provide theoretical justification for this regularizer and demonstrate its effectiveness to improve robustness of DNNs on classical supervised learning vision datasets. |
| Tasks | |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.10133v2 |
| http://arxiv.org/pdf/1805.10133v2.pdf | |
| PWC | https://paperswithcode.com/paper/laplacian-networks-bounding-indicator |
| Repo | |
| Framework | |
Open-endedness in AI systems, cellular evolution and intellectual discussions
| Title | Open-endedness in AI systems, cellular evolution and intellectual discussions |
| Authors | Kushal Shah |
| Abstract | One of the biggest challenges that artificial intelligence (AI) research is facing in recent times is to develop algorithms and systems that are not only good at performing a specific intelligent task but also good at learning a very diverse of skills somewhat like humans do. In other words, the goal is to be able to mimic biological evolution which has produced all the living species on this planet and which seems to have no end to its creativity. The process of intellectual discussions is also somewhat similar to biological evolution in this regard and is responsible for many of the innovative discoveries and inventions that scientists and engineers have made in the past. In this paper, we present an information theoretic analogy between the process of discussions and the molecular dynamics within a cell, showing that there is a common process of information exchange at the heart of these two seemingly different processes, which can perhaps help us in building AI systems capable of open-ended innovation. We also discuss the role of consciousness in this process and present a framework for the development of open-ended AI systems. |
| Tasks | |
| Published | 2018-12-28 |
| URL | http://arxiv.org/abs/1812.10900v1 |
| http://arxiv.org/pdf/1812.10900v1.pdf | |
| PWC | https://paperswithcode.com/paper/open-endedness-in-ai-systems-cellular |
| Repo | |
| Framework | |
A Face-to-Face Neural Conversation Model
| Title | A Face-to-Face Neural Conversation Model |
| Authors | Hang Chu, Daiqing Li, Sanja Fidler |
| Abstract | Neural networks have recently become good at engaging in dialog. However, current approaches are based solely on verbal text, lacking the richness of a real face-to-face conversation. We propose a neural conversation model that aims to read and generate facial gestures alongside with text. This allows our model to adapt its response based on the “mood” of the conversation. In particular, we introduce an RNN encoder-decoder that exploits the movement of facial muscles, as well as the verbal conversation. The decoder consists of two layers, where the lower layer aims at generating the verbal response and coarse facial expressions, while the second layer fills in the subtle gestures, making the generated output more smooth and natural. We train our neural network by having it “watch” 250 movies. We showcase our joint face-text model in generating more natural conversations through automatic metrics and a human study. We demonstrate an example application with a face-to-face chatting avatar. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01525v1 |
| http://arxiv.org/pdf/1812.01525v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-face-to-face-neural-conversation-model |
| Repo | |
| Framework | |
Understanding and representing the semantics of large structured documents
| Title | Understanding and representing the semantics of large structured documents |
| Authors | Muhammad Mahbubur Rahman, Tim Finin |
| Abstract | Understanding large, structured documents like scholarly articles, requests for proposals or business reports is a complex and difficult task. It involves discovering a document’s overall purpose and subject(s), understanding the function and meaning of its sections and subsections, and extracting low level entities and facts about them. In this research, we present a deep learning based document ontology to capture the general purpose semantic structure and domain specific semantic concepts from a large number of academic articles and business documents. The ontology is able to describe different functional parts of a document, which can be used to enhance semantic indexing for a better understanding by human beings and machines. We evaluate our models through extensive experiments on datasets of scholarly articles from arXiv and Request for Proposal documents. |
| Tasks | |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09842v1 |
| http://arxiv.org/pdf/1807.09842v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-and-representing-the-semantics |
| Repo | |
| Framework | |
Planning, Inference and Pragmatics in Sequential Language Games
| Title | Planning, Inference and Pragmatics in Sequential Language Games |
| Authors | Fereshte Khani, Noah D. Goodman, Percy Liang |
| Abstract | We study sequential language games in which two players, each with private information, communicate to achieve a common goal. In such games, a successful player must (i) infer the partner’s private information from the partner’s messages, (ii) generate messages that are most likely to help with the goal, and (iii) reason pragmatically about the partner’s strategy. We propose a model that captures all three characteristics and demonstrate their importance in capturing human behavior on a new goal-oriented dataset we collected using crowdsourcing. |
| Tasks | |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.11774v1 |
| http://arxiv.org/pdf/1805.11774v1.pdf | |
| PWC | https://paperswithcode.com/paper/planning-inference-and-pragmatics-in |
| Repo | |
| Framework | |
Artificial Intelligence and Robotics
| Title | Artificial Intelligence and Robotics |
| Authors | Javier Andreu Perez, Fani Deligianni, Daniele Ravi, Guang-Zhong Yang |
| Abstract | The recent successes of AI have captured the wildest imagination of both the scientific communities and the general public. Robotics and AI amplify human potentials, increase productivity and are moving from simple reasoning towards human-like cognitive abilities. Current AI technologies are used in a set area of applications, ranging from healthcare, manufacturing, transport, energy, to financial services, banking, advertising, management consulting and government agencies. The global AI market is around 260 billion USD in 2016 and it is estimated to exceed 3 trillion by 2024. To understand the impact of AI, it is important to draw lessons from it’s past successes and failures and this white paper provides a comprehensive explanation of the evolution of AI, its current status and future directions. |
| Tasks | |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10813v1 |
| http://arxiv.org/pdf/1803.10813v1.pdf | |
| PWC | https://paperswithcode.com/paper/artificial-intelligence-and-robotics |
| Repo | |
| Framework | |
Autoencoding topology
| Title | Autoencoding topology |
| Authors | Eric O. Korman |
| Abstract | The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoencoders) to fit deep neural networks. From a machine learning perspective, the resulting structure, an atlas of a manifold, may be viewed as a combination of dimensionality reduction and “fuzzy” clustering. |
| Tasks | Dimensionality Reduction |
| Published | 2018-03-01 |
| URL | http://arxiv.org/abs/1803.00156v1 |
| http://arxiv.org/pdf/1803.00156v1.pdf | |
| PWC | https://paperswithcode.com/paper/autoencoding-topology |
| Repo | |
| Framework | |
Conceptual Domain Adaptation Using Deep Learning
| Title | Conceptual Domain Adaptation Using Deep Learning |
| Authors | Behrang Mehrparvar, Ricardo Vilalta |
| Abstract | Deep learning has recently been shown to be instrumental in the problem of domain adaptation, where the goal is to learn a model on a target domain using a similar –but not identical– source domain. The rationale for coupling both techniques is the possibility of extracting common concepts across domains. Considering (strictly) local representations, traditional deep learning assumes common concepts must be captured in the same hidden units. We contend that jointly training a model with source and target data using a single deep network is prone to failure when there is inherently lower-level representational discrepancy between the two domains; such discrepancy leads to a misalignment of corresponding concepts in separate hidden units. We introduce a search framework to correctly align high-level representations when training deep networks; such framework leads to the notion of conceptual –as opposed to representational– domain adaptation. |
| Tasks | Domain Adaptation |
| Published | 2018-08-16 |
| URL | http://arxiv.org/abs/1808.05355v1 |
| http://arxiv.org/pdf/1808.05355v1.pdf | |
| PWC | https://paperswithcode.com/paper/conceptual-domain-adaptation-using-deep |
| Repo | |
| Framework | |
Identification and Recognition of Rice Diseases and Pests Using Convolutional Neural Networks
| Title | Identification and Recognition of Rice Diseases and Pests Using Convolutional Neural Networks |
| Authors | Chowdhury Rafeed Rahman, Preetom Saha Arko, Mohammed Eunus Ali, Mohammad Ashik Iqbal Khan, Sajid Hasan Apon, Farzana Nowrin, Abu Wasif |
| Abstract | An accurate and timely detection of diseases and pests in rice plants can help farmers in applying timely treatment on the plants and thereby can reduce the economic losses substantially. Recent developments in deep learning based convolutional neural networks (CNN) have greatly improved the image classification accuracy. Being motivated by the success of CNNs in image classification, deep learning based approaches have been developed in this paper for detecting diseases and pests from rice plant images. The contribution of this paper is two fold: (i) State-of-the-art large scale architectures such as VGG16 and InceptionV3 have been adopted and fine tuned for detecting and recognizing rice diseases and pests. Experimental results show the effectiveness of these models with real datasets. (ii) Since large scale architectures are not suitable for mobile devices, a two-stage small CNN architecture has been proposed, and compared with the state-of-the-art memory efficient CNN architectures such as MobileNet, NasNet Mobile and SqueezeNet. Experimental results show that the proposed architecture can achieve the desired accuracy of 93.3% with a significantly reduced model size (e.g., 99% less size compared to that of VGG16). |
| Tasks | Image Classification |
| Published | 2018-12-03 |
| URL | https://arxiv.org/abs/1812.01043v3 |
| https://arxiv.org/pdf/1812.01043v3.pdf | |
| PWC | https://paperswithcode.com/paper/identification-and-recognition-of-rice |
| Repo | |
| Framework | |
A Brandom-ian view of Reinforcement Learning towards strong-AI
| Title | A Brandom-ian view of Reinforcement Learning towards strong-AI |
| Authors | Atrisha Sarkar |
| Abstract | The analytic philosophy of Robert Brandom, based on the ideas of pragmatism, paints a picture of sapience, through inferentialism. In this paper, we present a theory, that utilizes essential elements of Brandom’s philosophy, towards the objective of achieving strong-AI. We do this by connecting the constitutive elements of reinforcement learning and the Game Of Giving and Asking For Reasons. Further, following Brandom’s prescriptive thoughts, we restructure the popular reinforcement learning algorithm A3C, and show that RL algorithms can be tuned towards the objective of strong-AI. |
| Tasks | |
| Published | 2018-03-07 |
| URL | http://arxiv.org/abs/1803.02912v1 |
| http://arxiv.org/pdf/1803.02912v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-brandom-ian-view-of-reinforcement-learning |
| Repo | |
| Framework | |
Theory and Algorithms for Forecasting Time Series
| Title | Theory and Algorithms for Forecasting Time Series |
| Authors | Vitaly Kuznetsov, Mehryar Mohri |
| Abstract | We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes. Our learning guarantees are expressed in terms of a data-dependent measure of sequential complexity and a discrepancy measure that can be estimated from data under some mild assumptions. We also also provide novel analysis of stable time series forecasting algorithm using this new notion of discrepancy that we introduce. We use our learning bounds to devise new algorithms for non-stationary time series forecasting for which we report some preliminary experimental results. |
| Tasks | Time Series, Time Series Forecasting |
| Published | 2018-03-15 |
| URL | http://arxiv.org/abs/1803.05814v1 |
| http://arxiv.org/pdf/1803.05814v1.pdf | |
| PWC | https://paperswithcode.com/paper/theory-and-algorithms-for-forecasting-time |
| Repo | |
| Framework | |
Sales forecasting using WaveNet within the framework of the Kaggle competition
| Title | Sales forecasting using WaveNet within the framework of the Kaggle competition |
| Authors | Glib Kechyn, Lucius Yu, Yangguang Zang, Svyatoslav Kechyn |
| Abstract | We took part in the Corporacion Favorita Grocery Sales Forecasting competition hosted on Kaggle and achieved the 2nd place. In this abstract paper, we present an overall analysis and solution to the underlying machine-learning problem based on time series data, where major challenges are identified and corresponding preliminary methods are proposed. Our approach is based on the adaptation of dilated convolutional neural network for time series forecasting. By applying this technique iteratively to batches of n examples, a big amount of time series data can be eventually processed with a decent speed and accuracy. We hope this paper could serve, to some extent, as a review and guideline of the time series forecasting benchmark, inspiring further attempts and researches. |
| Tasks | Time Series, Time Series Forecasting |
| Published | 2018-03-11 |
| URL | http://arxiv.org/abs/1803.04037v1 |
| http://arxiv.org/pdf/1803.04037v1.pdf | |
| PWC | https://paperswithcode.com/paper/sales-forecasting-using-wavenet-within-the |
| Repo | |
| Framework | |
