Paper Group ANR 560
Adversarial Inpainting of Medical Image Modalities. Automatic Short Answer Grading and Feedback Using Text Mining Methods. An Optical Frontend for a Convolutional Neural Network. Fabrik: An Online Collaborative Neural Network Editor. Conditional Variational Autoencoder for Neural Machine Translation. Auto-tuning Distributed Stream Processing System …
Adversarial Inpainting of Medical Image Modalities
Title | Adversarial Inpainting of Medical Image Modalities |
Authors | Karim Armanious, Youssef Mecky, Sergios Gatidis, Bin Yang |
Abstract | Numerous factors could lead to partial deteriorations of medical images. For example, metallic implants will lead to localized perturbations in MRI scans. This will affect further post-processing tasks such as attenuation correction in PET/MRI or radiation therapy planning. In this work, we propose the inpainting of medical images via Generative Adversarial Networks (GANs). The proposed framework incorporates two patch-based discriminator networks with additional style and perceptual losses for the inpainting of missing information in realistically detailed and contextually consistent manner. The proposed framework outperformed other natural image inpainting techniques both qualitatively and quantitatively on two different medical modalities. |
Tasks | Image Inpainting |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06621v1 |
http://arxiv.org/pdf/1810.06621v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-inpainting-of-medical-image |
Repo | |
Framework | |
Automatic Short Answer Grading and Feedback Using Text Mining Methods
Title | Automatic Short Answer Grading and Feedback Using Text Mining Methods |
Authors | Neslihan Suzen, Alexander Gorban, Jeremy Levesley, Evgeny Mirkes |
Abstract | Automatic grading is not a new approach but the need to adapt the latest technology to automatic grading has become very important. As the technology has rapidly became more powerful on scoring exams and essays, especially from the 1990s onwards, partially or wholly automated grading systems using computational methods have evolved and have become a major area of research. In particular, the demand of scoring of natural language responses has created a need for tools that can be applied to automatically grade these responses. In this paper, we focus on the concept of automatic grading of short answer questions such as are typical in the UK GCSE system, and providing useful feedback on their answers to students. We present experimental results on a dataset provided from the introductory computer science class in the University of North Texas. We first apply standard data mining techniques to the corpus of student answers for the purpose of measuring similarity between the student answers and the model answer. This is based on the number of common words. We then evaluate the relation between these similarities and marks awarded by scorers. We then consider an approach that groups student answers into clusters. Each cluster would be awarded the same mark, and the same feedback given to each answer in a cluster. In this manner, we demonstrate that clusters indicate the groups of students who are awarded the same or the similar scores. Words in each cluster are compared to show that clusters are constructed based on how many and which words of the model answer have been used. The main novelty in this paper is that we design a model to predict marks based on the similarities between the student answers and the model answer. |
Tasks | |
Published | 2018-07-27 |
URL | https://arxiv.org/abs/1807.10543v3 |
https://arxiv.org/pdf/1807.10543v3.pdf | |
PWC | https://paperswithcode.com/paper/automatic-short-answer-grading-and-feedback |
Repo | |
Framework | |
An Optical Frontend for a Convolutional Neural Network
Title | An Optical Frontend for a Convolutional Neural Network |
Authors | Shane Colburn, Yi Chu, Eli Shlizerman, Arka Majumdar |
Abstract | The parallelism of optics and the miniaturization of optical components using nanophotonic structures, such as metasurfaces present a compelling alternative to electronic implementations of convolutional neural networks. The lack of a low-power optical nonlinearity, however, requires slow and energy-inefficient conversions between the electronic and optical domains. Here, we design an architecture which utilizes a single electrical to optical conversion by designing a free-space optical frontend unit that implements the linear operations of the first layer with the subsequent layers realized electronically. Speed and power analysis of the architecture indicates that the hybrid photonic-electronic architecture outperforms sole electronic architecture for large image sizes and kernels. Benchmarking of the photonic-electronic architecture on a modified version of AlexNet achieves a classification accuracy of 87% on images from the Kaggle Cats and Dogs challenge database. |
Tasks | |
Published | 2018-12-23 |
URL | http://arxiv.org/abs/1901.03661v2 |
http://arxiv.org/pdf/1901.03661v2.pdf | |
PWC | https://paperswithcode.com/paper/an-optical-frontend-for-a-convolutional |
Repo | |
Framework | |
Fabrik: An Online Collaborative Neural Network Editor
Title | Fabrik: An Online Collaborative Neural Network Editor |
Authors | Utsav Garg, Viraj Prabhu, Deshraj Yadav, Ram Ramrakhya, Harsh Agrawal, Dhruv Batra |
Abstract | We present Fabrik, an online neural network editor that provides tools to visualize, edit, and share neural networks from within a browser. Fabrik provides a simple and intuitive GUI to import neural networks written in popular deep learning frameworks such as Caffe, Keras, and TensorFlow, and allows users to interact with, build, and edit models via simple drag and drop. Fabrik is designed to be framework agnostic and support high interoperability, and can be used to export models back to any supported framework. Finally, it provides powerful collaborative features to enable users to iterate over model design remotely and at scale. |
Tasks | |
Published | 2018-10-27 |
URL | http://arxiv.org/abs/1810.11649v1 |
http://arxiv.org/pdf/1810.11649v1.pdf | |
PWC | https://paperswithcode.com/paper/fabrik-an-online-collaborative-neural-network |
Repo | |
Framework | |
Conditional Variational Autoencoder for Neural Machine Translation
Title | Conditional Variational Autoencoder for Neural Machine Translation |
Authors | Artidoro Pagnoni, Kevin Liu, Shangyan Li |
Abstract | We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent variable to model features of the translation process. We extend this model with a co-attention mechanism motivated by Parikh et al. in the inference network. Compared to the vision domain, latent variable models for text face additional challenges due to the discrete nature of language, namely posterior collapse. We experiment with different approaches to mitigate this issue. We show that our conditional variational model improves upon both discriminative attention-based translation and the variational baseline presented in Zhang et al. Finally, we present some exploration of the learned latent space to illustrate what the latent variable is capable of capturing. This is the first reported conditional variational model for text that meaningfully utilizes the latent variable without weakening the translation model. |
Tasks | Latent Variable Models, Machine Translation, Text Generation |
Published | 2018-12-11 |
URL | http://arxiv.org/abs/1812.04405v1 |
http://arxiv.org/pdf/1812.04405v1.pdf | |
PWC | https://paperswithcode.com/paper/conditional-variational-autoencoder-for |
Repo | |
Framework | |
Auto-tuning Distributed Stream Processing Systems using Reinforcement Learning
Title | Auto-tuning Distributed Stream Processing Systems using Reinforcement Learning |
Authors | Luis M. Vaquero, Felix Cuadrado |
Abstract | Fine tuning distributed systems is considered to be a craftsmanship, relying on intuition and experience. This becomes even more challenging when the systems need to react in near real time, as streaming engines have to do to maintain pre-agreed service quality metrics. In this article, we present an automated approach that builds on a combination of supervised and reinforcement learning methods to recommend the most appropriate lever configurations based on previous load. With this, streaming engines can be automatically tuned without requiring a human to determine the right way and proper time to deploy them. This opens the door to new configurations that are not being applied today since the complexity of managing these systems has surpassed the abilities of human experts. We show how reinforcement learning systems can find substantially better configurations in less time than their human counterparts and adapt to changing workloads. |
Tasks | |
Published | 2018-09-14 |
URL | http://arxiv.org/abs/1809.05495v1 |
http://arxiv.org/pdf/1809.05495v1.pdf | |
PWC | https://paperswithcode.com/paper/auto-tuning-distributed-stream-processing |
Repo | |
Framework | |
Path Finding for the Coalition of Co-operative Agents Acting in the Environment with Destructible Obstacles
Title | Path Finding for the Coalition of Co-operative Agents Acting in the Environment with Destructible Obstacles |
Authors | Anton Andreychuk, Konstantin Yakovlev |
Abstract | The problem of planning a set of paths for the coalition of robots (agents) with different capabilities is considered in the paper. Some agents can modify the environment by destructing the obstacles thus allowing the other ones to shorten their paths to the goal. As a result the mutual solution of lower cost, e.g. time to completion, may be acquired. We suggest an original procedure to identify the obstacles for further removal that can be embedded into almost any heuristic search planner (we use Theta*) and evaluate it empirically. Results of the evaluation show that time-to-complete the mission can be decreased up to 9-12 % by utilizing the proposed technique. |
Tasks | |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.00771v1 |
http://arxiv.org/pdf/1807.00771v1.pdf | |
PWC | https://paperswithcode.com/paper/path-finding-for-the-coalition-of-co |
Repo | |
Framework | |
Characterizing machine learning process: A maturity framework
Title | Characterizing machine learning process: A maturity framework |
Authors | Rama Akkiraju, Vibha Sinha, Anbang Xu, Jalal Mahmud, Pritam Gundecha, Zhe Liu, Xiaotong Liu, John Schumacher |
Abstract | Academic literature on machine learning modeling fails to address how to make machine learning models work for enterprises. For example, existing machine learning processes cannot address how to define business use cases for an AI application, how to convert business requirements from offering managers into data requirements for data scientists, and how to continuously improve AI applications in term of accuracy and fairness, and how to customize general purpose machine learning models with industry, domain, and use case specific data to make them more accurate for specific situations etc. Making AI work for enterprises requires special considerations, tools, methods and processes. In this paper we present a maturity framework for machine learning model lifecycle management for enterprises. Our framework is a re-interpretation of the software Capability Maturity Model (CMM) for machine learning model development process. We present a set of best practices from our personal experience of building large scale real-world machine learning models to help organizations achieve higher levels of maturity independent of their starting point. |
Tasks | |
Published | 2018-11-12 |
URL | http://arxiv.org/abs/1811.04871v1 |
http://arxiv.org/pdf/1811.04871v1.pdf | |
PWC | https://paperswithcode.com/paper/characterizing-machine-learning-process-a |
Repo | |
Framework | |
Evaluating the Readability of Force Directed Graph Layouts: A Deep Learning Approach
Title | Evaluating the Readability of Force Directed Graph Layouts: A Deep Learning Approach |
Authors | Hammad Haleem, Yong Wang, Abishek Puri, Sahil Wadhwa, Huamin Qu |
Abstract | Existing graph layout algorithms are usually not able to optimize all the aesthetic properties desired in a graph layout. To evaluate how well the desired visual features are reflected in a graph layout, many readability metrics have been proposed in the past decades. However, the calculation of these readability metrics often requires access to the node and edge coordinates and is usually computationally inefficient, especially for dense graphs. Importantly, when the node and edge coordinates are not accessible, it becomes impossible to evaluate the graph layouts quantitatively. In this paper, we present a novel deep learning-based approach to evaluate the readability of graph layouts by directly using graph images. A convolutional neural network architecture is proposed and trained on a benchmark dataset of graph images, which is composed of synthetically-generated graphs and graphs created by sampling from real large networks. Multiple representative readability metrics (including edge crossing, node spread, and group overlap) are considered in the proposed approach. We quantitatively compare our approach to traditional methods and qualitatively evaluate our approach using a case study and visualizing convolutional layers. This work is a first step towards using deep learning based methods to evaluate images from the visualization field quantitatively. |
Tasks | |
Published | 2018-08-02 |
URL | http://arxiv.org/abs/1808.00703v2 |
http://arxiv.org/pdf/1808.00703v2.pdf | |
PWC | https://paperswithcode.com/paper/evaluating-the-readability-of-force-directed |
Repo | |
Framework | |
Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes
Title | Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes |
Authors | Le Pham Tuyen, Ngo Anh Vien, Abu Layek, TaeChoong Chung |
Abstract | In recent years, reinforcement learning has achieved many remarkable successes due to the growing adoption of deep learning techniques and the rapid growth in computing power. Nevertheless, it is well-known that flat reinforcement learning algorithms are often not able to learn well and data-efficient in tasks having hierarchical structures, e.g. consisting of multiple subtasks. Hierarchical reinforcement learning is a principled approach that is able to tackle these challenging tasks. On the other hand, many real-world tasks usually have only partial observability in which state measurements are often imperfect and partially observable. The problems of RL in such settings can be formulated as a partially observable Markov decision process (POMDP). In this paper, we study hierarchical RL in POMDP in which the tasks have only partial observability and possess hierarchical properties. We propose a hierarchical deep reinforcement learning approach for learning in hierarchical POMDP. The deep hierarchical RL algorithm is proposed to apply to both MDP and POMDP learning. We evaluate the proposed algorithm on various challenging hierarchical POMDP. |
Tasks | Hierarchical Reinforcement Learning |
Published | 2018-05-11 |
URL | http://arxiv.org/abs/1805.04419v1 |
http://arxiv.org/pdf/1805.04419v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-hierarchical-reinforcement-learning |
Repo | |
Framework | |
Task Transfer by Preference-Based Cost Learning
Title | Task Transfer by Preference-Based Cost Learning |
Authors | Mingxuan Jing, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Huaping Liu |
Abstract | The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on target task, both of which, however, are inconvenient to obtain in practice. In this paper, we relax these two strong conditions by developing a novel task transfer framework where the expert preference is applied as a guidance. In particular, we alternate the following two steps: Firstly, letting experts apply pre-defined preference rules to select related expert demonstrates for the target task. Secondly, based on the selection result, we learn the target cost function and trajectory distribution simultaneously via enhanced Adversarial MaxEnt IRL and generate more trajectories by the learned target distribution for the next preference selection. The theoretical analysis on the distribution learning and convergence of the proposed algorithm are provided. Extensive simulations on several benchmarks have been conducted for further verifying the effectiveness of the proposed method. |
Tasks | |
Published | 2018-05-12 |
URL | http://arxiv.org/abs/1805.04686v3 |
http://arxiv.org/pdf/1805.04686v3.pdf | |
PWC | https://paperswithcode.com/paper/task-transfer-by-preference-based-cost |
Repo | |
Framework | |
Programmatically Interpretable Reinforcement Learning
Title | Programmatically Interpretable Reinforcement Learning |
Authors | Abhinav Verma, Vijayaraghavan Murali, Rishabh Singh, Pushmeet Kohli, Swarat Chaudhuri |
Abstract | We present a reinforcement learning framework, called Programmatically Interpretable Reinforcement Learning (PIRL), that is designed to generate interpretable and verifiable agent policies. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, PIRL represents policies using a high-level, domain-specific programming language. Such programmatic policies have the benefits of being more easily interpreted than neural networks, and being amenable to verification by symbolic methods. We propose a new method, called Neurally Directed Program Search (NDPS), for solving the challenging nonsmooth optimization problem of finding a programmatic policy with maximal reward. NDPS works by first learning a neural policy network using DRL, and then performing a local search over programmatic policies that seeks to minimize a distance from this neural “oracle”. We evaluate NDPS on the task of learning to drive a simulated car in the TORCS car-racing environment. We demonstrate that NDPS is able to discover human-readable policies that pass some significant performance bars. We also show that PIRL policies can have smoother trajectories, and can be more easily transferred to environments not encountered during training, than corresponding policies discovered by DRL. |
Tasks | Car Racing |
Published | 2018-04-06 |
URL | http://arxiv.org/abs/1804.02477v3 |
http://arxiv.org/pdf/1804.02477v3.pdf | |
PWC | https://paperswithcode.com/paper/programmatically-interpretable-reinforcement |
Repo | |
Framework | |
Adversarial Open-World Person Re-Identification
Title | Adversarial Open-World Person Re-Identification |
Authors | Xiang Li, Ancong Wu, Wei-Shi Zheng |
Abstract | In a typical real-world application of re-id, a watch-list (gallery set) of a handful of target people (e.g. suspects) to track around a large volume of non-target people are demanded across camera views, and this is called the open-world person re-id. Different from conventional (closed-world) person re-id, a large portion of probe samples are not from target people in the open-world setting. And, it always happens that a non-target person would look similar to a target one and therefore would seriously challenge a re-id system. In this work, we introduce a deep open-world group-based person re-id model based on adversarial learning to alleviate the attack problem caused by similar non-target people. The main idea is learning to attack feature extractor on the target people by using GAN to generate very target-like images (imposters), and in the meantime the model will make the feature extractor learn to tolerate the attack by discriminative learning so as to realize group-based verification. The framework we proposed is called the adversarial open-world person re-identification, and this is realized by our Adversarial PersonNet (APN) that jointly learns a generator, a person discriminator, a target discriminator and a feature extractor, where the feature extractor and target discriminator share the same weights so as to makes the feature extractor learn to tolerate the attack by imposters for better group-based verification. While open-world person re-id is challenging, we show for the first time that the adversarial-based approach helps stabilize person re-id system under imposter attack more effectively. |
Tasks | Person Re-Identification |
Published | 2018-07-27 |
URL | http://arxiv.org/abs/1807.10482v3 |
http://arxiv.org/pdf/1807.10482v3.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-open-world-person-re |
Repo | |
Framework | |
Portmanteau test for the asymmetric power GARCH model when the power is unknown
Title | Portmanteau test for the asymmetric power GARCH model when the power is unknown |
Authors | Yacouba Boubacar Maïnassara, Othman Kadmiri, Bruno Saussereau |
Abstract | It is now widely accepted that, to model the dynamics of daily financial returns, volatility models have to incorporate the so-called leverage effect. We derive the asymptotic behaviour of the squared residuals autocovariances for the class of asymmetric power GARCH model when the power is unknown and is jointly estimated with the model’s parameters. We then deduce a portmanteau adequacy test based on the autocovariances of the squared residuals. These asymptotic results are illustrated by Monte Carlo experiments. An application to real financial data is also proposed. |
Tasks | |
Published | 2018-11-21 |
URL | http://arxiv.org/abs/1811.08769v1 |
http://arxiv.org/pdf/1811.08769v1.pdf | |
PWC | https://paperswithcode.com/paper/portmanteau-test-for-the-asymmetric-power |
Repo | |
Framework | |
Finite State Machines for Semantic Scene Parsing and Segmentation
Title | Finite State Machines for Semantic Scene Parsing and Segmentation |
Authors | Hichem Sahbi |
Abstract | We introduce in this work a novel stochastic inference process, for scene annotation and object class segmentation, based on finite state machines (FSMs). The design principle of our framework is generative and based on building, for a given scene, finite state machines that encode annotation lattices, and inference consists in finding and scoring the best configurations in these lattices. Different novel operations are defined using our FSM framework including reordering, segmentation, visual transduction, and label dependency modeling. All these operations are combined together in order to achieve annotation as well as object class segmentation. |
Tasks | Scene Parsing |
Published | 2018-12-27 |
URL | http://arxiv.org/abs/1812.10745v1 |
http://arxiv.org/pdf/1812.10745v1.pdf | |
PWC | https://paperswithcode.com/paper/finite-state-machines-for-semantic-scene |
Repo | |
Framework | |