arXiv research

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…

ResGCN detects anomalies in attributed networks by capturing sparsity and nonlinearity.

Efficient Winograd convolution for INT8 networks using RNS.

Networks with large receptive field (RF) have shown advanced fitting ability in recent years. In this work, we utilize the short-term residual learning method to improve the performance and robustness of networks for image denoising tasks. Here, we choose a multi-wavelet convolutional neural network (MWCNN), one of the…

Predicting diagnoses from Electronic Health Records (EHRs) is an important medical application of multi-label learning. We propose a convolutional residual model for multi-label classification from doctor notes in EHR data. A given patient may have multiple diagnoses, and therefore multi-label learning is required. We …

Review of neural network expressivity and architectures.

This paper proposes a multi-channel image reconstruction method, named DeepcomplexMRI, to accelerate parallel MR imaging with residual complex convolutional neural network. Different from most existing works which rely on the utilization of the coil sensitivities or prior information of predefined transforms, Deepcompl…

Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the training of and prediction with CNNs. To improve the efficiency of CNNs, we introd…

SRFRN accelerates image super-resolution using shallow residual units.

Deep, wide ConvResNets can approximate functions and their smoothness.

Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networ…

In this paper, we present NESTA, a specialized Neural engine that significantly accelerates the computation of convolution layers in a deep convolutional neural network, while reducing the computational energy. NESTA reformats Convolutions into $3 \times 3$ batches and uses a hierarchy of Hamming Weight Compressors to …

Model based iterative reconstruction (MBIR) algorithms for low-dose X-ray CT are computationally expensive. To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the texture were n…

Deep GCNII tackles over-smoothing problem in graph convolutional networks.

An emerging design principle in deep learning is that each layer of a deep artificial neural network should be able to easily express the identity transformation. This idea not only motivated various normalization techniques, such as \emph{batch normalization}, but was also key to the immense success of \emph{residual …

Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. While residual links improve gradient flow during training, feature diminution of shallow layer outputs can occur due to repetitiv…

Inverse modeling for the estimation of non-Gaussian hydraulic conductivity fields in subsurface flow and solute transport models remains a challenging problem. This is mainly due to the non-Gaussian property, the non-linear physics, and the fact that many repeated evaluations of the forward model are often required. In…

Unified ODE model explains residual and non-residual networks.

Unified learning-rate scale for CNNs and ResNets, avoiding depth imbalance.

This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech. Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCCs) have shown the ability to characterize emotion better than just plain text. Furth…

Due to the success of residual networks (resnets) and related architectures, shortcut connections have quickly become standard tools for building convolutional neural networks. The explanations in the literature for the apparent effectiveness of shortcuts are varied and often contradictory. We hypothesize that shortcut…

Scattering GCN improves graph neural networks by filtering oversmoothing.

Residual neural networks don't help overcome sampling complexity issues.

ConvResNets approximate Besov functions and classify on low-dimensional manifolds.

We propose a novel continual learning method called Residual Continual Learning (ResCL). Our method can prevent the catastrophic forgetting phenomenon in sequential learning of multiple tasks, without any source task information except the original network. ResCL reparameterizes network parameters by linearly combining…

Graph Convolutional Networks (GCNs) are state-of-the-art graph based representation learning models by iteratively stacking multiple layers of convolution aggregation operations and non-linear activation operations. Recently, in Collaborative Filtering (CF) based Recommender Systems (RS), by treating the user-item inte…

Residual networks with depthwise hyperparameter scaling transfer optimal hyperparameters across width and depth.

Vision Transformers show different internal representations compared to CNNs.

We characterize the singular values of the linear transformation associated with a standard 2D multi-channel convolutional layer, enabling their efficient computation. This characterization also leads to an algorithm for projecting a convolutional layer onto an operator-norm ball. We show that this is an effective regu…

Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized …

Paper analyzes the free energy of CNNs with skip connections in Bayesian learning.

A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partiall…

GT-DDP optimizer trains residual networks using game theory.

New multigrid approach reduces CNN parameters by focusing on structured convolutions.

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized neural network with residual connections (ResNet). Our analysis relies on the p…

This paper extends geometric study of neural networks to non-differentiable layers and random walks.

We show that Residual Networks (ResNet) is equivalent to boosting feature representation, without any modification to the underlying ResNet training algorithm. A regret bound based on Online Gradient Boosting theory is proved and suggests that ResNet could achieve Online Gradient Boosting regret bounds through neural n…

To have a superior generalization, a deep learning neural network often involves a large size of training sample. With increase of hidden layers in order to increase learning ability, neural network has potential degradation in accuracy. Both could seriously limit applicability of deep learning in some domains particul…

We introduce a general method of performing Residual Network inference and learning in the JPEG transform domain that allows the network to consume compressed images as input. Our formulation leverages the linearity of the JPEG transform to redefine convolution and batch normalization with a tune-able numerical approxi…

Due to a resource-constrained environment, network compression has become an important part of deep neural networks research. In this paper, we propose a new compression method, \textit{Inter-Layer Weight Prediction} (ILWP) and quantization method which quantize the predicted residuals between the weights in all convol…

Recently, with convolutional neural networks gaining significant achievements in many challenging machine learning fields, hand-crafted neural networks no longer satisfy our requirements as designing a network will cost a lot, and automatically generating architectures has attracted increasingly more attention and focu…

Subspace clustering aims to cluster unlabeled data that lies in a union of low-dimensional linear subspaces. Deep subspace clustering approaches based on auto-encoders have become very popular to solve subspace clustering problems. However, the training of current deep methods converges slowly, which is much less effic…

Ensemble methods, traditionally built with independently trained de-correlated models, have proven to be efficient methods for reducing the remaining residual generalization error, which results in robust and accurate methods for real-world applications. In the context of deep learning, however, training an ensemble of…

Due to the rapid growth of machine learning tools and specifically deep networks in various computer vision and image processing areas, application of Convolutional Neural Networks for watermarking have recently emerged. In this paper, we propose a deep end-to-end diffusion watermarking framework (ReDMark) which can be…

Convolutional neural networks (CNNs) often perform well, but their stability is poorly understood. To address this problem, we consider the simple prototypical problem of signal denoising, where classical approaches such as nonlinear diffusion, wavelet-based methods and regularisation offer provable stability guarantee…

STRIC detects anomalies in time series by analyzing residual signals.

We show that the output of a (residual) convolutional neural network (CNN) with an appropriate prior over the weights and biases is a Gaussian process (GP) in the limit of infinitely many convolutional filters, extending similar results for dense networks. For a CNN, the equivalent kernel can be computed exactly and, u…

Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve high-dimensional data. A CNN filters the input feature using a network containing spatial convolution operators with compactly supported stencils. In pra…