Paper Group ANR 977
Compressed Sensing with Adversarial Sparse Noise via L1 Regression. A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels. Systems of bounded rational agents with information-theoretic constraints. Looking at Hands in Autonomous Vehicles: A ConvNet Approach using Part Affinity Fields. Adding One Neuron Can Eliminate All Bad Local Minim …
Compressed Sensing with Adversarial Sparse Noise via L1 Regression
Title | Compressed Sensing with Adversarial Sparse Noise via L1 Regression |
Authors | Sushrut Karmalkar, Eric Price |
Abstract | We present a simple and effective algorithm for the problem of \emph{sparse robust linear regression}. In this problem, one would like to estimate a sparse vector $w^* \in \mathbb{R}^n$ from linear measurements corrupted by sparse noise that can arbitrarily change an adversarially chosen $\eta$ fraction of measured responses $y$, as well as introduce bounded norm noise to the responses. For Gaussian measurements, we show that a simple algorithm based on L1 regression can successfully estimate $w^*$ for any $\eta < \eta_0 \approx 0.239$, and that this threshold is tight for the algorithm. The number of measurements required by the algorithm is $O(k \log \frac{n}{k})$ for $k$-sparse estimation, which is within constant factors of the number needed without any sparse noise. Of the three properties we show—the ability to estimate sparse, as well as dense, $w^*$; the tolerance of a large constant fraction of outliers; and tolerance of adversarial rather than distributional (e.g., Gaussian) dense noise—to the best of our knowledge, no previous result achieved more than two. |
Tasks | |
Published | 2018-09-21 |
URL | http://arxiv.org/abs/1809.08055v4 |
http://arxiv.org/pdf/1809.08055v4.pdf | |
PWC | https://paperswithcode.com/paper/compressed-sensing-with-adversarial-sparse |
Repo | |
Framework | |
A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels
Title | A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels |
Authors | Yifan Ding, Liqiang Wang, Deliang Fan, Boqing Gong |
Abstract | The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dateset. On the contrary, it is fairly convenient, fast, and cheap to collect training images from the Web along with their noisy labels. This signifies the need of alternative approaches to training deep neural networks using such noisy labels. Existing methods tackling this problem either try to identify and correct the wrong labels or reweigh the data terms in the loss function according to the inferred noisy rates. Both strategies inevitably incur errors for some of the data points. In this paper, we contend that it is actually better to ignore the labels of some of the data points than to keep them if the labels are incorrect, especially when the noisy rate is high. After all, the wrong labels could mislead a neural network to a bad local optimum. We suggest a two-stage framework for the learning from noisy labels. In the first stage, we identify a small portion of images from the noisy training set of which the labels are correct with a high probability. The noisy labels of the other images are ignored. In the second stage, we train a deep neural network in a semi-supervised manner. This framework effectively takes advantage of the whole training set and yet only a portion of its labels that are most likely correct. Experiments on three datasets verify the effectiveness of our approach especially when the noisy rate is high. |
Tasks | |
Published | 2018-02-08 |
URL | http://arxiv.org/abs/1802.02679v3 |
http://arxiv.org/pdf/1802.02679v3.pdf | |
PWC | https://paperswithcode.com/paper/a-semi-supervised-two-stage-approach-to |
Repo | |
Framework | |
Systems of bounded rational agents with information-theoretic constraints
Title | Systems of bounded rational agents with information-theoretic constraints |
Authors | Sebastian Gottwald, Daniel A. Braun |
Abstract | Specialization and hierarchical organization are important features of efficient collaboration in economical, artificial, and biological systems. Here, we investigate the hypothesis that both features can be explained by the fact that each entity of such a system is limited in a certain way. We propose an information-theoretic approach based on a Free Energy principle, in order to computationally analyze systems of bounded rational agents that deal with such limitations optimally. We find that specialization allows to focus on fewer tasks, thus leading to a more efficient execution, but in turn requires coordination in hierarchical structures of specialized experts and coordinating units. Our results suggest that hierarchical architectures of specialized units at lower levels that are coordinated by units at higher levels are optimal, given that each unit’s information-processing capability is limited and conforms to constraints on complexity costs. |
Tasks | |
Published | 2018-09-16 |
URL | http://arxiv.org/abs/1809.05897v1 |
http://arxiv.org/pdf/1809.05897v1.pdf | |
PWC | https://paperswithcode.com/paper/systems-of-bounded-rational-agents-with |
Repo | |
Framework | |
Looking at Hands in Autonomous Vehicles: A ConvNet Approach using Part Affinity Fields
Title | Looking at Hands in Autonomous Vehicles: A ConvNet Approach using Part Affinity Fields |
Authors | Kevan Yuen, Mohan M. Trivedi |
Abstract | In the context of autonomous driving, where humans may need to take over in the event where the computer may issue a takeover request, a key step towards driving safety is the monitoring of the hands to ensure the driver is ready for such a request. This work, focuses on the first step of this process, which is to locate the hands. Such a system must work in real-time and under varying harsh lighting conditions. This paper introduces a fast ConvNet approach, based on the work of original work of OpenPose for full body joint estimation. The network is modified with fewer parameters and retrained using our own day-time naturalistic autonomous driving dataset to estimate joint and affinity heatmaps for driver & passenger’s wrist and elbows, for a total of 8 joint classes and part affinity fields between each wrist-elbow pair. The approach runs real-time on real-world data at 40 fps on multiple drivers and passengers. The system is extensively evaluated both quantitatively and qualitatively, showing at least 95% detection performance on joint localization and arm-angle estimation. |
Tasks | Autonomous Driving, Autonomous Vehicles |
Published | 2018-04-03 |
URL | http://arxiv.org/abs/1804.01176v1 |
http://arxiv.org/pdf/1804.01176v1.pdf | |
PWC | https://paperswithcode.com/paper/looking-at-hands-in-autonomous-vehicles-a |
Repo | |
Framework | |
Adding One Neuron Can Eliminate All Bad Local Minima
Title | Adding One Neuron Can Eliminate All Bad Local Minima |
Authors | Shiyu Liang, Ruoyu Sun, Jason D. Lee, R. Srikant |
Abstract | One of the main difficulties in analyzing neural networks is the non-convexity of the loss function which may have many bad local minima. In this paper, we study the landscape of neural networks for binary classification tasks. Under mild assumptions, we prove that after adding one special neuron with a skip connection to the output, or one special neuron per layer, every local minimum is a global minimum. |
Tasks | |
Published | 2018-05-22 |
URL | http://arxiv.org/abs/1805.08671v1 |
http://arxiv.org/pdf/1805.08671v1.pdf | |
PWC | https://paperswithcode.com/paper/adding-one-neuron-can-eliminate-all-bad-local |
Repo | |
Framework | |
Modeling Dengue Vector Population Using Remotely Sensed Data and Machine Learning
Title | Modeling Dengue Vector Population Using Remotely Sensed Data and Machine Learning |
Authors | J. M. Scavuzzo, F. Trucco, M. Espinosa, C. B. Tauro, M. Abril, C. M. Scavuzzo, A. C. Frery |
Abstract | Mosquitoes are vectors of many human diseases. In particular, Aedes \ae gypti (Linnaeus) is the main vector for Chikungunya, Dengue, and Zika viruses in Latin America and it represents a global threat. Public health policies that aim at combating this vector require dependable and timely information, which is usually expensive to obtain with field campaigns. For this reason, several efforts have been done to use remote sensing due to its reduced cost. The present work includes the temporal modeling of the oviposition activity (measured weekly on 50 ovitraps in a north Argentinean city) of Aedes \ae gypti (Linnaeus), based on time series of data extracted from operational earth observation satellite images. We use are NDVI, NDWI, LST night, LST day and TRMM-GPM rain from 2012 to 2016 as predictive variables. In contrast to previous works which use linear models, we employ Machine Learning techniques using completely accessible open source toolkits. These models have the advantages of being non-parametric and capable of describing nonlinear relationships between variables. Specifically, in addition to two linear approaches, we assess a Support Vector Machine, an Artificial Neural Networks, a K-nearest neighbors and a Decision Tree Regressor. Considerations are made on parameter tuning and the validation and training approach. The results are compared to linear models used in previous works with similar data sets for generating temporal predictive models. These new tools perform better than linear approaches, in particular Nearest Neighbor Regression (KNNR) performs the best. These results provide better alternatives to be implemented operatively on the Argentine geospatial Risk system that is running since 2012. |
Tasks | Time Series |
Published | 2018-05-04 |
URL | http://arxiv.org/abs/1805.02590v1 |
http://arxiv.org/pdf/1805.02590v1.pdf | |
PWC | https://paperswithcode.com/paper/modeling-dengue-vector-population-using |
Repo | |
Framework | |
Progressive Neural Networks for Image Classification
Title | Progressive Neural Networks for Image Classification |
Authors | Zhi Zhang, Guanghan Ning, Yigang Cen, Yang Li, Zhiqun Zhao, Hao Sun, Zhihai He |
Abstract | The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images. However, in practice, it is highly desirable to establish a progressive structure for deep neural networks which is able to adapt its inference process and complexity for images with different visual recognition complexity. In this work, we develop a multi-stage progressive structure with integrated confidence analysis and decision policy learning for deep neural networks. This new framework consists of a set of network units to be activated in a sequential manner with progressively increased complexity and visual recognition power. Our extensive experimental results on the CIFAR-10 and ImageNet datasets demonstrate that the proposed progressive deep neural network is able to obtain more than 10 fold complexity scalability while achieving the state-of-the-art performance using a single network model satisfying different complexity-accuracy requirements. |
Tasks | Image Classification |
Published | 2018-04-25 |
URL | http://arxiv.org/abs/1804.09803v1 |
http://arxiv.org/pdf/1804.09803v1.pdf | |
PWC | https://paperswithcode.com/paper/progressive-neural-networks-for-image |
Repo | |
Framework | |
Automated Verification of Neural Networks: Advances, Challenges and Perspectives
Title | Automated Verification of Neural Networks: Advances, Challenges and Perspectives |
Authors | Francesco Leofante, Nina Narodytska, Luca Pulina, Armando Tacchella |
Abstract | Neural networks are one of the most investigated and widely used techniques in Machine Learning. In spite of their success, they still find limited application in safety- and security-related contexts, wherein assurance about networks’ performances must be provided. In the recent past, automated reasoning techniques have been proposed by several researchers to close the gap between neural networks and applications requiring formal guarantees about their behavior. In this work, we propose a primer of such techniques and a comprehensive categorization of existing approaches for the automated verification of neural networks. A discussion about current limitations and directions for future investigation is provided to foster research on this topic at the crossroads of Machine Learning and Automated Reasoning. |
Tasks | |
Published | 2018-05-25 |
URL | http://arxiv.org/abs/1805.09938v1 |
http://arxiv.org/pdf/1805.09938v1.pdf | |
PWC | https://paperswithcode.com/paper/automated-verification-of-neural-networks |
Repo | |
Framework | |
Classification of Protein Crystallization X-Ray Images Using Major Convolutional Neural Network Architectures
Title | Classification of Protein Crystallization X-Ray Images Using Major Convolutional Neural Network Architectures |
Authors | Soheil Ghafurian, Peter Orth, Corey Strickland, Hua Su, Sangita Patel, Steven Soisson, Belma Dogdas |
Abstract | The generation of protein crystals is necessary for the study of protein molecular function and structure. This is done empirically by processing large numbers of crystallization trials and inspecting them regularly in search of those with forming crystals. To avoid missing the hard-gained crystals, this visual inspection of the trial X-ray images is done manually as opposed to the existing less accurate machine learning methods. To achieve higher accuracy for automation, we applied some of the most successful convolutional neural networks (ResNet, Inception, VGG, and AlexNet) for 10-way classification of the X-ray images. We showed that substantial classification accuracy is gained by using such networks compared to two simpler ones previously proposed for this purpose. The best accuracy was obtained from ResNet (81.43%), which corresponds to a missed crystal rate of 5.9%. This rate could be lowered to less than 0.1% by using a top-3 classification strategy. Our dataset consisted of 486,000 internally annotated images, which was augmented to more than a million to address class imbalance. We also provide a label-wise analysis of the results, identifying the main sources of error and inaccuracy. |
Tasks | |
Published | 2018-05-11 |
URL | http://arxiv.org/abs/1805.04563v1 |
http://arxiv.org/pdf/1805.04563v1.pdf | |
PWC | https://paperswithcode.com/paper/classification-of-protein-crystallization-x |
Repo | |
Framework | |
Continual Lifelong Learning with Neural Networks: A Review
Title | Continual Lifelong Learning with Neural Networks: A Review |
Authors | German I. Parisi, Ronald Kemker, Jose L. Part, Christopher Kanan, Stefan Wermter |
Abstract | Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor skills as well as to long-term memory consolidation and retrieval. Consequently, lifelong learning capabilities are crucial for autonomous agents interacting in the real world and processing continuous streams of information. However, lifelong learning remains a long-standing challenge for machine learning and neural network models since the continual acquisition of incrementally available information from non-stationary data distributions generally leads to catastrophic forgetting or interference. This limitation represents a major drawback for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations in which information becomes incrementally available over time. In this review, we critically summarize the main challenges linked to lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic forgetting. We discuss well-established and emerging research motivated by lifelong learning factors in biological systems such as structural plasticity, memory replay, curriculum and transfer learning, intrinsic motivation, and multisensory integration. |
Tasks | Transfer Learning |
Published | 2018-02-21 |
URL | http://arxiv.org/abs/1802.07569v4 |
http://arxiv.org/pdf/1802.07569v4.pdf | |
PWC | https://paperswithcode.com/paper/continual-lifelong-learning-with-neural |
Repo | |
Framework | |
Propagating Uncertainty through the tanh Function with Application to Reservoir Computing
Title | Propagating Uncertainty through the tanh Function with Application to Reservoir Computing |
Authors | Manan Gandhi, Keuntaek Lee, Yunpeng Pan, Evangelos Theodorou |
Abstract | Many neural networks use the tanh activation function, however when given a probability distribution as input, the problem of computing the output distribution in neural networks with tanh activation has not yet been addressed. One important example is the initialization of the echo state network in reservoir computing, where random initialization of the reservoir requires time to wash out the initial conditions, thereby wasting precious data and computational resources. Motivated by this problem, we propose a novel solution utilizing a moment based approach to propagate uncertainty through an Echo State Network to reduce the washout time. In this work, we contribute two new methods to propagate uncertainty through the tanh activation function and propose the Probabilistic Echo State Network (PESN), a method that is shown to have better average performance than deterministic Echo State Networks given the random initialization of reservoir states. Additionally we test single and multi-step uncertainty propagation of our method on two regression tasks and show that we are able to recover similar means and variances as computed by Monte-Carlo simulations. |
Tasks | |
Published | 2018-06-25 |
URL | http://arxiv.org/abs/1806.09431v1 |
http://arxiv.org/pdf/1806.09431v1.pdf | |
PWC | https://paperswithcode.com/paper/propagating-uncertainty-through-the-tanh |
Repo | |
Framework | |
Convolutional Neural Networks on 3D Surfaces Using Parallel Frames
Title | Convolutional Neural Networks on 3D Surfaces Using Parallel Frames |
Authors | Hao Pan, Shilin Liu, Yang Liu, Xin Tong |
Abstract | We extend Convolutional Neural Networks (CNNs) on flat and regular domains (e.g. 2D images) to curved surfaces embedded in 3D Euclidean space that are discretized as irregular meshes and widely used to represent geometric data in Computer Vision and Graphics. We define surface convolution on tangent spaces of a surface domain, where the convolution has two desirable properties: 1) the distortion of surface domain signals is locally minimal when being projected to the tangent space, and 2) the translation equi-variance property holds locally, by aligning tangent spaces with the canonical parallel transport that preserves metric. For computation, we rely on a parallel N-direction frame field on the surface that minimizes field variation and therefore is as compatible as possible to and approximates the parallel transport. On the tangent spaces equipped with parallel frames, the computation of surface convolution becomes standard routine. The frames have rotational symmetry which we disambiguate by constructing the covering space of surface induced by the parallel frames and grouping the feature maps into N sets accordingly; convolution is computed on the N branches of the cover space with respective feature maps while the kernel weights are shared. To handle irregular points of a discrete mesh while sharing kernel weights, we make the convolution semi-discrete, i.e. the convolution kernels are polynomial functions, and their convolution with discrete surface points becomes sampling and weighted summation. Pooling and unpooling operations are computed along a mesh hierarchy built through simplification. The presented surface CNNs allow effective deep learning on meshes. We show that for tasks of classification, segmentation and non-rigid registration, surface CNNs using only raw input signals achieve superior performances than previous models using sophisticated input features. |
Tasks | Semantic Segmentation |
Published | 2018-08-15 |
URL | http://arxiv.org/abs/1808.04952v1 |
http://arxiv.org/pdf/1808.04952v1.pdf | |
PWC | https://paperswithcode.com/paper/convolutional-neural-networks-on-3d-surfaces |
Repo | |
Framework | |
Beyond Local Nash Equilibria for Adversarial Networks
Title | Beyond Local Nash Equilibria for Adversarial Networks |
Authors | Frans A. Oliehoek, Rahul Savani, Jose Gallego, Elise van der Pol, Roderich Groß |
Abstract | Save for some special cases, current training methods for Generative Adversarial Networks (GANs) are at best guaranteed to converge to a local Nash equilibrium (LNE). Such LNEs, however, can be arbitrarily far from an actual Nash equilibrium (NE), which implies that there are no guarantees on the quality of the found generator or classifier. This paper proposes to model GANs explicitly as finite games in mixed strategies, thereby ensuring that every LNE is an NE. With this formulation, we propose a solution method that is proven to monotonically converge to a resource-bounded Nash equilibrium (RB-NE): by increasing computational resources we can find better solutions. We empirically demonstrate that our method is less prone to typical GAN problems such as mode collapse, and produces solutions that are less exploitable than those produced by GANs and MGANs, and closely resemble theoretical predictions about NEs. |
Tasks | |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.07268v2 |
http://arxiv.org/pdf/1806.07268v2.pdf | |
PWC | https://paperswithcode.com/paper/beyond-local-nash-equilibria-for-adversarial |
Repo | |
Framework | |
A Comparison between Background Modelling Methods for Vehicle Segmentation in Highway Traffic Videos
Title | A Comparison between Background Modelling Methods for Vehicle Segmentation in Highway Traffic Videos |
Authors | L. A. Marcomini, A. L. Cunha |
Abstract | The objective of this paper is to compare the performance of three background-modeling algorithms in segmenting and detecting vehicles in highway traffic videos. All algorithms are available in OpenCV and were all coded in Python. We analyzed seven videos, totaling 2 hours of recording. To compare the algorithms, we created 35 ground-truth images, five from each video, and we used three different metrics: accuracy rate, precision rate, and processing time. By using accuracy and precision, we aim to identify how well the algorithms perform in detection and segmentation, while using the processing time to evaluate the impact on the computational system. Results indicate that all three algorithms had more than 90% of precision rate, while obtaining an average of 80% on accuracy. The algorithm with the lowest impact on processing time allowed the computation of 60 frames per second. |
Tasks | |
Published | 2018-10-05 |
URL | http://arxiv.org/abs/1810.02835v1 |
http://arxiv.org/pdf/1810.02835v1.pdf | |
PWC | https://paperswithcode.com/paper/a-comparison-between-background-modelling |
Repo | |
Framework | |
MPRAD: A Multiparametric Radiomics Framework
Title | MPRAD: A Multiparametric Radiomics Framework |
Authors | Vishwa S. Parekh, Michael A. Jacobs |
Abstract | Multiparametric radiological imaging is vital for detection, characterization and diagnosis of many different diseases. The use of radiomics for quantitative extraction of textural features from radiological imaging is increasing moving towards clinical decision support. However, current methods in radiomics are limited to using single images for the extraction of these textural features and may limit the applicable scope of radiomics in different clinical settings. Thus, in the current form, they are not capable of capturing the true underlying tissue characteristics in high dimensional multiparametric imaging space. To overcome this challenge, we have developed a multiparametric imaging radiomic framework termed MPRAD for extraction of radiomic features from high dimensional datasets. MPRAD was tested on two different organs and diseases; breast cancer and cerebrovascular accidents in brain, commonly referred to as stroke. The MPRAD framework classified malignant from benign breast lesions with excellent sensitivity and specificity of 87% and 80.5% respectively with an AUC of 0.88 providing a 9%-28% increase in AUC over single radiomic parameters. More importantly, in breast, the glandular tissue MPRAD were similar between each group with no significance differences. Similarly, the MPRAD features in brain stroke demonstrated increased performance in distinguishing the perfusion-diffusion mismatch compared to single parameter radiomics and there were no differences within the white and gray matter tissue. In conclusion, we have introduced the use of multiparametric radiomics into a clinical setting |
Tasks | |
Published | 2018-09-25 |
URL | http://arxiv.org/abs/1809.09973v1 |
http://arxiv.org/pdf/1809.09973v1.pdf | |
PWC | https://paperswithcode.com/paper/mprad-a-multiparametric-radiomics-framework |
Repo | |
Framework | |