October 16, 2019

3032 words 15 mins read

Paper Group ANR 1075

An Agent-Based Simulation of Residential Location Choice of Tenants in Tehran, Iran. CAAD 2018: Powerful None-Access Black-Box Attack Based on Adversarial Transformation Network. Adversarial Learning of Semantic Relevance in Text to Image Synthesis. Correcting differences in multi-site neuroimaging data using Generative Adversarial Networks. Whitte …

An Agent-Based Simulation of Residential Location Choice of Tenants in Tehran, Iran


Title	An Agent-Based Simulation of Residential Location Choice of Tenants in Tehran, Iran
Authors	A. Shirzadi Babakan, A. Alimohammadi
Abstract	Residential location choice modeling is one of the substantial components of land use and transportation models. While numerous aggregated mathematical and statistical approaches have been developed to model the residence choice behavior of households, disaggregated approaches such as the agent-based modeling have shown interesting capabilities. In this article, a novel agent-based approach is developed to simulate the residential location choice of tenants in Tehran, the capital of Iran. Tenants are considered as agents who select their desired residential alternatives according to their characteristics and preferences for various criteria such as the rent, accessibility to different services and facilities, environmental pollution, and distance from their workplace and former residence. The choice set of agents is limited to their desired residential alternatives by applying a constrained NSGA-II algorithm. Then, agents compete with each other to select their final residence among their alternatives. Results of the proposed approach are validated by comparing simulated and actual residences of a sample of tenants. Results show that the proposed approach is able to accurately simulate the residence of 59.3% of tenants at the traffic analysis zone level.
Tasks
Published	2018-03-13
URL	http://arxiv.org/abs/1803.04927v1
PDF	http://arxiv.org/pdf/1803.04927v1.pdf
PWC	https://paperswithcode.com/paper/an-agent-based-simulation-of-residential
Repo
Framework

CAAD 2018: Powerful None-Access Black-Box Attack Based on Adversarial Transformation Network


Title	CAAD 2018: Powerful None-Access Black-Box Attack Based on Adversarial Transformation Network
Authors	Xiaoyi Dong, Weiming Zhang, Nenghai Yu
Abstract	In this paper, we propose an improvement of Adversarial Transformation Networks(ATN) to generate adversarial examples, which can fool white-box models and black-box models with a state of the art performance and won the 2rd place in the non-target task in CAAD 2018.
Tasks
Published	2018-11-03
URL	http://arxiv.org/abs/1811.01225v1
PDF	http://arxiv.org/pdf/1811.01225v1.pdf
PWC	https://paperswithcode.com/paper/caad-2018-powerful-none-access-black-box
Repo
Framework

Adversarial Learning of Semantic Relevance in Text to Image Synthesis


Title	Adversarial Learning of Semantic Relevance in Text to Image Synthesis
Authors	Miriam Cha, Youngjune L. Gwon, H. T. Kung
Abstract	We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previous work leveraging an auxiliary task in the discriminator. Our generated images are not limited to certain classes and do not suffer from mode collapse while semantically matching the text input. A key to our training methods is how to form positive and negative training examples with respect to the class label of a given image. Instead of selecting random training examples, we perform negative sampling based on the semantic distance from a positive example in the class. We evaluate our approach using the Oxford-102 flower dataset, adopting the inception score and multi-scale structural similarity index (MS-SSIM) metrics to assess discriminability and diversity of the generated images. The empirical results indicate greater diversity in the generated images, especially when we gradually select more negative training examples closer to a positive example in the semantic space.
Tasks	Image Generation
Published	2018-12-12
URL	http://arxiv.org/abs/1812.05083v2
PDF	http://arxiv.org/pdf/1812.05083v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-learning-of-semantic-relevance-in
Repo
Framework

Correcting differences in multi-site neuroimaging data using Generative Adversarial Networks


Title	Correcting differences in multi-site neuroimaging data using Generative Adversarial Networks
Authors	Harrison Nguyen, Richard W. Morris, Anthony W. Harris, Mayuresh S. Korgoankar, Fabio Ramos
Abstract	Magnetic Resonance Imaging (MRI) of the brain has been used to investigate a wide range of neurological disorders, but data acquisition can be expensive, time-consuming, and inconvenient. Multi-site studies present a valuable opportunity to advance research by pooling data in order to increase sensitivity and statistical power. However images derived from MRI are susceptible to both obvious and non-obvious differences between sites which can introduce bias and subject variance, and so reduce statistical power. To rectify these differences, we propose a data driven approach using a deep learning architecture known as generative adversarial networks (GANs). GANs learn to estimate two distributions, and can then be used to transform examples from one distribution into the other distribution. Here we transform T1-weighted brain images collected from two different sites into MR images from the same site. We evaluate whether our model can reduce site-specific differences without loss of information related to gender (male, female) or clinical diagnosis (schizophrenia, bipolar disorder, healthy). When trained appropriately, our model is able to normalise imaging sets to a common scanner set with less information loss compared to current approaches. An important advantage is our method can be treated as a black box that does not require any knowledge of the sources of bias but only needs at least two distinct imaging sets.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09375v2
PDF	http://arxiv.org/pdf/1803.09375v2.pdf
PWC	https://paperswithcode.com/paper/correcting-differences-in-multi-site
Repo
Framework

Whittemore: An embedded domain specific language for causal programming


Title	Whittemore: An embedded domain specific language for causal programming
Authors	Joshua Brulé
Abstract	This paper introduces Whittemore, a language for causal programming. Causal programming is based on the theory of structural causal models and consists of two primary operations: identification, which finds formulas that compute causal queries, and estimation, which applies formulas to transform probability distributions to other probability distribution. Causal programming provides abstractions to declare models, queries, and distributions with syntax similar to standard mathematical notation, and conducts rigorous causal inference, without requiring detailed knowledge of the underlying algorithms. Examples of causal inference with real data are provided, along with discussion of the implementation and possibilities for future extension.
Tasks	Causal Inference
Published	2018-12-21
URL	http://arxiv.org/abs/1812.11918v1
PDF	http://arxiv.org/pdf/1812.11918v1.pdf
PWC	https://paperswithcode.com/paper/whittemore-an-embedded-domain-specific
Repo
Framework

Neural Autoregressive Flows


Title	Neural Autoregressive Flows
Authors	Chin-Wei Huang, David Krueger, Alexandre Lacoste, Aaron Courville
Abstract	Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify and generalize these approaches, replacing the (conditionally) affine univariate transformations of MAF/IAF with a more general class of invertible univariate transformations expressed as monotonic neural networks. We demonstrate that the proposed neural autoregressive flows (NAF) are universal approximators for continuous probability distributions, and their greater expressivity allows them to better capture multimodal target distributions. Experimentally, NAF yields state-of-the-art performance on a suite of density estimation tasks and outperforms IAF in variational autoencoders trained on binarized MNIST.
Tasks	Density Estimation, Speech Synthesis
Published	2018-04-03
URL	http://arxiv.org/abs/1804.00779v1
PDF	http://arxiv.org/pdf/1804.00779v1.pdf
PWC	https://paperswithcode.com/paper/neural-autoregressive-flows
Repo
Framework

Neuromemrisitive Architecture of HTM with On-Device Learning and Neurogenesis


Title	Neuromemrisitive Architecture of HTM with On-Device Learning and Neurogenesis
Authors	Abdullah M. Zyarah, Dhireesha Kudithipudi
Abstract	Hierarchical temporal memory (HTM) is a biomimetic sequence memory algorithm that holds promise for invariant representations of spatial and spatiotemporal inputs. This paper presents a comprehensive neuromemristive crossbar architecture for the spatial pooler (SP) and the sparse distributed representation classifier, which are fundamental to the algorithm. There are several unique features in the proposed architecture that tightly link with the HTM algorithm. A memristor that is suitable for emulating the HTM synapses is identified and a new Z-window function is proposed. The architecture exploits the concept of synthetic synapses to enable potential synapses in the HTM. The crossbar for the SP avoids dark spots caused by unutilized crossbar regions and supports rapid on-chip training within 2 clock cycles. This research also leverages plasticity mechanisms such as neurogenesis and homeostatic intrinsic plasticity to strengthen the robustness and performance of the SP. The proposed design is benchmarked for image recognition tasks using MNIST and Yale faces datasets, and is evaluated using different metrics including entropy, sparseness, and noise robustness. Detailed power analysis at different stages of the SP operations is performed to demonstrate the suitability for mobile platforms.
Tasks
Published	2018-12-27
URL	http://arxiv.org/abs/1812.10730v1
PDF	http://arxiv.org/pdf/1812.10730v1.pdf
PWC	https://paperswithcode.com/paper/neuromemrisitive-architecture-of-htm-with-on
Repo
Framework

VSE-ens: Visual-Semantic Embeddings with Efficient Negative Sampling


Title	VSE-ens: Visual-Semantic Embeddings with Efficient Negative Sampling
Authors	Guibing Guo, Songlin Zhai, Fajie Yuan, Yuan Liu, Xingwei Wang
Abstract	Jointing visual-semantic embeddings (VSE) have become a research hotpot for the task of image annotation, which suffers from the issue of semantic gap, i.e., the gap between images’ visual features (low-level) and labels’ semantic features (high-level). This issue will be even more challenging if visual features cannot be retrieved from images, that is, when images are only denoted by numerical IDs as given in some real datasets. The typical way of existing VSE methods is to perform a uniform sampling method for negative examples that violate the ranking order against positive examples, which requires a time-consuming search in the whole label space. In this paper, we propose a fast adaptive negative sampler that can work well in the settings of no figure pixels available. Our sampling strategy is to choose the negative examples that are most likely to meet the requirements of violation according to the latent factors of images. In this way, our approach can linearly scale up to large datasets. The experiments demonstrate that our approach converges 5.02x faster than the state-of-the-art approaches on OpenImages, 2.5x on IAPR-TCI2 and 2.06x on NUS-WIDE datasets, as well as better ranking accuracy across datasets.
Tasks
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01632v2
PDF	http://arxiv.org/pdf/1801.01632v2.pdf
PWC	https://paperswithcode.com/paper/vse-ens-visual-semantic-embeddings-with
Repo
Framework

Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding


Title	Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding
Authors	JIhwan Lee, Dongchan Kim, Ruhi Sarikaya, Young-Bum Kim
Abstract	Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents, and slots by taking advantage of their hierarchical dependency in a Spoken Language Understanding system. Our proposed model learns the vector representation of intents based on the slots tied to these intents by aggregating the representations of the slots. Similarly, the vector representation of a domain is learned by aggregating the representations of the intents tied to a specific domain. To the best of our knowledge, it is the first approach to jointly learning the representations of domains, intents, and slots using their hierarchical relationships. The experimental results demonstrate the effectiveness of the representations learned by our model, as evidenced by improved performance on the contextual cross-domain reranking task.
Tasks	Representation Learning, Spoken Language Understanding
Published	2018-12-13
URL	http://arxiv.org/abs/1812.06083v1
PDF	http://arxiv.org/pdf/1812.06083v1.pdf
PWC	https://paperswithcode.com/paper/coupled-representation-learning-for-domains
Repo
Framework

Learning Personalized End-to-End Goal-Oriented Dialog


Title	Learning Personalized End-to-End Goal-Oriented Dialog
Authors	Liangchen Luo, Wenhao Huang, Qi Zeng, Zaiqing Nie, Xu Sun
Abstract	Most existing works on dialog systems only consider conversation content while neglecting the personality of the user the bot is interacting with, which begets several unsolved issues. In this paper, we present a personalized end-to-end model in an attempt to leverage personalization in goal-oriented dialogs. We first introduce a Profile Model which encodes user profiles into distributed embeddings and refers to conversation history from other similar users. Then a Preference Model captures user preferences over knowledge base entities to handle the ambiguity in user requests. The two models are combined into the Personalized MemN2N. Experiments show that the proposed model achieves qualitative performance improvements over state-of-the-art methods. As for human evaluation, it also outperforms other approaches in terms of task completion rate and user satisfaction.
Tasks	Goal-Oriented Dialog
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04604v1
PDF	http://arxiv.org/pdf/1811.04604v1.pdf
PWC	https://paperswithcode.com/paper/learning-personalized-end-to-end-goal
Repo
Framework

Quantification of Trabeculae Inside the Heart from MRI Using Fractal Analysis


Title	Quantification of Trabeculae Inside the Heart from MRI Using Fractal Analysis
Authors	Md. Kamrul Hasan, Fakrul Islam Tushar
Abstract	Left ventricular non-compaction (LVNC) is a rare cardiomyopathy (CMP) that should be considered as a possible diagnosis because of its potential complications which are heart failure, ventricular arrhythmias, and embolic events. For analysis cardiac functionality, extracting information from the Left ventricular (LV) is already a broad field of Medical Imaging. Different algorithms and strategies ranging that is semiautomated or automated has already been developed to get useful information from such a critical structure of heart. Trabeculae in the heart undergoes difference changes like solid from spongy. Due to failure of this process left ventricle non-compaction occurred. In this project, we will demonstrate the fractal dimension (FD) and manual segmentation of the Magnetic Resonance Imaging (MRI) of the heart that quantify amount of trabeculae inside the heart. The greater the value of fractal dimension inside the heart indicates the greater complex pattern of the trabeculae in the heart.
Tasks
Published	2018-09-30
URL	http://arxiv.org/abs/1810.04637v2
PDF	http://arxiv.org/pdf/1810.04637v2.pdf
PWC	https://paperswithcode.com/paper/quantification-of-trabeculae-inside-the-heart
Repo
Framework

Synchronized Detection and Recovery of Steganographic Messages with Adversarial Learning


Title	Synchronized Detection and Recovery of Steganographic Messages with Adversarial Learning
Authors	Haichao Shi, Xiao-Yu Zhang
Abstract	In this work, we mainly study the mechanism of learning the steganographic algorithm as well as combining the learning process with adversarial learning to learn a good steganographic algorithm. To handle the problem of embedding secret messages into the specific medium, we design a novel adversarial modules to learn the steganographic algorithm, and simultaneously train three modules called generator, discriminator and steganalyzer. Different from existing methods, the three modules are formalized as a game to communicate with each other. In the game, the generator and discriminator attempt to communicate with each other using secret messages hidden in an image. While the steganalyzer attempts to analyze whether there is a transmission of confidential information. We show that through unsupervised adversarial training, the adversarial model can produce robust steganographic solutions, which act like an encryption. Furthermore, we propose to utilize supervised adversarial training method to train a robust steganalyzer, which is utilized to discriminate whether an image contains secret information. Numerous experiments are conducted on publicly available dataset to demonstrate the effectiveness of the proposed method.
Tasks
Published	2018-01-31
URL	http://arxiv.org/abs/1801.10365v3
PDF	http://arxiv.org/pdf/1801.10365v3.pdf
PWC	https://paperswithcode.com/paper/synchronized-detection-and-recovery-of
Repo
Framework

Functional Sequential Treatment Allocation


Title	Functional Sequential Treatment Allocation
Authors	Anders Bredahl Kock, David Preinerstorfer, Bezirgen Veliyev
Abstract	Consider a setting in which a policy maker assigns subjects to treatments, observing each outcome before the next subject arrives. Initially, it is unknown which treatment is best. However, the sequential nature of the problem permits learning about the effectiveness of the treatments, which we measure by a functional of the associated outcome distributions, for example an inequality, welfare or poverty measure. In the present article, we evaluate assignment policies according to their regret, that is, the sum of all losses incurred due to assigning subjects to suboptimal treatments. We first study explore-then-commit (ETC) policies. These are policies, where one initially explores which treatment is of the highest quality, typically through a randomized controlled trial, and subsequently fully commits to the “inferred superior” (but potentially suboptimal) treatment. Then, we introduce and study the Functional Upper Confidence Bound (F-UCB) policy, which interweaves exploration and exploitation and is thus not of the ETC type. Our results show, in particular, that the F-UCB policy (i) performs much better than any ETC policy, and (ii) is near minimax optimal. We also show that a suitably adapted F-UCB policy is near minimax optimal under minimal assumptions when covariate information is available.
Tasks
Published	2018-12-21
URL	https://arxiv.org/abs/1812.09408v3
PDF	https://arxiv.org/pdf/1812.09408v3.pdf
PWC	https://paperswithcode.com/paper/functional-sequential-treatment-allocation
Repo
Framework

Deep Determinantal Point Processes


Title	Deep Determinantal Point Processes
Authors	Mike Gartrell, Elvis Dohmatob, Jon Alberdi
Abstract	Determinantal point processes (DPPs) have attracted significant attention as an elegant model that is able to capture the balance between quality and diversity within sets. DPPs are parameterized by a positive semi-definite kernel matrix. While DPPs have substantial expressive power, they are fundamentally limited by the parameterization of the kernel matrix and their inability to capture nonlinear interactions between items within sets. We present the deep DPP model as way to address these limitations, by using a deep feed-forward neural network to learn the kernel matrix. In addition to allowing us to capture nonlinear item interactions, the deep DPP also allows easy incorporation of item metadata into DPP learning. Since the learning target is the DPP kernel matrix, the deep DPP allows us to use existing DPP algorithms for efficient learning, sampling, and prediction. Through an evaluation on several real-world datasets, we show experimentally that the deep DPP can provide a considerable improvement in the predictive performance of DPPs, while also outperforming strong baseline models in many cases.
Tasks	Point Processes
Published	2018-11-17
URL	https://arxiv.org/abs/1811.07245v3
PDF	https://arxiv.org/pdf/1811.07245v3.pdf
PWC	https://paperswithcode.com/paper/deep-determinantal-point-processes
Repo
Framework

An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks


Title	An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks
Authors	Chirag Agarwal, Bo Dong, Dan Schonfeld, Anthony Hoogs
Abstract	Deep Neural Networks(DNN) have excessively advanced the field of computer vision by achieving state of the art performance in various vision tasks. These results are not limited to the field of vision but can also be seen in speech recognition and machine translation tasks. Recently, DNNs are found to poorly fail when tested with samples that are crafted by making imperceptible changes to the original input images. This causes a gap between the validation and adversarial performance of a DNN. An effective and generalizable robustness metric for evaluating the performance of DNN on these adversarial inputs is still missing from the literature. In this paper, we propose Noise Sensitivity Score (NSS), a metric that quantifies the performance of a DNN on a specific input under different forms of fix-directional attacks. An insightful mathematical explanation is provided for deeply understanding the proposed metric. By leveraging the NSS, we also proposed a skewness based dataset robustness metric for evaluating a DNN’s adversarial performance on a given dataset. Extensive experiments using widely used state of the art architectures along with popular classification datasets, such as MNIST, CIFAR-10, CIFAR-100, and ImageNet, are used to validate the effectiveness and generalization of our proposed metrics. Instead of simply measuring a DNN’s adversarial robustness in the input domain, as previous works, the proposed NSS is built on top of insightful mathematical understanding of the adversarial attack and gives a more explicit explanation of the robustness.
Tasks	Adversarial Attack, Machine Translation, Speech Recognition
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01477v2
PDF	http://arxiv.org/pdf/1806.01477v2.pdf
PWC	https://paperswithcode.com/paper/an-explainable-adversarial-robustness-metric
Repo
Framework