Paper Group ANR 387
Estimating Heterogeneous Consumer Preferences for Restaurants and Travel Time Using Mobile Location Data. StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks. A Novel Framework for Recurrent Neural Networks with Enhancing Information Processing and Transmission between Units. Unsupervise …
Estimating Heterogeneous Consumer Preferences for Restaurants and Travel Time Using Mobile Location Data
Title | Estimating Heterogeneous Consumer Preferences for Restaurants and Travel Time Using Mobile Location Data |
Authors | Susan Athey, David Blei, Robert Donnelly, Francisco Ruiz, Tobias Schmidt |
Abstract | This paper analyzes consumer choices over lunchtime restaurants using data from a sample of several thousand anonymous mobile phone users in the San Francisco Bay Area. The data is used to identify users’ approximate typical morning location, as well as their choices of lunchtime restaurants. We build a model where restaurants have latent characteristics (whose distribution may depend on restaurant observables, such as star ratings, food category, and price range), each user has preferences for these latent characteristics, and these preferences are heterogeneous across users. Similarly, each item has latent characteristics that describe users’ willingness to travel to the restaurant, and each user has individual-specific preferences for those latent characteristics. Thus, both users’ willingness to travel and their base utility for each restaurant vary across user-restaurant pairs. We use a Bayesian approach to estimation. To make the estimation computationally feasible, we rely on variational inference to approximate the posterior distribution, as well as stochastic gradient descent as a computational approach. Our model performs better than more standard competing models such as multinomial logit and nested logit models, in part due to the personalization of the estimates. We analyze how consumers re-allocate their demand after a restaurant closes to nearby restaurants versus more distant restaurants with similar characteristics, and we compare our predictions to actual outcomes. Finally, we show how the model can be used to analyze counterfactual questions such as what type of restaurant would attract the most consumers in a given location. |
Tasks | |
Published | 2018-01-22 |
URL | http://arxiv.org/abs/1801.07826v1 |
http://arxiv.org/pdf/1801.07826v1.pdf | |
PWC | https://paperswithcode.com/paper/estimating-heterogeneous-consumer-preferences |
Repo | |
Framework | |
StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks
Title | StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks |
Authors | Mohammad Javad Shafiee, Brendan Chwyl, Francis Li, Rongyan Chen, Michelle Karg, Christian Scharfenberger, Alexander Wong |
Abstract | The computational complexity of leveraging deep neural networks for extracting deep feature representations is a significant barrier to its widespread adoption, particularly for use in embedded devices. One particularly promising strategy to addressing the complexity issue is the notion of evolutionary synthesis of deep neural networks, which was demonstrated to successfully produce highly efficient deep neural networks while retaining modeling performance. Here, we further extend upon the evolutionary synthesis strategy for achieving efficient feature extraction via the introduction of a stress-induced evolutionary synthesis framework, where stress signals are imposed upon the synapses of a deep neural network during training to induce stress and steer the synthesis process towards the production of more efficient deep neural networks over successive generations and improved model fidelity at a greater efficiency. The proposed stress-induced evolutionary synthesis approach is evaluated on a variety of different deep neural network architectures (LeNet5, AlexNet, and YOLOv2) on different tasks (object classification and object detection) to synthesize efficient StressedNets over multiple generations. Experimental results demonstrate the efficacy of the proposed framework to synthesize StressedNets with significant improvement in network architecture efficiency (e.g., 40x for AlexNet and 33x for YOLOv2) and speed improvements (e.g., 5.5x inference speed-up for YOLOv2 on an Nvidia Tegra X1 mobile processor). |
Tasks | Object Classification, Object Detection |
Published | 2018-01-16 |
URL | http://arxiv.org/abs/1801.05387v1 |
http://arxiv.org/pdf/1801.05387v1.pdf | |
PWC | https://paperswithcode.com/paper/stressednets-efficient-feature |
Repo | |
Framework | |
A Novel Framework for Recurrent Neural Networks with Enhancing Information Processing and Transmission between Units
Title | A Novel Framework for Recurrent Neural Networks with Enhancing Information Processing and Transmission between Units |
Authors | Xi Chen, Zhihong Deng, Gehui Shen, Ting Huang |
Abstract | This paper proposes a novel framework for recurrent neural networks (RNNs) inspired by the human memory models in the field of cognitive neuroscience to enhance information processing and transmission between adjacent RNNs’ units. The proposed framework for RNNs consists of three stages that is working memory, forget, and long-term store. The first stage includes taking input data into sensory memory and transferring it to working memory for preliminary treatment. And the second stage mainly focuses on proactively forgetting the secondary information rather than the primary in the working memory. And finally, we get the long-term store normally using some kind of RNN’s unit. Our framework, which is generalized and simple, is evaluated on 6 datasets which fall into 3 different tasks, corresponding to text classification, image classification and language modelling. Experiments reveal that our framework can obviously improve the performance of traditional recurrent neural networks. And exploratory task shows the ability of our framework of correctly forgetting the secondary information. |
Tasks | Image Classification, Language Modelling, Text Classification |
Published | 2018-06-02 |
URL | http://arxiv.org/abs/1806.00628v1 |
http://arxiv.org/pdf/1806.00628v1.pdf | |
PWC | https://paperswithcode.com/paper/a-novel-framework-for-recurrent-neural |
Repo | |
Framework | |
Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss
Title | Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss |
Authors | Lipu Zhou, Jiamin Ye, Montiel Abello, Shengze Wang, Michael Kaess |
Abstract | We present a novel unsupervised learning framework for single view depth estimation using monocular videos. It is well known in 3D vision that enlarging the baseline can increase the depth estimation accuracy, and jointly optimizing a set of camera poses and landmarks is essential. In previous monocular unsupervised learning frameworks, only part of the photometric and geometric constraints within a sequence are used as supervisory signals. This may result in a short baseline and overfitting. Besides, previous works generally estimate a low resolution depth from a low resolution impute image. The low resolution depth is then interpolated to recover the original resolution. This strategy may generate large errors on object boundaries, as the depth of background and foreground are mixed to yield the high resolution depth. In this paper, we introduce a bundle adjustment framework and a super-resolution network to solve the above two problems. In bundle adjustment, depths and poses of an image sequence are jointly optimized, which increases the baseline by establishing the relationship between farther frames. The super resolution network learns to estimate a high resolution depth from a low resolution image. Additionally, we introduce the clip loss to deal with moving objects and occlusion. Experimental results on the KITTI dataset show that the proposed algorithm outperforms the state-of-the-art unsupervised methods using monocular sequences, and achieves comparable or even better result compared to unsupervised methods using stereo sequences. |
Tasks | Depth Estimation, Monocular Depth Estimation, Super-Resolution |
Published | 2018-12-08 |
URL | http://arxiv.org/abs/1812.03368v1 |
http://arxiv.org/pdf/1812.03368v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-learning-of-monocular-depth |
Repo | |
Framework | |
MADARi: A Web Interface for Joint Arabic Morphological Annotation and Spelling Correction
Title | MADARi: A Web Interface for Joint Arabic Morphological Annotation and Spelling Correction |
Authors | Ossama Obeid, Salam Khalifa, Nizar Habash, Houda Bouamor, Wajdi Zaghouani, Kemal Oflazer |
Abstract | In this paper, we introduce MADARi, a joint morphological annotation and spelling correction system for texts in Standard and Dialectal Arabic. The MADARi framework provides intuitive interfaces for annotating text and managing the annotation process of a large number of sizable documents. Morphological annotation includes indicating, for a word, in context, its baseword, clitics, part-of-speech, lemma, gloss, and dialect identification. MADARi has a suite of utilities to help with annotator productivity. For example, annotators are provided with pre-computed analyses to assist them in their task and reduce the amount of work needed to complete it. MADARi also allows annotators to query a morphological analyzer for a list of possible analyses in multiple dialects or look up previously submitted analyses. The MADARi management interface enables a lead annotator to easily manage and organize the whole annotation process remotely and concurrently. We describe the motivation, design and implementation of this interface; and we present details from a user study working with this system. |
Tasks | Spelling Correction |
Published | 2018-08-25 |
URL | http://arxiv.org/abs/1808.08392v1 |
http://arxiv.org/pdf/1808.08392v1.pdf | |
PWC | https://paperswithcode.com/paper/madari-a-web-interface-for-joint-arabic |
Repo | |
Framework | |
Impostor Networks for Fast Fine-Grained Recognition
Title | Impostor Networks for Fast Fine-Grained Recognition |
Authors | Vadim Lebedev, Artem Babenko, Victor Lempitsky |
Abstract | In this work we introduce impostor networks, an architecture that allows to perform fine-grained recognition with high accuracy and using a light-weight convolutional network, making it particularly suitable for fine-grained applications on low-power and non-GPU enabled platforms. Impostor networks compensate for the lightness of its `backend’ network by combining it with a lightweight non-parametric classifier. The combination of a convolutional network and such non-parametric classifier is trained in an end-to-end fashion. Similarly to convolutional neural networks, impostor networks can fit large-scale training datasets very well, while also being able to generalize to new data points. At the same time, the bulk of computations within impostor networks happen through nearest neighbor search in high-dimensions. Such search can be performed efficiently on a variety of architectures including standard CPUs, where deep convolutional networks are inefficient. In a series of experiments with three fine-grained datasets, we show that impostor networks are able to boost the classification accuracy of a moderate-sized convolutional network considerably at a very small computational cost. | |
Tasks | |
Published | 2018-06-13 |
URL | http://arxiv.org/abs/1806.05217v1 |
http://arxiv.org/pdf/1806.05217v1.pdf | |
PWC | https://paperswithcode.com/paper/impostor-networks-for-fast-fine-grained |
Repo | |
Framework | |
On Learning and Learned Representation by Capsule Networks
Title | On Learning and Learned Representation by Capsule Networks |
Authors | Ancheng Lin, Jun Li, Zhenyuan Ma |
Abstract | In this work, we investigate the following: 1) how the routing affects the CapsNet model fitting; 2) how the representation using capsules helps discover global structures in data distribution, and; 3) how the learned data representation adapts and generalizes to new tasks. Our investigation yielded the results some of which have been mentioned in the original paper of CapsNet, they are: 1) the routing operation determines the certainty with which a layer of capsules pass information to the layer above and the appropriate level of certainty is related to the model fitness; 2) in a designed experiment using data with a known 2D structure, capsule representations enable a more meaningful 2D manifold embedding than neurons do in a standard convolutional neural network (CNN), and; 3) compared with neurons of the standard CNN, capsules of successive layers are less coupled and more adaptive to new data distribution. |
Tasks | |
Published | 2018-10-08 |
URL | http://arxiv.org/abs/1810.04041v2 |
http://arxiv.org/pdf/1810.04041v2.pdf | |
PWC | https://paperswithcode.com/paper/on-learning-and-learned-representation-with |
Repo | |
Framework | |
Introducing Noise in Decentralized Training of Neural Networks
Title | Introducing Noise in Decentralized Training of Neural Networks |
Authors | Linara Adilova, Nathalie Paul, Peter Schlicht |
Abstract | It has been shown that injecting noise into the neural network weights during the training process leads to a better generalization of the resulting model. Noise injection in the distributed setup is a straightforward technique and it represents a promising approach to improve the locally trained models. We investigate the effects of noise injection into the neural networks during a decentralized training process. We show both theoretically and empirically that noise injection has no positive effect in expectation on linear models, though. However for non-linear neural networks we empirically show that noise injection substantially improves model quality helping to reach a generalization ability of a local model close to the serial baseline. |
Tasks | |
Published | 2018-09-27 |
URL | http://arxiv.org/abs/1809.10678v1 |
http://arxiv.org/pdf/1809.10678v1.pdf | |
PWC | https://paperswithcode.com/paper/introducing-noise-in-decentralized-training |
Repo | |
Framework | |
Divide, Denoise, and Defend against Adversarial Attacks
Title | Divide, Denoise, and Defend against Adversarial Attacks |
Authors | Seyed-Mohsen Moosavi-Dezfooli, Ashish Shrivastava, Oncel Tuzel |
Abstract | Deep neural networks, although shown to be a successful class of machine learning algorithms, are known to be extremely unstable to adversarial perturbations. Improving the robustness of neural networks against these attacks is important, especially for security-critical applications. To defend against such attacks, we propose dividing the input image into multiple patches, denoising each patch independently, and reconstructing the image, without losing significant image content. We call our method D3. This proposed defense mechanism is non-differentiable which makes it non-trivial for an adversary to apply gradient-based attacks. Moreover, we do not fine-tune the network with adversarial examples, making it more robust against unknown attacks. We present an analysis of the tradeoff between accuracy and robustness against adversarial attacks. We evaluate our method under black-box, grey-box, and white-box settings. On the ImageNet dataset, our method outperforms the state-of-the-art by 19.7% under grey-box setting, and performs comparably under black-box setting. For the white-box setting, the proposed method achieves 34.4% accuracy compared to the 0% reported in the recent works. |
Tasks | Denoising |
Published | 2018-02-19 |
URL | http://arxiv.org/abs/1802.06806v2 |
http://arxiv.org/pdf/1802.06806v2.pdf | |
PWC | https://paperswithcode.com/paper/divide-denoise-and-defend-against-adversarial |
Repo | |
Framework | |
Probabilistic Warnings in National Security Crises: Pearl Harbor Revisited
Title | Probabilistic Warnings in National Security Crises: Pearl Harbor Revisited |
Authors | David M. Blum, M. Elisabeth Pate-Cornell |
Abstract | Imagine a situation where a group of adversaries is preparing an attack on the United States or U.S. interests. An intelligence analyst has observed some signals, but the situation is rapidly changing. The analyst faces the decision to alert a principal decision maker that an attack is imminent, or to wait until more is known about the situation. This warning decision is based on the analyst’s observation and evaluation of signals, independent or correlated, and on her updating of the prior probabilities of possible scenarios and their outcomes. The warning decision also depends on the analyst’s assessment of the crisis’ dynamics and perception of the preferences of the principal decision maker, as well as the lead time needed for an appropriate response. This article presents a model to support this analyst’s dynamic warning decision. As with most problems involving warning, the key is to manage the tradeoffs between false positives and false negatives given the probabilities and the consequences of intelligence failures of both types. The model is illustrated by revisiting the case of the attack on Pearl Harbor in December 1941. It shows that the radio silence of the Japanese fleet carried considerable information (Sir Arthur Conan Doyle’s “dog in the night” problem), which was misinterpreted at the time. Even though the probabilities of different attacks were relatively low, their consequences were such that the Bayesian dynamic reasoning described here may have provided valuable information to key decision makers. |
Tasks | |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.04887v1 |
http://arxiv.org/pdf/1802.04887v1.pdf | |
PWC | https://paperswithcode.com/paper/probabilistic-warnings-in-national-security |
Repo | |
Framework | |
UnDEMoN 2.0: Improved Depth and Ego Motion Estimation through Deep Image Sampling
Title | UnDEMoN 2.0: Improved Depth and Ego Motion Estimation through Deep Image Sampling |
Authors | Madhu Babu V, Swagat Kumar, Anima Majumder, Kaushik Das |
Abstract | In this paper, we provide an improved version of UnDEMoN model for depth and ego motion estimation from monocular images. The improvement is achieved by combining the standard bi-linear sampler with a deep network based image sampling model (DIS-NET) to provide better image reconstruction capabilities on which the depth estimation accuracy depends in un-supervised learning models. While DIS-NET provides higher order regression and larger input search space, the bi-linear sampler provides geometric constraints necessary for reducing the size of the solution space for an ill-posed problem of this kind. This combination is shown to provide significant improvement in depth and pose estimation accuracy outperforming all existing state-of-the-art methods in this category. In addition, the modified network uses far less number of tunable parameters making it one of the lightest deep network model for depth estimation. The proposed model is labeled as “UnDEMoN 2.0” indicating an improvement over the existing UnDEMoN model. The efficacy of the proposed model is demonstrated through rigorous experimental analysis on the standard KITTI dataset. |
Tasks | Depth Estimation, Image Reconstruction, Motion Estimation, Pose Estimation |
Published | 2018-11-27 |
URL | http://arxiv.org/abs/1811.10884v1 |
http://arxiv.org/pdf/1811.10884v1.pdf | |
PWC | https://paperswithcode.com/paper/undemon-20-improved-depth-and-ego-motion |
Repo | |
Framework | |
Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data
Title | Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data |
Authors | Stefan Schneider, Graham W. Taylor, Stefan S. Linquist, Stefan C. Kremer |
Abstract | The ability of a researcher to re-identify (re-ID) an individual animal upon re-encounter is fundamental for addressing a broad range of questions in the study of ecosystem function, community and population dynamics, and behavioural ecology. In this review, we describe a brief history of camera traps for re-ID, present a collection of computer vision feature engineering methodologies previously used for animal re-ID, provide an introduction to the underlying mechanisms of deep learning relevant to animal re-ID, highlight the success of deep learning methods for human re-ID, describe the few ecological studies currently utilizing deep learning for camera trap analyses, and our predictions for near future methodologies based on the rapid development of deep learning methods. By utilizing novel deep learning methods for object detection and similarity comparisons, ecologists can extract animals from an image/video data and train deep learning classifiers to re-ID animal individuals beyond the capabilities of a human observer. This methodology will allow ecologists with camera/video trap data to re-identify individuals that exit and re-enter the camera frame. Our expectation is that this is just the beginning of a major trend that could stand to revolutionize the analysis of camera trap data and, ultimately, our approach to animal ecology. |
Tasks | Feature Engineering, Object Detection |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07749v1 |
http://arxiv.org/pdf/1811.07749v1.pdf | |
PWC | https://paperswithcode.com/paper/past-present-and-future-approaches-using |
Repo | |
Framework | |
Conditional probability calculation using restricted Boltzmann machine with application to system identification
Title | Conditional probability calculation using restricted Boltzmann machine with application to system identification |
Authors | Erick de la Rosa, Wen Yu |
Abstract | There are many advantages to use probability method for nonlinear system identification, such as the noises and outliers in the data set do not affect the probability models significantly; the input features can be extracted in probability forms. The biggest obstacle of the probability model is the probability distributions are not easy to be obtained. In this paper, we form the nonlinear system identification into solving the conditional probability. Then we modify the restricted Boltzmann machine (RBM), such that the joint probability, input distribution, and the conditional probability can be calculated by the RBM training. Binary encoding and continue valued methods are discussed. The universal approximation analysis for the conditional probability based modelling is proposed. We use two benchmark nonlinear systems to compare our probability modelling method with the other black-box modeling methods. The results show that this novel method is much better when there are big noises and the system dynamics are complex. |
Tasks | |
Published | 2018-06-07 |
URL | http://arxiv.org/abs/1806.02499v1 |
http://arxiv.org/pdf/1806.02499v1.pdf | |
PWC | https://paperswithcode.com/paper/conditional-probability-calculation-using |
Repo | |
Framework | |
Towards Global Explanations for Credit Risk Scoring
Title | Towards Global Explanations for Credit Risk Scoring |
Authors | Irene Unceta, Jordi Nin, Oriol Pujol |
Abstract | In this paper we propose a method to obtain global explanations for trained black-box classifiers by sampling their decision function to learn alternative interpretable models. The envisaged approach provides a unified solution to approximate non-linear decision boundaries with simpler classifiers while retaining the original classification accuracy. We use a private residential mortgage default dataset as a use case to illustrate the feasibility of this approach to ensure the decomposability of attributes during pre-processing. |
Tasks | |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07698v3 |
http://arxiv.org/pdf/1811.07698v3.pdf | |
PWC | https://paperswithcode.com/paper/towards-global-explanations-for-credit-risk |
Repo | |
Framework | |
Learning Material-Aware Local Descriptors for 3D Shapes
Title | Learning Material-Aware Local Descriptors for 3D Shapes |
Authors | Hubert Lin, Melinos Averkiou, Evangelos Kalogerakis, Balazs Kovacs, Siddhant Ranade, Vladimir G. Kim, Siddhartha Chaudhuri, Kavita Bala |
Abstract | Material understanding is critical for design, geometric modeling, and analysis of functional objects. We enable material-aware 3D shape analysis by employing a projective convolutional neural network architecture to learn material- aware descriptors from view-based representations of 3D points for point-wise material classification or material- aware retrieval. Unfortunately, only a small fraction of shapes in 3D repositories are labeled with physical mate- rials, posing a challenge for learning methods. To address this challenge, we crowdsource a dataset of 3080 3D shapes with part-wise material labels. We focus on furniture models which exhibit interesting structure and material variabil- ity. In addition, we also contribute a high-quality expert- labeled benchmark of 115 shapes from Herman-Miller and IKEA for evaluation. We further apply a mesh-aware con- ditional random field, which incorporates rotational and reflective symmetries, to smooth our local material predic- tions across neighboring surface patches. We demonstrate the effectiveness of our learned descriptors for automatic texturing, material-aware retrieval, and physical simulation. The dataset and code will be publicly available. |
Tasks | 3D Shape Analysis, Material Classification |
Published | 2018-10-20 |
URL | http://arxiv.org/abs/1810.08729v1 |
http://arxiv.org/pdf/1810.08729v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-material-aware-local-descriptors-for |
Repo | |
Framework | |