October 20, 2019

2803 words 14 mins read

Paper Group AWR 293

Machine Learning Classifiers Do Not Improve the Prediction of Academic Risk: Evidence from Australia. Deep Reinforcement Learning for General Video Game AI. Links: A High-Dimensional Online Clustering Method. Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network. I-HAZE: a dehazing benchmark with real hazy and haze- …

Machine Learning Classifiers Do Not Improve the Prediction of Academic Risk: Evidence from Australia


Title	Machine Learning Classifiers Do Not Improve the Prediction of Academic Risk: Evidence from Australia
Authors	Sarah Cornell-Farrow, Robert Garrard
Abstract	Machine learning methods tend to outperform traditional statistical models at prediction. In the prediction of academic achievement, ML models have not shown substantial improvement over logistic regression. So far, these results have almost entirely focused on college achievement, due to the availability of administrative datasets, and have contained relatively small sample sizes by ML standards. In this article we apply popular machine learning models to a large dataset ($n=1.2$ million) containing primary and middle school performance on a standardized test given annually to Australian students. We show that machine learning models do not outperform logistic regression for detecting students who will perform in the `below standard’ band of achievement upon sitting their next test, even in a large-$n$ setting. \|
Tasks
Published	2018-07-19
URL	https://arxiv.org/abs/1807.07215v4
PDF	https://arxiv.org/pdf/1807.07215v4.pdf
PWC	https://paperswithcode.com/paper/machine-learning-classifiers-do-not-improve
Repo	https://github.com/RobGarrard/A-Machine-Learning-Approach-for-Detecting-Students-at-Risk-of-Low-Academic-Achievement
Framework	tf

Deep Reinforcement Learning for General Video Game AI


Title	Deep Reinforcement Learning for General Video Game AI
Authors	Ruben Rodriguez Torrado, Philip Bontrager, Julian Togelius, Jialin Liu, Diego Perez-Liebana
Abstract	The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward model that allows the use of algorithms such as Monte Carlo Tree Search. In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems. Using this interface, we characterize how widely used implementations of several deep reinforcement learning algorithms fare on a number of GVGAI games. We further analyze the results to provide a first indication of the relative difficulty of these games relative to each other, and relative to those in the Arcade Learning Environment under similar conditions.
Tasks	Atari Games
Published	2018-06-06
URL	http://arxiv.org/abs/1806.02448v1
PDF	http://arxiv.org/pdf/1806.02448v1.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-general-video
Repo	https://github.com/rubenrtorrado/GVGAI_GYM
Framework	none

Links: A High-Dimensional Online Clustering Method


Title	Links: A High-Dimensional Online Clustering Method
Authors	Philip Andrew Mansfield, Quan Wang, Carlton Downey, Li Wan, Ignacio Lopez Moreno
Abstract	We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space. The algorithm is appropriate when it is necessary to cluster data efficiently as it streams in, and is to be contrasted with traditional batch clustering algorithms that have access to all data at once. For example, Links has been successfully applied to embedding vectors generated from face images or voice recordings for the purpose of recognizing people, thereby providing real-time identification during video or audio capture.
Tasks
Published	2018-01-30
URL	http://arxiv.org/abs/1801.10123v1
PDF	http://arxiv.org/pdf/1801.10123v1.pdf
PWC	https://paperswithcode.com/paper/links-a-high-dimensional-online-clustering
Repo	https://github.com/QEDan/links_clustering
Framework	none

Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network


Title	Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network
Authors	Qiang Zhang, Qiangqiang Yuan, Jie Li, Xinxin Liu, Huanfeng Shen, Liangpei Zhang
Abstract	The existence of hybrid noise in hyperspectral images (HSIs) severely degrades the data quality, reduces the interpretation accuracy of HSIs, and restricts the subsequent HSIs applications. In this paper, the spatial-spectral gradient network (SSGN) is presented for mixed noise removal in HSIs. The proposed method employs a spatial-spectral gradient learning strategy, in consideration of the unique spatial structure directionality of sparse noise and spectral differences with additional complementary information for better extracting intrinsic and deep features of HSIs. Based on a fully cascaded multi-scale convolutional network, SSGN can simultaneously deal with the different types of noise in different HSIs or spectra by the use of the same model. The simulated and real-data experiments undertaken in this study confirmed that the proposed SSGN performs better at mixed noise removal than the other state-of-the-art HSI denoising algorithms, in evaluation indices, visual assessments, and time consumption.
Tasks	Denoising
Published	2018-10-01
URL	http://arxiv.org/abs/1810.00495v3
PDF	http://arxiv.org/pdf/1810.00495v3.pdf
PWC	https://paperswithcode.com/paper/hybrid-noise-removal-in-hyperspectral-imagery
Repo	https://github.com/WHUQZhang/SSGN
Framework	none

I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images


Title	I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images
Authors	Codruta O. Ancuti, Cosmin Ancuti, Radu Timofte, Christophe De Vleeschouwer
Abstract	Image dehazing has become an important computational imaging topic in the recent years. However, due to the lack of ground truth images, the comparison of dehazing methods is not straightforward, nor objective. To overcome this issue we introduce a new dataset -named I-HAZE- that contains 35 image pairs of hazy and corresponding haze-free (ground-truth) indoor images. Different from most of the existing dehazing databases, hazy images have been generated using real haze produced by a professional haze machine. For easy color calibration and improved assessment of dehazing algorithms, each scene include a MacBeth color checker. Moreover, since the images are captured in a controlled environment, both haze-free and hazy images are captured under the same illumination conditions. This represents an important advantage of the I-HAZE dataset that allows us to objectively compare the existing image dehazing techniques using traditional image quality metrics such as PSNR and SSIM.
Tasks	Calibration, Image Dehazing
Published	2018-04-13
URL	http://arxiv.org/abs/1804.05091v1
PDF	http://arxiv.org/pdf/1804.05091v1.pdf
PWC	https://paperswithcode.com/paper/i-haze-a-dehazing-benchmark-with-real-hazy
Repo	https://github.com/inyong37/Vision
Framework	tf

Complexity Reduction in the Negotiation of New Lexical Conventions


Title	Complexity Reduction in the Negotiation of New Lexical Conventions
Authors	William Schueller, Vittorio Loreto, Pierre-Yves Oudeyer
Abstract	In the process of collectively inventing new words for new concepts in a population, conflicts can quickly become numerous, in the form of synonymy and homonymy. Remembering all of them could cost too much memory, and remembering too few may slow down the overall process. Is there an efficient behavior that could help balance the two? The Naming Game is a multi-agent computational model for the emergence of language, focusing on the negotiation of new lexical conventions, where a common lexicon self-organizes but going through a phase of high complexity. Previous work has been done on the control of complexity growth in this particular model, by allowing agents to actively choose what they talk about. However, those strategies were relying on ad hoc heuristics highly dependent on fine-tuning of parameters. We define here a new principled measure and a new strategy, based on the beliefs of each agent on the global state of the population. The measure does not rely on heavy computation, and is cognitively plausible. The new strategy yields an efficient control of complexity growth, along with a faster agreement process. Also, we show that short-term memory is enough to build relevant beliefs about the global lexicon.
Tasks
Published	2018-05-15
URL	http://arxiv.org/abs/1805.05631v2
PDF	http://arxiv.org/pdf/1805.05631v2.pdf
PWC	https://paperswithcode.com/paper/complexity-reduction-in-the-negotiation-of
Repo	https://github.com/wschuell/notebooks_cogsci2018
Framework	none

Medical Concept Embedding with Time-Aware Attention


Title	Medical Concept Embedding with Time-Aware Attention
Authors	Xiangrui Cai, Jinyang Gao, Kee Yuan Ngiam, Beng Chin Ooi, Ying Zhang, Xiaojie Yuan
Abstract	Embeddings of medical concepts such as medication, procedure and diagnosis codes in Electronic Medical Records (EMRs) are central to healthcare analytics. Previous work on medical concept embedding takes medical concepts and EMRs as words and documents respectively. Nevertheless, such models miss out the temporal nature of EMR data. On the one hand, two consecutive medical concepts do not indicate they are temporally close, but the correlations between them can be revealed by the time gap. On the other hand, the temporal scopes of medical concepts often vary greatly (e.g., \textit{common cold} and \textit{diabetes}). In this paper, we propose to incorporate the temporal information to embed medical codes. Based on the Continuous Bag-of-Words model, we employ the attention mechanism to learn a “soft” time-aware context window for each medical concept. Experiments on public and proprietary datasets through clustering and nearest neighbour search tasks demonstrate the effectiveness of our model, showing that it outperforms five state-of-the-art baselines.
Tasks
Published	2018-06-06
URL	http://arxiv.org/abs/1806.02873v1
PDF	http://arxiv.org/pdf/1806.02873v1.pdf
PWC	https://paperswithcode.com/paper/medical-concept-embedding-with-time-aware
Repo	https://github.com/XiangruiCAI/mce
Framework	none

Sylvester Normalizing Flows for Variational Inference


Title	Sylvester Normalizing Flows for Variational Inference
Authors	Rianne van den Berg, Leonard Hasenclever, Jakub M. Tomczak, Max Welling
Abstract	Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can be seen as a generalization of planar flows. Sylvester normalizing flows remove the well-known single-unit bottleneck from planar flows, making a single transformation much more flexible. We compare the performance of Sylvester normalizing flows against planar flows and inverse autoregressive flows and demonstrate that they compare favorably on several datasets.
Tasks
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05649v2
PDF	http://arxiv.org/pdf/1803.05649v2.pdf
PWC	https://paperswithcode.com/paper/sylvester-normalizing-flows-for-variational
Repo	https://github.com/riannevdberg/sylvester-flows
Framework	pytorch

Relational recurrent neural networks


Title	Relational recurrent neural networks
Authors	Adam Santoro, Ryan Faulkner, David Raposo, Jack Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy Lillicrap
Abstract	Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to perform complex relational reasoning with the information they remember. Here, we first confirm our intuitions that standard memory architectures may struggle at tasks that heavily involve an understanding of the ways in which entities are connected – i.e., tasks involving relational reasoning. We then improve upon these deficits by using a new memory module – a \textit{Relational Memory Core} (RMC) – which employs multi-head dot product attention to allow memories to interact. Finally, we test the RMC on a suite of tasks that may profit from more capable relational reasoning across sequential information, and show large gains in RL domains (e.g. Mini PacMan), program evaluation, and language modeling, achieving state-of-the-art results on the WikiText-103, Project Gutenberg, and GigaWord datasets.
Tasks	Language Modelling, Relational Reasoning
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01822v2
PDF	http://arxiv.org/pdf/1806.01822v2.pdf
PWC	https://paperswithcode.com/paper/relational-recurrent-neural-networks
Repo	https://github.com/L0SG/relational-rnn-pytorch
Framework	pytorch

Disconnected Manifold Learning for Generative Adversarial Networks


Title	Disconnected Manifold Learning for Generative Adversarial Networks
Authors	Mahyar Khayatkhoei, Ahmed Elgammal, Maneesh Singh
Abstract	Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs). In this work, we first show that single generator GANs are unable to correctly model a distribution supported on a disconnected manifold, and investigate how sample quality, mode dropping and local convergence are affected by this. Next, we show how using a collection of generators can address this problem, providing new insights into the success of such multi-generator GANs. Finally, we explain the serious issues caused by considering a fixed prior over the collection of generators and propose a novel approach for learning the prior and inferring the necessary number of generators without any supervision. Our proposed modifications can be applied on top of any other GAN model to enable learning of distributions supported on disconnected manifolds. We conduct several experiments to illustrate the aforementioned shortcoming of GANs, its consequences in practice, and the effectiveness of our proposed modifications in alleviating these issues.
Tasks
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00880v3
PDF	http://arxiv.org/pdf/1806.00880v3.pdf
PWC	https://paperswithcode.com/paper/disconnected-manifold-learning-for-generative
Repo	https://github.com/mahyarkoy/dmgan_release
Framework	tf

Adversarial Inference for Multi-Sentence Video Description


Title	Adversarial Inference for Multi-Sentence Video Description
Authors	Jae Sung Park, Marcus Rohrbach, Trevor Darrell, Anna Rohrbach
Abstract	While significant progress has been made in the image captioning task, video description is still in its infancy due to the complex nature of video data. Generating multi-sentence descriptions for long videos is even more challenging. Among the main issues are the fluency and coherence of the generated descriptions, and their relevance to the video. Recently, reinforcement and adversarial learning based methods have been explored to improve the image captioning models; however, both types of methods suffer from a number of issues, e.g. poor readability and high redundancy for RL and stability issues for GANs. In this work, we instead propose to apply adversarial techniques during inference, designing a discriminator which encourages better multi-sentence video description. In addition, we find that a multi-discriminator “hybrid” design, where each discriminator targets one aspect of a description, leads to the best results. Specifically, we decouple the discriminator to evaluate on three criteria: 1) visual relevance to the video, 2) language diversity and fluency, and 3) coherence across sentences. Our approach results in more accurate, diverse, and coherent multi-sentence video descriptions, as shown by automatic as well as human evaluation on the popular ActivityNet Captions dataset.
Tasks	Image Captioning, Video Description
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05634v2
PDF	http://arxiv.org/pdf/1812.05634v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-inference-for-multi-sentence
Repo	https://github.com/jamespark3922/adv-inf
Framework	pytorch

Deep Triplet Ranking Networks for One-Shot Recognition


Title	Deep Triplet Ranking Networks for One-Shot Recognition
Authors	Meng Ye, Yuhong Guo
Abstract	Despite the breakthroughs achieved by deep learning models in conventional supervised learning scenarios, their dependence on sufficient labeled training data in each class prevents effective applications of these deep models in situations where labeled training instances for a subset of novel classes are very sparse – in the extreme case only one instance is available for each class. To tackle this natural and important challenge, one-shot learning, which aims to exploit a set of well labeled base classes to build classifiers for the new target classes that have only one observed instance per class, has recently received increasing attention from the research community. In this paper we propose a novel end-to-end deep triplet ranking network to perform one-shot learning. The proposed approach learns class universal image embeddings on the well labeled base classes under a triplet ranking loss, such that the instances from new classes can be categorized based on their similarity with the one-shot instances in the learned embedding space. Moreover, our approach can naturally incorporate the available one-shot instances from the new classes into the embedding learning process to improve the triplet ranking model. We conduct experiments on two popular datasets for one-shot learning. The results show the proposed approach achieves better performance than the state-of-the- art comparison methods.
Tasks	One-Shot Learning
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07275v1
PDF	http://arxiv.org/pdf/1804.07275v1.pdf
PWC	https://paperswithcode.com/paper/deep-triplet-ranking-networks-for-one-shot
Repo	https://github.com/Mushfequr-Rahman/Omniglot_baselines
Framework	pytorch

AlphaGAN: Generative adversarial networks for natural image matting


Title	AlphaGAN: Generative adversarial networks for natural image matting
Authors	Sebastian Lutz, Konstantinos Amplianitis, Aljosa Smolic
Abstract	We present the first generative adversarial network (GAN) for natural image matting. Our novel generator network is trained to predict visually appealing alphas with the addition of the adversarial loss from the discriminator that is trained to classify well-composited images. Further, we improve existing encoder-decoder architectures to better deal with the spatial localization issues inherited in convolutional neural networks (CNN) by using dilated convolutions to capture global context information without downscaling feature maps and losing spatial information. We present state-of-the-art results on the alphamatting online benchmark for the gradient error and give comparable results in others. Our method is particularly well suited for fine structures like hair, which is of great importance in practical matting applications, e.g. in film/TV production.
Tasks	Image Matting
Published	2018-07-26
URL	http://arxiv.org/abs/1807.10088v1
PDF	http://arxiv.org/pdf/1807.10088v1.pdf
PWC	https://paperswithcode.com/paper/alphagan-generative-adversarial-networks-for
Repo	https://github.com/CDOTAD/AlphaGAN-Matting
Framework	pytorch

DLOPT: Deep Learning Optimization Library


Title	DLOPT: Deep Learning Optimization Library
Authors	Andrés Camero, Jamal Toutouh, Enrique Alba
Abstract	Deep learning hyper-parameter optimization is a tough task. Finding an appropriate network configuration is a key to success, however most of the times this labor is roughly done. In this work we introduce a novel library to tackle this problem, the Deep Learning Optimization Library: DLOPT. We briefly describe its architecture and present a set of use examples. This is an open source project developed under the GNU GPL v3 license and it is freely available at https://github.com/acamero/dlopt
Tasks
Published	2018-07-10
URL	http://arxiv.org/abs/1807.03523v1
PDF	http://arxiv.org/pdf/1807.03523v1.pdf
PWC	https://paperswithcode.com/paper/dlopt-deep-learning-optimization-library
Repo	https://github.com/acamero/dlopt
Framework	none

Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks


Title	Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
Authors	Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama
Abstract	High sensitivity of neural networks against malicious perturbations on inputs causes security concerns. To take a steady step towards robust classifiers, we aim to create neural network models provably defended from perturbations. Prior certification work requires strong assumptions on network structures and massive computational costs, and thus the range of their applications was limited. From the relationship between the Lipschitz constants and prediction margins, we present a computationally efficient calculation technique to lower-bound the size of adversarial perturbations that can deceive networks, and that is widely applicable to various complicated networks. Moreover, we propose an efficient training procedure that robustifies networks and significantly improves the provably guarded areas around data points. In experimental evaluations, our method showed its ability to provide a non-trivial guarantee and enhance robustness for even large networks.
Tasks
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04034v3
PDF	http://arxiv.org/pdf/1802.04034v3.pdf
PWC	https://paperswithcode.com/paper/lipschitz-margin-training-scalable
Repo	https://github.com/ytsmiling/lmt
Framework	none