Paper Group ANR 887
Gated-Dilated Networks for Lung Nodule Classification in CT scans. SGAS: Sequential Greedy Architecture Search. TensorNetwork for Machine Learning. Fast End-to-End Wikification. Extending Deep Knowledge Tracing: Inferring Interpretable Knowledge and Predicting Post-System Performance. NNVA: Neural Network Assisted Visual Analysis of Yeast Cell Pola …
Gated-Dilated Networks for Lung Nodule Classification in CT scans
| Title | Gated-Dilated Networks for Lung Nodule Classification in CT scans |
| Authors | Mundher Al-Shabi, Hwee Kuan Lee, Maxine Tan |
| Abstract | Different types of Convolutional Neural Networks (CNNs) have been applied to detect cancerous lung nodules from computed tomography (CT) scans. However, the size of a nodule is very diverse and can range anywhere between 3 and 30 millimeters. The high variation of nodule sizes makes classifying them a difficult and challenging task. In this study, we propose a novel CNN architecture called Gated-Dilated (GD) networks to classify nodules as malignant or benign. Unlike previous studies, the GD network uses multiple dilated convolutions instead of max-poolings to capture the scale variations. Moreover, the GD network has a Context-Aware sub-network that analyzes the input features and guides the features to a suitable dilated convolution. We evaluated the proposed network on more than 1,000 CT scans from the LIDC-LDRI dataset. Our proposed network outperforms state-of-the-art baseline models including Multi-Crop, Resnet, and Densenet, with an AUC of >0.95. Compared to the baseline models, the GD network improves the classification accuracies of mid-range sized nodules. Furthermore, we observe a relationship between the size of the nodule and the attention signal generated by the Context-Aware sub-network, which validates our new network architecture. |
| Tasks | Computed Tomography (CT), Lung Nodule Classification |
| Published | 2019-01-01 |
| URL | https://arxiv.org/abs/1901.00120v2 |
| https://arxiv.org/pdf/1901.00120v2.pdf | |
| PWC | https://paperswithcode.com/paper/gated-dilated-networks-for-lung-nodule |
| Repo | |
| Framework | |
SGAS: Sequential Greedy Architecture Search
| Title | SGAS: Sequential Greedy Architecture Search |
| Authors | Guohao Li, Guocheng Qian, Itzel C. Delgadillo, Matthias Müller, Ali Thabet, Bernard Ghanem |
| Abstract | Architecture design has become a crucial component of successful deep learning. Recent progress in automatic neural architecture search (NAS) shows a lot of promise. However, discovered architectures often fail to generalize in the final evaluation. Architectures with a higher validation accuracy during the search phase may perform worse in the evaluation. Aiming to alleviate this common issue, we introduce sequential greedy architecture search (SGAS), an efficient method for neural architecture search. By dividing the search procedure into sub-problems, SGAS chooses and prunes candidate operations in a greedy fashion. We apply SGAS to search architectures for Convolutional Neural Networks (CNN) and Graph Convolutional Networks (GCN). Extensive experiments show that SGAS is able to find state-of-the-art architectures for tasks such as image classification, point cloud classification and node classification in protein-protein interaction graphs with minimal computational cost. Please visit https://sites.google.com/kaust.edu.sa/sgas for more information about SGAS. |
| Tasks | Image Classification, Neural Architecture Search, Node Classification |
| Published | 2019-11-30 |
| URL | https://arxiv.org/abs/1912.00195v1 |
| https://arxiv.org/pdf/1912.00195v1.pdf | |
| PWC | https://paperswithcode.com/paper/sgas-sequential-greedy-architecture-search |
| Repo | |
| Framework | |
TensorNetwork for Machine Learning
| Title | TensorNetwork for Machine Learning |
| Authors | Stavros Efthymiou, Jack Hidary, Stefan Leichenauer |
| Abstract | We demonstrate the use of tensor networks for image classification with the TensorNetwork open source library. We explain in detail the encoding of image data into a matrix product state form, and describe how to contract the network in a way that is parallelizable and well-suited to automatic gradients for optimization. Applying the technique to the MNIST and Fashion-MNIST datasets we find out-of-the-box performance of 98% and 88% accuracy, respectively, using the same tensor network architecture. The TensorNetwork library allows us to seamlessly move from CPU to GPU hardware, and we see a factor of more than 10 improvement in computational speed using a GPU. |
| Tasks | Image Classification, Tensor Networks |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.06329v1 |
| https://arxiv.org/pdf/1906.06329v1.pdf | |
| PWC | https://paperswithcode.com/paper/tensornetwork-for-machine-learning |
| Repo | |
| Framework | |
Fast End-to-End Wikification
| Title | Fast End-to-End Wikification |
| Authors | Ilya Shnayderman, Liat Ein-Dor, Yosi Mass, Alon Halfon, Benjamin Sznajder, Artem Spector, Yoav Katz, Dafna Sheinwald, Ranit Aharonov, Noam Slonim |
| Abstract | Wikification of large corpora is beneficial for various NLP applications. Existing methods focus on quality performance rather than run-time, and are therefore non-feasible for large data. Here, we introduce RedW, a run-time oriented Wikification solution, based on Wikipedia redirects, that can Wikify massive corpora with competitive performance. We further propose an efficient method for estimating RedW confidence, opening the door for applying more demanding methods only on top of RedW lower-confidence results. Our experimental results support the validity of the proposed approach. |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06785v1 |
| https://arxiv.org/pdf/1908.06785v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-end-to-end-wikification |
| Repo | |
| Framework | |
Extending Deep Knowledge Tracing: Inferring Interpretable Knowledge and Predicting Post-System Performance
| Title | Extending Deep Knowledge Tracing: Inferring Interpretable Knowledge and Predicting Post-System Performance |
| Authors | Richard Scruggs, Ryan S. Baker, Bruce M. McLaren |
| Abstract | Recent student knowledge modeling algorithms such as DKT and DKVMN have been shown to produce accurate predictions of problem correctness within the same learning system. However, these algorithms do not generate estimates of student knowledge. In this paper we present an extension that infers knowledge estimates from correctness predictions. We apply this extension to DKT and DKVMN, resulting in knowledge estimates that correlate better with a posttest than knowledge estimates produced by PFA or BKT. We also apply our extension to correctness predictions from PFA and BKT, finding that knowledge predictions produced with it correlate better with the posttest than BKT and PFA’s own knowledge predictions. These findings are significant since the primary aim of education is to prepare students for later experiences outside of the immediate learning activity. |
| Tasks | Knowledge Tracing |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.12597v1 |
| https://arxiv.org/pdf/1910.12597v1.pdf | |
| PWC | https://paperswithcode.com/paper/extending-deep-knowledge-tracing-inferring |
| Repo | |
| Framework | |
NNVA: Neural Network Assisted Visual Analysis of Yeast Cell Polarization Simulation
| Title | NNVA: Neural Network Assisted Visual Analysis of Yeast Cell Polarization Simulation |
| Authors | Subhashis Hazarika, Haoyu Li, Ko-Chih Wang, Han-Wei Shen, Ching-Shan Chou |
| Abstract | Complex computational models are often designed to simulate real-world physical phenomena in many scientific disciplines. However, these simulation models tend to be computationally very expensive and involve a large number of simulation input parameters which need to be analyzed and properly calibrated before the models can be applied for real scientific studies. We propose a visual analysis system to facilitate interactive exploratory analysis of high-dimensional input parameter space for a complex yeast cell polarization simulation. The proposed system can assist the computational biologists, who designed the simulation model, to visually calibrate the input parameters by modifying the parameter values and immediately visualizing the predicted simulation outcome without having the need to run the original expensive simulation for every instance. Our proposed visual analysis system is driven by a trained neural network-based surrogate model as the backend analysis framework. Surrogate models are widely used in the field of simulation sciences to efficiently analyze computationally expensive simulation models. In this work, we demonstrate the advantage of using neural networks as surrogate models for visual analysis by incorporating some of the recent advances in the field of uncertainty quantification, interpretability and explainability of neural network-based models. We utilize the trained network to perform interactive parameter sensitivity analysis of the original simulation at multiple levels-of-detail as well as recommend optimal parameter configurations using the activation maximization framework of neural networks. We also facilitate detail analysis of the trained network to extract useful insights about the simulation model, learned by the network, during the training process. |
| Tasks | |
| Published | 2019-04-19 |
| URL | https://arxiv.org/abs/1904.09044v3 |
| https://arxiv.org/pdf/1904.09044v3.pdf | |
| PWC | https://paperswithcode.com/paper/nnva-neural-network-assisted-visual-analysis |
| Repo | |
| Framework | |
Number-State Preserving Tensor Networks as Classifiers for Supervised Learning
| Title | Number-State Preserving Tensor Networks as Classifiers for Supervised Learning |
| Authors | Glen Evenbly |
| Abstract | We propose a restricted class of tensor network state, built from number-state preserving tensors, for supervised learning tasks. This class of tensor network is argued to be a natural choice for classifiers as (i) they map classical data to classical data, and thus preserve the interpretability of data under tensor transformations, (ii) they can be efficiently trained to maximize their scalar product against classical data sets, and (iii) they seem to be as powerful as generic (unrestricted) tensor networks in this task. Our proposal is demonstrated using a variety of benchmark classification problems, where number-state preserving versions of commonly used networks (including MPS, TTN and MERA) are trained as effective classifiers. This work opens the path for powerful tensor network methods such as MERA, which were previously computationally intractable as classifiers, to be employed for difficult tasks such as image recognition. |
| Tasks | Tensor Networks |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06352v1 |
| https://arxiv.org/pdf/1905.06352v1.pdf | |
| PWC | https://paperswithcode.com/paper/number-state-preserving-tensor-networks-as |
| Repo | |
| Framework | |
Texture CNN for Thermoelectric Metal Pipe Image Classification
| Title | Texture CNN for Thermoelectric Metal Pipe Image Classification |
| Authors | Daniel Vriesman, Alessandro Zimmer, Alceu S. Britto Jr., Alessandro L. Koerich |
| Abstract | In this paper, the concept of representation learning based on deep neural networks is applied as an alternative to the use of handcrafted features in a method for automatic visual inspection of corroded thermoelectric metallic pipes. A texture convolutional neural network (TCNN) replaces handcrafted features based on Local Phase Quantization (LPQ) and Haralick descriptors (HD) with the advantage of learning an appropriate textural representation and the decision boundaries into a single optimization process. Experimental results have shown that it is possible to reach the accuracy of 99.20% in the task of identifying different levels of corrosion in the internal surface of thermoelectric pipe walls, while using a compact network that requires much less effort in tuning parameters when compared to the handcrafted approach since the TCNN architecture is compact regarding the number of layers and connections. The observed results open up the possibility of using deep neural networks in real-time applications such as the automatic inspection of thermoelectric metal pipes. |
| Tasks | Image Classification, Quantization, Representation Learning |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12003v1 |
| https://arxiv.org/pdf/1905.12003v1.pdf | |
| PWC | https://paperswithcode.com/paper/texture-cnn-for-thermoelectric-metal-pipe |
| Repo | |
| Framework | |
General Subpopulation Framework and Taming the Conflict Inside Populations
| Title | General Subpopulation Framework and Taming the Conflict Inside Populations |
| Authors | Danilo Vasconcellos Vargas, Junichi Murata, Hirotaka Takano, Alexandre Claudio Botazzo Delbem |
| Abstract | Structured evolutionary algorithms have been investigated for some time. However, they have been under-explored specially in the field of multi-objective optimization. Despite their good results, the use of complex dynamics and structures make their understanding and adoption rate low. Here, we propose the general subpopulation framework that has the capability of integrating optimization algorithms without restrictions as well as aid the design of structured algorithms. The proposed framework is capable of generalizing most of the structured evolutionary algorithms, such as cellular algorithms, island models, spatial predator-prey and restricted mating based algorithms under its formalization. Moreover, we propose two algorithms based on the general subpopulation framework, demonstrating that with the simple addition of a number of single-objective differential evolution algorithms for each objective the results improve greatly, even when the combined algorithms behave poorly when evaluated alone at the tests. Most importantly, the comparison between the subpopulation algorithms and their related panmictic algorithms suggests that the competition between different strategies inside one population can have deleterious consequences for an algorithm and reveal a strong benefit of using the subpopulation framework. The code for SAN, the proposed multi-objective algorithm which has the current best results in the hardest benchmark, is available at the following https://github.com/zweifel/zweifel |
| Tasks | |
| Published | 2019-01-02 |
| URL | http://arxiv.org/abs/1901.00266v1 |
| http://arxiv.org/pdf/1901.00266v1.pdf | |
| PWC | https://paperswithcode.com/paper/general-subpopulation-framework-and-taming |
| Repo | |
| Framework | |
WiseMove: A Framework for Safe Deep Reinforcement Learning for Autonomous Driving
| Title | WiseMove: A Framework for Safe Deep Reinforcement Learning for Autonomous Driving |
| Authors | Jaeyoung Lee, Aravind Balakrishnan, Ashish Gaurav, Krzysztof Czarnecki, Sean Sedwards |
| Abstract | Machine learning can provide efficient solutions to the complex problems encountered in autonomous driving, but ensuring their safety remains a challenge. A number of authors have attempted to address this issue, but there are few publicly-available tools to adequately explore the trade-offs between functionality, scalability, and safety. We thus present WiseMove, a software framework to investigate safe deep reinforcement learning in the context of motion planning for autonomous driving. WiseMove adopts a modular learning architecture that suits our current research questions and can be adapted to new technologies and new questions. We present the details of WiseMove, demonstrate its use on a common traffic scenario, and describe how we use it in our ongoing safe learning research. |
| Tasks | Autonomous Driving, Motion Planning |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.04118v1 |
| http://arxiv.org/pdf/1902.04118v1.pdf | |
| PWC | https://paperswithcode.com/paper/wisemove-a-framework-for-safe-deep |
| Repo | |
| Framework | |
An Implementation of a Non-monotonic Logic in an Embedded Computer for a Motor-glider
| Title | An Implementation of a Non-monotonic Logic in an Embedded Computer for a Motor-glider |
| Authors | José Luis Vilchis Medina, Pierre Siegel, Vincent Risch, Andrei Doncescu |
| Abstract | In this article we present an implementation of non-monotonic reasoning in an embedded system. As a part of an autonomous motor-glider, it simulates piloting decisions of an airplane. A real pilot must take care not only about the information arising from the cockpit (airspeed, altitude, variometer, compass…) but also from outside the cabin. Throughout a flight, a pilot is constantly in communication with the control tower to follow orders, because there is an airspace regulation to respect. In addition, if the control tower sends orders while the pilot has an emergency, he may have to violate these orders and airspace regulations to solve his problem (e.g. emergency landing). On the other hand, climate changes constantly (wind, snow, hail..) and can affect the sensors. All these cases easily lead to contradictions. Switching to reasoning under uncertainty, a pilot must make decisions to carry out a flight. The objective of this implementation is to validate a non-monotonic model which allows to solve the question of incomplete and contradictory information. We formalize the problem using default logic, a non-monotonic logic which allows to find fixed-points in the face of contradictions. For the implementation, the Prolog language is used in an embedded computer running at 1 GHz single core with 512 Mb of RAM and 0.8 watts of energy consumption. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13305v2 |
| https://arxiv.org/pdf/1907.13305v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-implementation-of-a-non-monotonic-logic-in |
| Repo | |
| Framework | |
Learning-Based Synthesis of Safety Controllers
| Title | Learning-Based Synthesis of Safety Controllers |
| Authors | Daniel Neider, Oliver Markgraf |
| Abstract | We propose a machine learning framework to synthesize reactive controllers for systems whose interactions with their adversarial environment are modeled by infinite-duration, two-player games over (potentially) infinite graphs. Our framework targets safety games with infinitely many vertices, but it is also applicable to safety games over finite graphs whose size is too prohibitive for conventional synthesis techniques. The learning takes place in a feedback loop between a teacher component, which can reason symbolically about the safety game, and a learning algorithm, which successively learns an overapproximation of the winning region from various kinds of examples provided by the teacher. We develop a novel decision tree learning algorithm for this setting and show that our algorithm is guaranteed to converge to a reactive safety controller if a suitable overapproximation of the winning region can be expressed as a decision tree. Finally, we empirically compare the performance of a prototype implementation to existing approaches, which are based on constraint solving and automata learning, respectively. |
| Tasks | Motion Planning |
| Published | 2019-01-21 |
| URL | https://arxiv.org/abs/1901.06801v3 |
| https://arxiv.org/pdf/1901.06801v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-based-synthesis-of-safety |
| Repo | |
| Framework | |
LAEO-Net: revisiting people Looking At Each Other in videos
| Title | LAEO-Net: revisiting people Looking At Each Other in videos |
| Authors | Manuel J. Marin-Jimenez, Vicky Kalogeiton, Pablo Medina-Suarez, Andrew Zisserman |
| Abstract | Capturing the `mutual gaze’ of people is essential for understanding and interpreting the social interactions between them. To this end, this paper addresses the problem of detecting people Looking At Each Other (LAEO) in video sequences. For this purpose, we propose LAEO-Net, a new deep CNN for determining LAEO in videos. In contrast to previous works, LAEO-Net takes spatio-temporal tracks as input and reasons about the whole track. It consists of three branches, one for each character’s tracked head and one for their relative position. Moreover, we introduce two new LAEO datasets: UCO-LAEO and AVA-LAEO. A thorough experimental evaluation demonstrates the ability of LAEONet to successfully determine if two people are LAEO and the temporal window where it happens. Our model achieves state-of-the-art results on the existing TVHID-LAEO video dataset, significantly outperforming previous approaches. Finally, we apply LAEO-Net to social network analysis, where we automatically infer the social relationship between pairs of people based on the frequency and duration that they LAEO. | |
| Tasks | |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05261v1 |
| https://arxiv.org/pdf/1906.05261v1.pdf | |
| PWC | https://paperswithcode.com/paper/laeo-net-revisiting-people-looking-at-each-1 |
| Repo | |
| Framework | |
Deep Grid Net (DGN): A Deep Learning System for Real-Time Driving Context Understanding
| Title | Deep Grid Net (DGN): A Deep Learning System for Real-Time Driving Context Understanding |
| Authors | Liviu Marina, Bogdan Trasnea, Cocias Tiberiu, Andrei Vasilcoi, Florin Moldoveanu, Sorin Grigorescu |
| Abstract | Grid maps obtained from fused sensory information are nowadays among the most popular approaches for motion planning for autonomous driving cars. In this paper, we introduce Deep Grid Net (DGN), a deep learning (DL) system designed for understanding the context in which an autonomous car is driving. DGN incorporates a learned driving environment representation based on Occupancy Grids (OG) obtained from raw Lidar data and constructed on top of the Dempster-Shafer (DS) theory. The predicted driving context is further used for switching between different driving strategies implemented within EB robinos, Elektrobit’s Autonomous Driving (AD) software platform. Based on genetic algorithms (GAs), we also propose a neuroevolutionary approach for learning the tuning hyperparameters of DGN. The performance of the proposed deep network has been evaluated against similar competing driving context estimation classifiers. |
| Tasks | Autonomous Driving, Motion Planning |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1901.05203v1 |
| http://arxiv.org/pdf/1901.05203v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-grid-net-dgn-a-deep-learning-system-for |
| Repo | |
| Framework | |
Robust Multi-Output Learning with Highly Incomplete Data via Restricted Boltzmann Machines
| Title | Robust Multi-Output Learning with Highly Incomplete Data via Restricted Boltzmann Machines |
| Authors | Giancarlo Fissore, Aurélien Decelle, Cyril Furtlehner, Yufei Han |
| Abstract | In a standard multi-output classification scenario, both features and labels of training data are partially observed. This challenging issue is widely witnessed due to sensor or database failures, crowd-sourcing and noisy communication channels in industrial data analytic services. Classic methods for handling multi-output classification with incomplete supervision information usually decompose the problem into an imputation stage that reconstructs the missing training information, and a learning stage that builds a classifier based on the imputed training set. These methods fail to fully leverage the dependencies between features and labels. In order to take full advantage of these dependencies we consider a purely probabilistic setting in which the features imputation and multi-label classification problems are jointly solved. Indeed, we show that a simple Restricted Boltzmann Machine can be trained with an adapted algorithm based on mean-field equations to efficiently solve problems of inductive and transductive learning in which both features and labels are missing at random. The effectiveness of the approach is demonstrated empirically on various datasets, with particular focus on a real-world Internet-of-Things security dataset. |
| Tasks | Imputation, Multi-Label Classification |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09382v1 |
| https://arxiv.org/pdf/1912.09382v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-multi-output-learning-with-highly |
| Repo | |
| Framework | |
