Paper Group ANR 579
Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer. Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning. Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in …
Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer
| Title | Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer |
| Authors | Nicolás Cruz, Kenzo Lobos-Tsunekawa, Javier Ruiz-del-Solar |
| Abstract | The main goal of this paper is to analyze the general problem of using Convolutional Neural Networks (CNNs) in robots with limited computational capabilities, and to propose general design guidelines for their use. In addition, two different CNN based NAO robot detectors that are able to run in real-time while playing soccer are proposed. One of the detectors is based on the XNOR-Net and the other on the SqueezeNet. Each detector is able to process a robot object-proposal in ~1ms, with an average number of 1.5 proposals per frame obtained by the upper camera of the NAO. The obtained detection rate is ~97%. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06702v1 |
| http://arxiv.org/pdf/1706.06702v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-convolutional-neural-networks-in-robots |
| Repo | |
| Framework | |
Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning
| Title | Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning |
| Authors | Jaeyoon Yoo, Heonseok Ha, Jihun Yi, Jongha Ryu, Chanju Kim, Jung-Woo Ha, Young-Han Kim, Sungroh Yoon |
| Abstract | Recommender systems aim to find an accurate and efficient mapping from historic data of user-preferred items to a new item that is to be liked by a user. Towards this goal, energy-based sequence generative adversarial nets (EB-SeqGANs) are adopted for recommendation by learning a generative model for the time series of user-preferred items. By recasting the energy function as the feature function, the proposed EB-SeqGANs is interpreted as an instance of maximum-entropy imitation learning. |
| Tasks | Imitation Learning, Recommendation Systems, Time Series |
| Published | 2017-06-28 |
| URL | http://arxiv.org/abs/1706.09200v1 |
| http://arxiv.org/pdf/1706.09200v1.pdf | |
| PWC | https://paperswithcode.com/paper/energy-based-sequence-gans-for-recommendation |
| Repo | |
| Framework | |
Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean
| Title | Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean |
| Authors | Koushik Nagasubramanian, Sarah Jones, Soumik Sarkar, Asheesh K. Singh, Arti Singh, Baskar Ganapathysubramanian |
| Abstract | Charcoal rot is a fungal disease that thrives in warm dry conditions and affects the yield of soybeans and other important agronomic crops worldwide. There is a need for robust, automatic and consistent early detection and quantification of disease symptoms which are important in breeding programs for the development of improved cultivars and in crop production for the implementation of disease control measures for yield protection. Current methods of plant disease phenotyping are predominantly visual and hence are slow and prone to human error and variation. There has been increasing interest in hyperspectral imaging applications for early detection of disease symptoms. However, the high dimensionality of hyperspectral data makes it very important to have an efficient analysis pipeline in place for the identification of disease so that effective crop management decisions can be made. The focus of this work is to determine the minimal number of most effective hyperspectral bands that can distinguish between healthy and diseased specimens early in the growing season. Healthy and diseased hyperspectral data cubes were captured at 3, 6, 9, 12, and 15 days after inoculation. We utilized inoculated and control specimens from 4 different genotypes. Each hyperspectral image was captured at 240 different wavelengths in the range of 383 to 1032 nm. We used a combination of genetic algorithm as an optimizer and support vector machines as a classifier for identification of maximally effective band combinations. A binary classification between healthy and infected samples using six selected band combinations obtained a classification accuracy of 97% and a F1 score of 0.97 for the infected class. The results demonstrated that these carefully chosen bands are more informative than RGB images, and could be used in a multispectral camera for remote identification of charcoal rot infection in soybean. |
| Tasks | |
| Published | 2017-10-12 |
| URL | http://arxiv.org/abs/1710.04681v1 |
| http://arxiv.org/pdf/1710.04681v1.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-band-selection-using-genetic |
| Repo | |
| Framework | |
Rethink ReLU to Training Better CNNs
| Title | Rethink ReLU to Training Better CNNs |
| Authors | Gangming Zhao, Zhaoxiang Zhang, He Guan, Peng Tang, Jingdong Wang |
| Abstract | Most of convolutional neural networks share the same characteristic: each convolutional layer is followed by a nonlinear activation layer where Rectified Linear Unit (ReLU) is the most widely used. In this paper, we argue that the designed structure with the equal ratio between these two layers may not be the best choice since it could result in the poor generalization ability. Thus, we try to investigate a more suitable method on using ReLU to explore the better network architectures. Specifically, we propose a proportional module to keep the ratio between convolution and ReLU amount to be N:M (N>M). The proportional module can be applied in almost all networks with no extra computational cost to improve the performance. Comprehensive experimental results indicate that the proposed method achieves better performance on different benchmarks with different network architectures, thus verify the superiority of our work. |
| Tasks | |
| Published | 2017-09-19 |
| URL | http://arxiv.org/abs/1709.06247v2 |
| http://arxiv.org/pdf/1709.06247v2.pdf | |
| PWC | https://paperswithcode.com/paper/rethink-relu-to-training-better-cnns |
| Repo | |
| Framework | |
Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization
| Title | Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization |
| Authors | Izhar Wallach, Abraham Heifets |
| Abstract | Undetected overfitting can occur when there are significant redundancies between training and validation data. We describe AVE, a new measure of training-validation redundancy for ligand-based classification problems that accounts for the similarity amongst inactive molecules as well as active. We investigated seven widely-used benchmarks for virtual screening and classification, and show that the amount of AVE bias strongly correlates with the performance of ligand-based predictive methods irrespective of the predicted property, chemical fingerprint, similarity measure, or previously-applied unbiasing techniques. Therefore, it may be that the previously-reported performance of most ligand-based methods can be explained by overfitting to benchmarks rather than good prospective accuracy. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06619v2 |
| http://arxiv.org/pdf/1706.06619v2.pdf | |
| PWC | https://paperswithcode.com/paper/most-ligand-based-classification-benchmarks |
| Repo | |
| Framework | |
On the Semantics and Complexity of Probabilistic Logic Programs
| Title | On the Semantics and Complexity of Probabilistic Logic Programs |
| Authors | Fabio Gagliardi Cozman, Denis Deratani Mauá |
| Abstract | We examine the meaning and the complexity of probabilistic logic programs that consist of a set of rules and a set of independent probabilistic facts (that is, programs based on Sato’s distribution semantics). We focus on two semantics, respectively based on stable and on well-founded models. We show that the semantics based on stable models (referred to as the “credal semantics”) produces sets of probability models that dominate infinitely monotone Choquet capacities, we describe several useful consequences of this result. We then examine the complexity of inference with probabilistic logic programs. We distinguish between the complexity of inference when a probabilistic program and a query are given (the inferential complexity), and the complexity of inference when the probabilistic program is fixed and the query is given (the query complexity, akin to data complexity as used in database theory). We obtain results on the inferential and query complexity for acyclic, stratified, and cyclic propositional and relational programs, complexity reaches various levels of the counting hierarchy and even exponential levels. |
| Tasks | |
| Published | 2017-01-31 |
| URL | http://arxiv.org/abs/1701.09000v1 |
| http://arxiv.org/pdf/1701.09000v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-semantics-and-complexity-of |
| Repo | |
| Framework | |
Flower Categorization using Deep Convolutional Neural Networks
| Title | Flower Categorization using Deep Convolutional Neural Networks |
| Authors | Ayesha Gurnani, Viraj Mavani, Vandit Gajjar, Yash Khandhediya |
| Abstract | We have developed a deep learning network for classification of different flowers. For this, we have used Visual Geometry Group’s 102 category flower dataset having 8189 images of 102 different flowers from University of Oxford. The method is basically divided into two parts; Image segmentation and classification. We have compared the performance of two different Convolutional Neural Network architectures GoogLeNet and AlexNet for classification purpose. By keeping the hyper parameters same for both architectures, we have found that the top 1 and top 5 accuracies of GoogLeNet are 47.15% and 69.17% respectively whereas the top 1 and top 5 accuracies of AlexNet are 43.39% and 68.68% respectively. These results are extremely good when compared to random classification accuracy of 0.98%. This method for classification of flowers can be implemented in real time applications and can be used to help botanists for their research as well as camping enthusiasts. |
| Tasks | Semantic Segmentation |
| Published | 2017-08-12 |
| URL | http://arxiv.org/abs/1708.03763v2 |
| http://arxiv.org/pdf/1708.03763v2.pdf | |
| PWC | https://paperswithcode.com/paper/flower-categorization-using-deep |
| Repo | |
| Framework | |
Exploring Cross-Domain Data Dependencies for Smart Homes to Improve Energy Efficiency
| Title | Exploring Cross-Domain Data Dependencies for Smart Homes to Improve Energy Efficiency |
| Authors | Shamaila Iram, Terrence Fernando, May Bassanino |
| Abstract | Over the past decade, the idea of smart homes has been conceived as a potential solution to counter energy crises or to at least mitigate its intensive destructive consequences in the residential building sector. |
| Tasks | |
| Published | 2017-10-11 |
| URL | http://arxiv.org/abs/1710.03978v1 |
| http://arxiv.org/pdf/1710.03978v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-cross-domain-data-dependencies-for |
| Repo | |
| Framework | |
Alternative Semantic Representations for Zero-Shot Human Action Recognition
| Title | Alternative Semantic Representations for Zero-Shot Human Action Recognition |
| Authors | Qian Wang, Ke Chen |
| Abstract | A proper semantic representation for encoding side information is key to the success of zero-shot learning. In this paper, we explore two alternative semantic representations especially for zero-shot human action recognition: textual descriptions of human actions and deep features extracted from still images relevant to human actions. Such side information are accessible on Web with little cost, which paves a new way in gaining side information for large-scale zero-shot human action recognition. We investigate different encoding methods to generate semantic representations for human actions from such side information. Based on our zero-shot visual recognition method, we conducted experiments on UCF101 and HMDB51 to evaluate two proposed semantic representations . The results suggest that our proposed text- and image-based semantic representations outperform traditional attributes and word vectors considerably for zero-shot human action recognition. In particular, the image-based semantic representations yield the favourable performance even though the representation is extracted from a small number of images per class. |
| Tasks | Temporal Action Localization, Zero-Shot Learning |
| Published | 2017-06-28 |
| URL | http://arxiv.org/abs/1706.09317v1 |
| http://arxiv.org/pdf/1706.09317v1.pdf | |
| PWC | https://paperswithcode.com/paper/alternative-semantic-representations-for-zero |
| Repo | |
| Framework | |
WSNet: Compact and Efficient Networks Through Weight Sampling
| Title | WSNet: Compact and Efficient Networks Through Weight Sampling |
| Authors | Xiaojie Jin, Yingzhen Yang, Ning Xu, Jianchao Yang, Nebojsa Jojic, Jiashi Feng, Shuicheng Yan |
| Abstract | We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via ad hoc processing such as model pruning or filter factorization. Alternatively, WSNet proposes learning model parameters by sampling from a compact set of learnable parameters, which naturally enforces {parameter sharing} throughout the learning process. We demonstrate that such a novel weight sampling approach (and induced WSNet) promotes both weights and computation sharing favorably. By employing this method, we can more efficiently learn much smaller networks with competitive performance compared to baseline networks with equal numbers of convolution filters. Specifically, we consider learning compact and efficient 1D convolutional neural networks for audio classification. Extensive experiments on multiple audio classification datasets verify the effectiveness of WSNet. Combined with weight quantization, the resulted models are up to 180 times smaller and theoretically up to 16 times faster than the well-established baselines, without noticeable performance drop. |
| Tasks | Audio Classification, Quantization |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10067v3 |
| http://arxiv.org/pdf/1711.10067v3.pdf | |
| PWC | https://paperswithcode.com/paper/wsnet-compact-and-efficient-networks-through |
| Repo | |
| Framework | |
Low Dose CT Image Reconstruction With Learned Sparsifying Transform
| Title | Low Dose CT Image Reconstruction With Learned Sparsifying Transform |
| Authors | Xuehang Zheng, Zening Lu, Saiprasad Ravishankar, Yong Long, Jeffrey A. Fessler |
| Abstract | A major challenge in computed tomography (CT) is to reduce X-ray dose to a low or even ultra-low level while maintaining the high quality of reconstructed images. We propose a new method for CT reconstruction that combines penalized weighted-least squares reconstruction (PWLS) with regularization based on a sparsifying transform (PWLS-ST) learned from a dataset of numerous CT images. We adopt an alternating algorithm to optimize the PWLS-ST cost function that alternates between a CT image update step and a sparse coding step. We adopt a relaxed linearized augmented Lagrangian method with ordered-subsets (relaxed OS-LALM) to accelerate the CT image update step by reducing the number of forward and backward projections. Numerical experiments on the XCAT phantom show that for low dose levels, the proposed PWLS-ST method dramatically improves the quality of reconstructed images compared to PWLS reconstruction with a nonadaptive edge-preserving regularizer (PWLS-EP). |
| Tasks | Computed Tomography (CT), Image Reconstruction |
| Published | 2017-07-10 |
| URL | http://arxiv.org/abs/1707.02914v1 |
| http://arxiv.org/pdf/1707.02914v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-dose-ct-image-reconstruction-with-learned |
| Repo | |
| Framework | |
House Price Prediction Using LSTM
| Title | House Price Prediction Using LSTM |
| Authors | Xiaochen Chen, Lai Wei, Jiaxin Xu |
| Abstract | In this paper, we use the house price data ranging from January 2004 to October 2016 to predict the average house price of November and December in 2016 for each district in Beijing, Shanghai, Guangzhou and Shenzhen. We apply Autoregressive Integrated Moving Average model to generate the baseline while LSTM networks to build prediction model. These algorithms are compared in terms of Mean Squared Error. The result shows that the LSTM model has excellent properties with respect to predict time series. Also, stateful LSTM networks and stack LSTM networks are employed to further study the improvement of accuracy of the house prediction model. |
| Tasks | Time Series |
| Published | 2017-09-25 |
| URL | http://arxiv.org/abs/1709.08432v1 |
| http://arxiv.org/pdf/1709.08432v1.pdf | |
| PWC | https://paperswithcode.com/paper/house-price-prediction-using-lstm |
| Repo | |
| Framework | |
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
| Title | Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors |
| Authors | Gintare Karolina Dziugaite, Daniel M. Roy |
| Abstract | We show that Entropy-SGD (Chaudhari et al., 2017), when viewed as a learning algorithm, optimizes a PAC-Bayes bound on the risk of a Gibbs (posterior) classifier, i.e., a randomized classifier obtained by a risk-sensitive perturbation of the weights of a learned classifier. Entropy-SGD works by optimizing the bound’s prior, violating the hypothesis of the PAC-Bayes theorem that the prior is chosen independently of the data. Indeed, available implementations of Entropy-SGD rapidly obtain zero training error on random labels and the same holds of the Gibbs posterior. In order to obtain a valid generalization bound, we rely on a result showing that data-dependent priors obtained by stochastic gradient Langevin dynamics (SGLD) yield valid PAC-Bayes bounds provided the target distribution of SGLD is {\epsilon}-differentially private. We observe that test error on MNIST and CIFAR10 falls within the (empirically nonvacuous) risk bounds computed under the assumption that SGLD reaches stationarity. In particular, Entropy-SGLD can be configured to yield relatively tight generalization bounds and still fit real labels, although these same settings do not obtain state-of-the-art performance. |
| Tasks | |
| Published | 2017-12-26 |
| URL | http://arxiv.org/abs/1712.09376v3 |
| http://arxiv.org/pdf/1712.09376v3.pdf | |
| PWC | https://paperswithcode.com/paper/entropy-sgd-optimizes-the-prior-of-a-pac |
| Repo | |
| Framework | |
Recurrent Neural Networks as Weighted Language Recognizers
| Title | Recurrent Neural Networks as Weighted Language Recognizers |
| Authors | Yining Chen, Sorcha Gilroy, Andreas Maletti, Jonathan May, Kevin Knight |
| Abstract | We investigate the computational complexity of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages. We focus on the single-layer, ReLU-activation, rational-weight RNNs with softmax, which are commonly used in natural language processing applications. We show that most problems for such RNNs are undecidable, including consistency, equivalence, minimization, and the determination of the highest-weighted string. However, for consistent RNNs the last problem becomes decidable, although the solution length can surpass all computable bounds. If additionally the string is limited to polynomial length, the problem becomes NP-complete and APX-hard. In summary, this shows that approximations and heuristic algorithms are necessary in practical applications of those RNNs. |
| Tasks | |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05408v2 |
| http://arxiv.org/pdf/1711.05408v2.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-neural-networks-as-weighted |
| Repo | |
| Framework | |
School bus routing by maximizing trip compatibility
| Title | School bus routing by maximizing trip compatibility |
| Authors | Ali Shafahi, Zhongxiang Wang, Ali Haghani |
| Abstract | School bus planning is usually divided into routing and scheduling due to the complexity of solving them concurrently. However, the separation between these two steps may lead to worse solutions with higher overall costs than that from solving them together. When finding the minimal number of trips in the routing problem, neglecting the importance of trip compatibility may increase the number of buses actually needed in the scheduling problem. This paper proposes a new formulation for the multi-school homogeneous fleet routing problem that maximizes trip compatibility while minimizing total travel time. This incorporates the trip compatibility for the scheduling problem in the routing problem. Since the problem is inherently just a routing problem, finding a good solution is not cumbersome. To compare the performance of the model with traditional routing problems, we generate eight mid-size data sets. Through importing the generated trips of the routing problems into the bus scheduling (blocking) problem, it is shown that the proposed model uses up to 13% fewer buses than the common traditional routing models. |
| Tasks | |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00530v2 |
| http://arxiv.org/pdf/1711.00530v2.pdf | |
| PWC | https://paperswithcode.com/paper/school-bus-routing-by-maximizing-trip |
| Repo | |
| Framework | |
