Novel LSTM network predicts pulsar timing residuals with few-shot data.
problem Predicting pulsar timing residuals with limited data.
method Long Short-Term Memory (LSTM) network optimized with model-agnostic meta-learning and particle swarm optimization.
result Robust generalization and accurate predictions across high-frequency test domains with minimal data.
Momentum ResNets improve ResNets' memory efficiency.
problem Memory inefficiency in deep residual neural networks (ResNets).
method Adding a momentum term to the forward rule of ResNets to make them invertible.
result Momentum ResNets can learn any linear mapping up to a multiplicative factor, improving memory efficiency.
Proposes RMN for learning long-term dependencies in feed-forward networks.
problem Complicated training of deep RNN architectures.
method Residual Memory Neural Network (RMN) with residual and time-delayed connections.
result RMN and BRMN outperform LSTM and BLSTM networks in learning long-term and hierarchical information.
RSmote improves PINNs accuracy with less memory usage.
problem Imbalanced learning in Physics-Informed Neural Networks (PINNs).
method Residual-based Smote (RSmote) for local adaptive sampling.
result RSmote achieves or exceeds accuracy of state-of-the-art methods while reducing memory usage.
JKO-iFlow uses neural ODEs to improve generative models with reduced memory and training complexity.
problem Efficiently training deep generative models in high dimensions with reduced memory and training complexity.
method JKO scheme inspired neural ODE flow network with adaptive time reparameterization.
result JKO-iFlow achieves competitive performance compared to existing models at reduced computational and memory cost.
Investigates the relationship between ResNets and Neural ODEs, quantifying their closeness and providing training methods.
problem Quantifying the distance between ResNet dynamics and Neural ODE solutions.
method Bounding the distance between hidden state trajectories and Neural ODE solutions, using gradient descent and Heun's method.
result Gradient descent and Heun's method can implicitly regularize ResNets towards Neural ODEs, especially for smooth residual functions.
New model captures long-term memory effects in epidemic dynamics.
problem Identifying memory effects in disease progression and recovery.
method Physics-informed neural networks (PINN) with fractional SEIRD model.
result Fractional memory order α improves predictive performance over classical models. Residual Flows improve flow-based models for density estimation.
problem Density estimation using flow-based models with biased log-density estimates.
method Proposed a Russian roulette estimator for unbiased log-density estimation and used an alternative infinite series for gradient calculation. Improved invertible residual blocks with activation functions avoiding derivative saturation and generalized Lipschitz condition to induced mixed norms.
result Residual Flows achieve state-of-the-art performance on density estimation and outperform coupling block networks in joint generative and discriminative modeling.
Paper tackles stutter detection using deep learning.
problem Identification and classification of stuttered speech.
method Uses a deep residual network with bidirectional LSTM layers.
result Achieves an average miss rate of 10.03%, outperforming state-of-the-art.
Many engineers wish to deploy modern neural networks in memory-limited settings; but the development of flexible methods for reducing memory use is in its infancy, and there is little knowledge of the resulting cost-benefit. We propose structural model distillation for memory reduction using a strategy that produces a …
New deep architecture improves stability and robustness of neural networks.
problem Improving stability and robustness of neural networks.
method Proposes a new deep architecture using implicit residual blocks with fixed point definitions.
result Improved stability and generalization power with fewer hyperparameters.
MemNet optimizes neural architectures for memory efficiency.
problem Memory constraints in mobile devices limit the use of large neural networks.
method Augment-trim learning with memory consumption ranking score.
result MemNet finds architectures with 24.17% less memory usage compared to state-of-the-art methods.
Second-order optimizers retain residual information after data deletion, affecting machine unlearning.
problem Residual information in second-order optimizers after data deletion.
method Comparison of first-order and second-order learners, eigendecomposition analysis.
result Second-order optimizers retain residual information, not detectable by first-order analysis.
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…
Extended LSTM improves language modeling performance.
problem Improving LSTM for large-scale language modeling.
method Exponential gating, modified memory structure, and residual stacking.
result xLSTM outperforms state-of-the-art models in performance and scaling.
Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with deeper and wider architectures. In this work, we interpret deep residual networks as ordinary differential equations (ODEs), which have long been s…
Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we present Lat-Net, a method for compressing both the computation time and memory usage of Lattice Boltzm…
Investigates scaling deep neural networks to avoid capacity issues.
problem Avoiding the shattering problem in deep neural networks.
method Formulates conjecture and studies various architectures to determine scaling relations.
result Reveals scaling relations for deep residual networks and recurrent networks.
A new method selects PCA components based on residual memory, outperforming existing techniques.
problem Selecting the optimal number of components in PCA for data with long memory effects.
method Sequentially removes components, stopping when maximum memory accounted for.
result Our method outperforms existing techniques in computational efficiency and accuracy.
Efficient hybrid networks improve AI performance at the edge.
problem Achieving AI performance at the edge with minimal energy and memory usage.
method Proposed hybrid networks combining binary and full-precision layers.
result Hybrid networks achieve close to full-precision performance with up to 21.8x memory compression.
Simplifies residual flows to make flow-based modeling more practical.
problem Extremely high computational cost of residual flows limits their applicability.
method Introduces Quasi-Autoregressive (QuAR) approach to residual flows.
result Significantly reduces compute time and memory requirements for flow-based modeling.
BiGraphNet generalizes graph neural networks for more efficient operations.
problem Fragmented graph neural network architectures hinder optimization.
method Explicitly separates input and output nodes, enabling new efficient operations.
result BiGraphNet accelerates and scales computations in hierarchical networks.
CloGAN uses memory replay and GAN to prevent forgetting in continual learning.
problem Catastrophic forgetting in sequential learning tasks.
method Cumulative closed-loop memory replay GAN with external regularization.
result Model performance asymptotically approaches full dataset training.
Dual model predicts electricity spot prices using neural networks and wavelets.
problem Forecasting hourly electricity spot prices.
method Dual generalized long memory modelling with k-factor GARMA and G-GARCH models, using LLWNN and PSO for variance prediction.
result The hybrid k-factor GARMA-LLWNN model outperforms other methods in forecasting accuracy.
DiffusionBlocks trains neural networks by breaking them into independent blocks, reducing memory usage.
problem Memory bottlenecks in end-to-end neural network training.
method Transforming transformer-based networks into independent trainable blocks via a denoising process.
result Independent block-wise training matches end-to-end training performance while reducing memory requirements.
The covariance matrix is formulated in the framework of a linear multivariate ARCH process with long memory, where the natural cross product structure of the covariance is generalized by adding two linear terms with their respective parameter. The residuals of the linear ARCH process are computed using historical data …
Wide residual networks generalize well with uniform convergence to RNTK as width increases.
problem Understanding the generalization ability of wide residual networks.
method Uniform convergence of residual network kernel to residual neural tangent kernel (RNTK).
result Generalization error converges to kernel regression error with respect to RNTK.
Batch normalization makes deep residual networks train faster.
problem Training deep residual networks with large depths.
method Downscaling the residual branch by a normalizing factor early in training.
result Normalized residual blocks compute functions close to the identity function early in training.
Unified ODE model explains residual and non-residual networks.
problem Unclear relationship between residual and non-residual networks.
method Introducing a damping term in an ODE model to interpolate between ResNet and CNN architectures.
result Unified framework for understanding residual and non-residual networks.
ResGCN detects anomalies in attributed networks by capturing sparsity and nonlinearity.
problem Detecting anomalous nodes in attributed networks.
method Attention-based deep residual modeling using Graph Convolutional Networks.
result ResGCN effectively detects anomalies in attributed networks.
Deep residual networks trained with gradient descent have small generalization gap.
problem Limited theoretical understanding of why residual networks generalize well.
method Analyzing overparameterized deep residual networks trained by gradient descent.
result Demonstrates that residual networks have a small generalization gap between training and test error.
Analysis shows BN prevents gradient vanishing/explosion in residual networks.
problem Gradient vanishing/explosion problem in residual networks.
method Mathematical analysis of BN and residual network training.
result BN confounds gradient variance, preventing vanishing/explosion.
Neural RDEs extend CDEs to irregular time series.
problem Modeling long irregular time series efficiently.
method Representing time series through log-signature and solving RDEs.
result Significant training speed-ups and improved model performance.
Continuous neural networks using differential equations.
problem Training and optimizing neural networks with continuous-depth architectures.
method Parameterize derivative of hidden state using neural networks and solve differential equations.
result End-to-end training of continuous-depth models.
Paper presents a deep learning method for CT image super-resolution.
problem Developing high-quality CT images with reduced radiation exposure.
method Generative adversarial network (GAN) with cycle consistency and residual learning constraints.
result The proposed method achieves accurate, efficient, and robust super-resolution of CT images.
Residual neural networks don't help overcome sampling complexity issues.
problem Learning invertible residual neural networks from samples is hard due to the curse of dimensionality.
method Investigated invertible residual neural networks and their sampling complexity.
result Invertible residual neural networks still suffer from the curse of dimensionality in sampling complexity.
A new network learns market conditions and predicts stock performance.
problem Optimizing stock portfolio performance in the US equities market.
method Residual Switching Network combining two ResNets: a switching module and a main module.
result The residual switching network strategy outperformed other models with an average annual Sharpe ratio of 2.22.
Residuals improve deep neural networks without increasing hypothesis complexity.
problem Understanding how residual connections affect hypothesis complexity and generalization.
method Analyzing the covering number of the hypothesis space and deriving a margin-based generalization bound.
result Residual connections do not increase the hypothesis complexity of neural networks.
Proposes a neural network method to correct residual distortions in coordinate transformations.
problem Nonlinear and spatially dependent distortions in coordinate transformation models.
method Residual-based neural network approach focusing on systematic distortions.
result The method improves accuracy and stability in challenging conditions.
Enhanced image denoising with MWRDCNN using residual dense blocks.
problem Image denoising with improved performance and robustness.
method Multi-wavelet residual dense convolutional neural network (MWRDCNN) with residual dense blocks (RDBs).
result Significantly improved performance in image denoising compared to existing techniques.
Paper proposes continuous residual layers for graph neural networks.
problem Low-pass filtering effect in GCN-based models.
method Integrates Ordinary Differential Equations (ODE) to produce outputs of continuous residual layers.
result Continuous residual layers achieve better results than non-residual modules in multiple layers.
Generalization bounds derived for neural ODEs and deep residual networks.
problem Understanding the generalization capability of neural ODEs and deep residual networks.
method Lipschitz-based argument and analogy with deep residual networks.
result A generalization bound involving the magnitude of weight matrix differences.
Gradient descent converges globally in deep linear residual networks with ZAS initialization.
problem Optimizing deep linear residual networks for convergence.
method Zero-asymmetric (ZAS) initialization for gradient descent.
result Gradient descent converges to an ε-optimal point in O(L^3 log(1/ε)) iterations.
Residual networks analyzed using linearization for stability under perturbations.
problem Understanding the behavior of residual networks under small input perturbations.
method Linearization of residual units and network stages, using singular value decomposition for stability analysis.
result Most singular values of residual units are 1, but scaling and weights significantly affect them.
SRFRN accelerates image super-resolution using shallow residual units.
problem High computational complexity and time in deep learning image super-resolution.
method SRFRN uses a bicubic interpolated low-resolution image and residual representative units (RFR) for faster and more efficient high-resolution image reconstruction.
result SRFRN achieves superior performance and faster execution time compared to existing methods.
Deep residual networks implicitly converge to neural ODEs.
problem Link between discrete and continuous deep learning models.
method Establishing implicit regularization for residual networks towards neural ODEs.
result Deep residual networks initialized as discretizations of neural ODEs converge to such ODEs during training.
Residual Continual Learning prevents forgetting in sequential tasks.
problem Preventing catastrophic forgetting in sequential learning of multiple tasks.
method ResCL reparameterizes network parameters by combining original and fine-tuned networks, keeping network size constant.
result ResCL achieves state-of-the-art performance in various continual learning scenarios.
Residual networks with block width max(d_x, d_y) approximate all functions.
problem Achieving universal approximation with residual networks.
method Established bounds on block width for different activation functions.
result Minimum block width for universal approximation is max(d_x, d_y) with inner width 1.