Generative Adversarial Networks create synthetic data for structural damage detection.
problem Data scarcity in structural damage detection.
method 1-D Wasserstein Deep Convolutional Generative Adversarial Networks (1-D WDCGAN-GP) for synthetic data generation.
result Generated synthetic data improves damage detection accuracy in 1-D Deep Convolutional Neural Networks.
Where dealing with temporal sequences it is fair to assume that the same kind of deformations that motivated the development of the Dynamic Time Warp algorithm could be relevant also in the calculation of the dot product ("convolution") in a 1-D convolution layer. In this work a method is proposed for aligning the conv…
1-D CNNs classify pupil size variations in scotopic conditions.
problem Handling wide inter-subjects variability in pupil analysis.
method 1-D Convolutional Neural Networks applied directly to raw pupil size data.
result 1-D CNNs provide high accuracy in classifying short-range pupil size sequences.
Proposes a new deep learning framework for financial stock trading.
problem Lack of effective techniques to fuse multi-channel financial time-series data.
method Inspired by convolution transform learning, SDCF processes channels through 1-D convolutions, fuses outputs with fully-connected layers, and applies softmax classification.
result Proposed framework yields better results than state-of-the-art techniques for stock trading.
We propose weight-sharing regularization for neural networks.
problem Training fully connected networks with shuffled pixel data.
method Introduce a regularization penalty on weights and design parallel algorithms.
result Weight-sharing regularization enables learning convolution-like filters.
Deep neural nets on 1-D data are convex Lasso models with reflection features.
problem Training neural networks on 1-D data.
method Proving equivalence to convex Lasso problems with discrete, explicitly defined dictionary matrices.
result Reflection features in neural networks with certain activations.
Deep ReLU networks can approximate and learn smooth functions efficiently.
problem Efficiently approximating and learning smooth functions using deep ReLU neural networks.
method Extending recent results to anisotropic and mixed smooth function classes, establishing approximation rates.
result Deep ReLU networks achieve minimax optimal rates up to logarithmic factors for various smooth function classes.
Deep ReLU networks can efficiently approximate Sobolev and Besov functions.
problem Approximating functions in Sobolev and Besov spaces using deep neural networks.
method Used deep ReLU neural networks with varied width and depth to approximate functions in Sobolev and Besov spaces.
result Generalized the approximation rate to hold under the Sobolev embedding condition.
Study improves mortality prediction in ICU patients using feature engineering and 1D CNN.
problem Improving mortality prediction in ICU patients with high-dimensional, imbalanced, and missing data.
method Feature engineering, 1D Convolutional Neural Network (1D CNN), traditional machine learning algorithms.
result Best AUC of 0.848 achieved with 1D CNN model.
Deep neural networks can approximate complex functions through repeated compositions of a fixed-size ReLU network.
problem Understanding the expressive power of deep neural networks through function compositions.
method Demonstrated the surprising expressive power of repeated compositions of a single fixed-size ReLU network.
result Repeated compositions of a single fixed-size ReLU network can approximate 1-Lipschitz continuous functions on [0,1]d with an error O(r−1/d). Deep learning methods are increasingly being used with neuroimaging data like structural and function magnetic resonance imaging (MRI) to predict the diagnosis of neuropsychiatric and neurological disorders. For psychiatric disorders in particular, it is believed that one of the most promising modality is the resting-s…
Deep neural network predicts traffic flow on city maps.
problem Short-term traffic flow prediction on high-resolution city maps.
method UNet-based deep convolutional neural network with densely connected layers.
result Best performance on the Traffic4cast challenge 2019.
This work proposes hyperbolic deep convolutional neural networks for better pattern recognition.
problem The limitations of Euclidean deep convolutional neural networks in capturing intricate patterns.
method Developed Hyperbolic DCNN based on Poincaré Disc, analyzing expansive convolution in non-Euclidean space.
result Hyperbolic convolutional architecture outperforms Euclidean ones in pattern recognition tasks.
Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, and many other domains. The involved deep neural network architectures and computational issues have been well studied in machine learning. But there lacks a theoretical foundation for understanding the approximation…
Proves DCNNs with expansive convolution are strongly universally consistent.
problem Theoretical consistency of deep convolutional neural networks (DCNNs).
method Empirical risk minimization on DCNNs with expansive convolution (with zero-padding).
result DCNNs with expansive convolution are strongly universally consistent.
Deep ReLU networks can approximate smooth functions nearly optimally.
problem Approximating smooth functions with deep neural networks.
method Using Taylor expansions and deep ReLU network approximations, the paper establishes optimal approximation error bounds.
result Deep ReLU networks of width and depth O(NlnN) and O(LlnL) can approximate f∈Cs([0,1]d) with an error O(∥f∥Cs([0,1]d)N−2s/dL−2s/d). EASTER improves OCR efficiency and scalability.
problem Efficient and scalable Optical Character Recognition (OCR) for machine printed and handwritten text.
method 1-D convolutional layers without recurrence, parallel training, synthetic dataset generation.
result EASTER achieves comparable performance to complex RNN models with less data and outperforms them on benchmark datasets.
LipKernel adds robustness to CNNs by enforcing Lipschitz bounds.
problem Improving robustness of CNNs in real-time applications.
method Dissipative layers parameterized by LMIs and 2-D Roesser model.
result Orders of magnitude faster run-time compared to state-of-the-art methods.
The study examines deep convolutional neural networks and their learning ability.
problem Understanding the learning ability of deep convolutional neural networks (DCNNs).
method Examines DCNNs under both underparameterized and overparameterized settings, using a novel network deepening scheme.
result Establishes the first learning rates of underparameterized DCNNs and shows how adding layers can create interpolating DCNNs with good learning rates.
The paper verifies deep neural networks' ability to approximate functions on spheres.
problem Theoretical verification of deep neural networks' performance on spherical functions.
method Spherical analysis using reproducing kernels and convolutional factorizations.
result Rates of uniform approximation for functions in Sobolev spaces and additive ridge forms.
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters. Reducing the number of parameters while preserving essentially the same predictive performance is critically important …
The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.
problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.
An electrocardiogram (ECG) is a time-series signal that is represented by one-dimensional (1-D) data. Higher dimensional representation contains more information that is accessible for feature extraction. Hidden variables such as frequency relation and morphology of segment is not directly accessible in the time domain…
Spiking neural networks perform similarly to deep networks on occluded images.
problem Robust object recognition in partially occluded images.
method Developed a two-layer spiking neural network trained on natural scenes with a biologically plausible learning rule, compared to deep convolutional networks.
result Spiking neural networks achieve good accuracy and robustness on stepwise pixel erasement tasks.
Convolutional networks struggle with repeating patterns in ECGs.
problem Modeling repeating patterns in electrocardiogram signals.
method Demonstrated through ECG examples, highlighting systemic issues in deep learning.
result Counterintuitive effects on generalization in deep networks.
The paper analyzes deep ReLU CNNs' approximation properties in 2D space.
problem Establishing L2 approximation properties for deep ReLU CNNs. method Analysis based on decomposition theorem for convolutional kernels, properties of ReLU activation, and connections with one-hidden-layer ReLU NNs.
result Universal approximation theorem for deep ReLU CNNs with classic structure.
New mechanism discovered for feature learning in CNNs.
problem Understanding how CNNs learn features from images.
method Proposed Convolutional Neural Feature Ansatz linking filter covariances to patch-based AGOPs.
result Deep ConvRFM algorithm learns features similar to deep CNNs, improving performance.
Review of neural network expressivity and architectures.
problem Understanding neural network expressivity across different architectures.
method Comprehensive overview of approximation results for various neural network types.
result Deep neural networks offer advantages over shallow ones for specific function classes.
In this paper, some patterns of the Neuron Response of deep Convolutional Neural Networks were observed.
We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In exp…
CMDRNN predicts user location using WiFi fingerprints with deep learning.
problem Predicting user activity with WiFi fingerprints is challenging due to high dimensionality.
method Combines CNN, RNN, and MDN to model high-dimensional time-series data.
result CMDRNN effectively predicts user location using WiFi fingerprints.
This paper removes the finite variance assumption for deep convolutional neural networks.
problem Removing the finite variance assumption for deep convolutional neural networks.
method Assuming iid parameters distributed according to a stable distribution, the paper shows that the infinite-channel limit of a deep feed-forward convolutional neural network is a multivariate stable stochastic process.
result The infinite-channel limit of a deep feed-forward convolutional neural network, under suitable scaling, is a multivariate stable stochastic process.
In recent work, it was shown that combining multi-kernel based support vector machines (SVMs) can lead to near state-of-the-art performance on an action recognition dataset (HMDB-51 dataset). This was 0.4\% lower than frameworks that used hand-crafted features in addition to the deep convolutional feature extractors. I…
Deep convolutional neural networks comprise a subclass of deep neural networks (DNN) with a constrained architecture that leverages the spatial and temporal structure of the domain they model. Convolutional networks achieve the best predictive performance in areas such as speech and image recognition by hierarchically …
A hybrid method improves Convolutional Neural Networks training.
problem Training Convolutional Neural Networks efficiently and avoiding local minima.
method Combines backpropagation with evolutionary strategies.
result Improves accuracy by 0.61% on CIFAR-10 image classification.
Convolutional neural networks outperform other architectures in streaming time series classification.
problem Efficient deep learning models for real-time data streams.
method Asynchronous dual-pipeline deep learning framework for real-time predictions.
result Convolutional architectures achieve higher accuracy and efficiency in streaming time series classification.
Graph convolutional neural networks (GCN) have been the model of choice for graph representation learning, which is mainly due to the effective design of graph convolution that computes the representation of a node by aggregating those of its neighbors. However, existing GCN variants commonly use 1-D graph convolution …
Deep neural networks are a powerful tool for feature learning and extraction given their ability to model high-level abstractions in highly complex data. One area worth exploring in feature learning and extraction using deep neural networks is efficient neural connectivity formation for faster feature learning and extr…
New bounds for neural networks ensure robustness and accuracy.
problem Ensuring robustness of neural networks by computing Lipschitz constants.
method Analyzed and proposed new bounds for l1 and l∞ norms, using explicit and implicit methods for convnets. result One of the new bounds is optimal and more accurate than existing ones.
Normalization layers are widely used in deep neural networks to stabilize training. In this paper, we consider the training of convolutional neural networks with gradient descent on a single training example. This optimization problem arises in recent approaches for solving inverse problems such as the deep image prior…
We train an enhanced deep convolutional neural network in order to identify eight cardiac abnormalities from the standard 12-lead electrocardiograms (ECGs) using the dataset of 14000 ECGs. Instead of straightforwardly applying an end-to-end deep learning approach, we find that deep convolutional neural networks enhance…
Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the trained network to platforms with memory and processing constraints. We propose to modify the structure of the Very Deep Convolutional Neural…
Deep neural networks solve optimal risk sharing problems.
problem Optimally sharing financial positions among agents with different risk measures.
method Neural network-based framework to compute inf-convolution and optimal allocations.
result Convergence of neural network approximations to theoretical values.
Image understanding using deep convolutional network has reached human-level performance, yet a closely related problem of video understanding especially, action recognition has not reached the requisite level of maturity. We combine multi-kernels based support-vector-machines (SVM) with a multi-stream deep convolution…
Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers. We adapt this approach to the convolutional setting.
We analyze the eigenvalue distribution of a neural network's kernel under specific scaling.
problem Analyzing the eigenvalue distribution of the Neural Tangent Kernel (NTK) of a neural network.
method Asymptotic analysis of the NTK matrix under given scaling conditions.
result The eigenvalue distribution is described as a free multiplicative convolution of the Marchenko-Pastur distribution and a deterministic distribution.
Deep Learning Library (DLL) is a new library for machine learning with deep neural networks that focuses on speed. It supports feed-forward neural networks such as fully-connected Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs). It also has very comprehensive support for Restricted Boltzmann …
Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic extraction of high-level features. The computation with filters requires a fixed …