A new method for the unsupervised learning of sparse representations using autoencoders is proposed and implemented by ordering the output of the hidden units by their activation value and progressively reconstructing the input in this order. This can be done efficiently in parallel with the use of cumulative sums and …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,982 papers · 148 categories
Trend · papers per month
48 results for “input reconstruction”
This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretical summarize the general properties of all algorithms that are based on traditional Auto-Encoders: 1) The reconstruction error of the input can not be lower than a lower bound, wh…
Autoencoderscs.LG
Autoencoders compress and reconstruct data for various applications.
problem Efficiently compress and reconstruct data.
method Neural network architecture that encodes and decodes data.
result Autoencoders can be applied to various data types and applications.
There is an increasingly apparent need for validating the classifications made by deep learning systems in safety-critical applications like autonomous vehicle systems. A number of recent papers have proposed methods for detecting anomalous image data that appear different from known inlier data samples, including reco…
We present a novel nonnegative tensor decomposition method, called Legendre decomposition, which factorizes an input tensor into a multiplicative combination of parameters. Thanks to the well-developed theory of information geometry, the reconstructed tensor is unique and always minimizes the KL divergence from an inpu…
Paper uses CNNs for eye tracking data segmentation, generation, and reconstruction.
problem Semantic segmentation and reconstruction of raw eye tracking data.
method Fully convolutional neural networks (FCNNs) for data segmentation and generation, variational auto-encoder for data generation.
result FCNNs can process any input size directly without preprocessing, generating raw eye tracking data.
EggNet: An Evolving Graph-based Graph Attention Network for Particle Track Reconstructionphysics.data-an
EggNet reconstructs particle tracks from hits using evolving graph attention networks.
problem Particle track reconstruction is computationally expensive and combinatorial.
method EggNet uses a one-shot object condensation approach with evolving graph attention networks.
result EggNet outperforms methods requiring fixed input graphs on TrackML dataset.
DOODLER detects out-of-distribution inputs by reconstructing in-distribution data.
problem Detecting real-world out-of-distribution inputs for deep learning models.
method DOODLER uses a Variational Auto-Encoder to reconstruct in-distribution data and identifies failures as out-of-distribution.
result DOODLER outperforms other OOD detection methods under similar constraints.
Study proposes a new method for MRI image reconstruction using denoising autoencoders and undecimated wavelet transforms.
problem Efficient MRI image reconstruction using under-sampled data.
method Undecimated wavelet transform, denoising autoencoder, proximal gradient algorithm.
result The proposed method enhances MRI image reconstruction efficiency and robustness.
Capsule networks detect and diagnose adversarial images better than CNNs.
problem Detecting and diagnosing adversarial images in neural networks.
method Class-conditional capsule reconstruction and reconstructive attack.
result Capsule networks outperform CNNs in detecting and diagnosing adversarial images.
Deep learning networks have shown state-of-the-art performance in many image reconstruction problems. However, it is not well understood what properties of representation and learning may improve the generalization ability of the network. In this paper, we propose that the generalization ability of an encoder-decoder n…
A new faster neural network training method using backprojection.
problem Training feedforward neural networks more efficiently.
method Projection and reconstruction at each layer to force projected data and reconstructed labels to be similar.
result The proposed method is faster than backpropagation and gives insights into networks.
New method reconstructs missing variables in time series using autoencoders and automatic differentiation.
problem Reconstruct missing variables in time series with flexible input and output combinations.
method Train an autoencoder with all features, optimize missing variables as inputs, and use automatic differentiation.
result Flexible input and output combinations can be achieved without retraining the autoencoder.
Improved unsupervised word translation using adversarial autoencoder with cycle consistency and input reconstruction.
problem Challenging language pairs and lack of parallel data for unsupervised word translation.
method Adversarial autoencoder with cycle consistency and input reconstruction regularization.
result More stable and better performance than recent approaches.
Predicts trainability of deep neural networks using reconstruction entropy.
problem Predicting the initial conditions for trainability of deep neural networks.
method Cascade of auxiliary networks to reconstruct input from activation layers, computing relative entropy.
result Predicts trainability of deep feedforward networks on various datasets with a single epoch.
RECol generates error columns to improve outlier detection.
problem Outlier detection in data with complex relationships.
method Generates reconstruction error columns for leave-one-out feature sets.
result Improves ROC-AUC and PR-AUC values of common outlier detection methods.
Generative adversarial network-based approach to signal reconstruction from magnitude spectrogramseess.SP
In this paper, we address the problem of reconstructing a time-domain signal (or a phase spectrogram) solely from a magnitude spectrogram. Since magnitude spectrograms do not contain phase information, we must restore or infer phase information to reconstruct a time-domain signal. One widely used approach for dealing w…
Bayesian image reconstruction using pre-trained generative models.
problem Distribution shifts and latent variable changes in image data.
method Combining SOTA generative models with Bayes' theorem for image restoration tasks.
result Competitive performance on super-resolution and in-painting tasks without training.
RADAR uses diffusion models to detect anomalies without reconstruction, improving accuracy and efficiency.
problem Challenges in anomaly detection and segmentation, especially in real-time applications.
method RADAR uses attention-based diffusion models to directly produce anomaly maps from the diffusion process, bypassing reconstruction.
result RADAR improves F1 score by 7% on MVTec-AD and 13% on 3D-printed material compared to state-of-the-art methods.
Develops a new robustness criterion for VAEs and provides theoretical guarantees.
problem Lack of formalization for robustness in VAEs.
method Introduces -robustness criterion and derives reconstruction margins.
result Derives theoretical guarantees for VAE robustness.
Proposes a new method for efficient model reconstruction with uncertain parameters.
problem Reconstructing models with latent variables or parameters of unknown distribution.
method Local squared Wasserstein-2 (W_2) method.
result Efficiently reconstructs output distributions from observation data.
Deep Kernelized Autoencodersstat.ML
In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from such a kernel space to input space. The proposed method is based on traditional a…
Since its introduction, unsupervised representation learning has attracted a lot of attention from the research community, as it is demonstrated to be highly effective and easy-to-apply in tasks such as dimension reduction, clustering, visualization, information retrieval, and semi-supervised learning. In this work, we…
Paper proposes a CNN for speech emotion recognition using center loss and reconstruction.
problem Speech emotion recognition (SER) in audio signals.
method Convolutional Neural Network (CNN) with center loss and reconstruction as regularizers.
result Proposed method achieves highly discriminative features for SER.
Autoencoder Treescs.LG
We discuss an autoencoder model in which the encoding and decoding functions are implemented by decision trees. We use the soft decision tree where internal nodes realize soft multivariate splits given by a gating function and the overall output is the average of all leaves weighted by the gating values on their path. …
This paper proposes a method to train multiple neural networks with shared parameters using a reconstruction loss.
problem Training multiple neural networks for correlated tasks separately is inefficient.
method Introduces a novel approach with a reconstruction loss to encourage shared features across multiple tasks.
result The proposed method achieves efficient transfer learning with competitive performance.
Improved hybrid image compression using deep learning and traditional codecs.
problem Efficiently compressing images with high quality and low bitrates.
method Combining CNN for compact representation, FLIF for base layer, and BPG for enhancement layer.
result Outperforms state-of-the-art schemes in PSNR and MS-SSIM metrics.
Compressive sensing (CS) has been studied and applied in structural health monitoring for wireless data acquisition and transmission, structural modal identification, and spare damage identification. The key issue in CS is finding the optimal solution for sparse optimization. In the past years, many algorithms have bee…
Machine Learning for Particle Flow Reconstruction at CMSphysics.data-an
CMS uses machine learning to improve particle flow reconstruction.
problem Improving particle flow reconstruction in CMS.
method Machine learning, graph neural network, heterogeneous computing.
result Machine-learned PF model outperforms standard algorithm.
STAR-GCN improves recommender systems by learning node representations.
problem Cold start problem in recommender systems.
method Stacked and reconstructed Graph Convolutional Networks (GCN) with intermediate supervision and node embedding reconstruction.
result Significant improvements in predicting ratings, especially in the cold start scenario.
New method improves model reconstruction using counterfactuals and polytope theory.
problem Reconstructing models with minimal input changes and avoiding decision boundary shifts.
method Using polytope theory to derive loss functions that treat counterfactuals differently from ordinary instances.
result Improves fidelity between target and surrogate model predictions on multiple datasets.
A neural network learns a convex regularizer for better image reconstruction.
problem Improving image reconstruction in inverse problems.
method Adversarial training of a data-adaptive ICNN as a convex regularizer.
result The convex regularizer leads to better convergence and error reduction in image reconstruction.
PC-RNN reconstructs MRI images from undersampled data with more details.
problem Recovering fine details from undersampled MRI data.
method Pyramid Convolutional RNN (PC-RNN) with three ConvRNN modules for multi-scale reconstruction.
result PC-RNN outperforms other methods in recovering more details from MRI images.
SANs use sparse activation functions to compress data representations.
problem Learning meaningful features without considering compression.
method Introduce φ metric, define activation functions, and present SANs.
result SANs achieve small description length and interpretable kernels.
We introduce the concrete autoencoder, an end-to-end differentiable method for global feature selection, which efficiently identifies a subset of the most informative features and simultaneously learns a neural network to reconstruct the input data from the selected features. Our method is unsupervised, and is based on…
We present a simple technique that allows capsule models to detect adversarial images. In addition to being trained to classify images, the capsule model is trained to reconstruct the images from the pose parameters and identity of the correct top-level capsule. Adversarial images do not look like a typical member of t…
Convolutional neural networks (CNNs) have shown remarkable results over the last several years for a wide range of computer vision tasks. A new architecture recently introduced by Sabour et al., referred to as a capsule networks with dynamic routing, has shown great initial results for digit recognition and small image…
CASTLE learns causal DAG to improve model generalization.
problem Improving model generalization to out-of-sample data.
method CASTLE learns causal relationships via adjacency matrix embedded in neural network input layers, reconstructing only causal features.
result CASTLE leads to better out-of-sample predictions compared to other regularizers.
New method reconstructs images from fMRI data using unlabeled data.
problem Challenges in acquiring labeled data for fMRI-to-image reconstruction.
method Self-supervised training with Encoder-Decoder and Decoder-Encoder networks.
result Reconstruction network adapts to new unlabeled test data.
SANs use sparse activation functions to minimize model complexity.
problem Model complexity in unsupervised learning.
method Introduce φ metric, define activation functions, present Sparsely Activated Networks (SANs).
result SANs with selected activation functions have small description length and interpretable kernels.
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to extract the semantic feature…
This work provides statistical guarantees for VAEs using PAC-Bayesian theory.
problem Theoretical properties of VAEs remain open questions.
method PAC-Bayesian theory to derive statistical guarantees.
result Upper bounds on Wasserstein distance between input and generative model.
Unified deep learning approach for time series forecasting using VMD-CNN-LSTM.
problem Time series forecasting problem.
method Proposes a unified deep learning approach with decomposition-reconstruction-ensemble framework using VMD-CNN-LSTM.
result The proposed approach outperforms benchmark approaches in forecasting accuracy.
Reconstructing polytopes with fixed facet directions from support function evaluations.
problem Reconstructing polytopes with known facet directions from limited data.
method Least-squares estimate via convex quadratic program, combinatorial characterization for uniqueness, algorithm convergence.
result The least-squares estimate for a fixed simplicial normal fan is a convex quadratic program, and the solution is unique under certain conditions.
Paper defends iris recognition from adversarial examples using wavelet decomposition.
problem Adversarial examples threaten deep neural networks in biometric applications.
method Wavelet domain denoising of input examples to detect and mitigate adversarial attacks.
result Proposed defense strategies improve recognition accuracy against adversarial attacks.
KM-GPT: An Automated Pipeline for Reconstructing Individual Patient Data from Kaplan-Meier Plotscs.LG
KM-GPT automates IPD reconstruction from KM plots with high accuracy and scalability.
problem Manual digitization of IPD from KM plots is error-prone and lacks scalability.
method KM-GPT integrates advanced image preprocessing, multi-modal reasoning, and iterative reconstruction algorithms.
result KM-GPT generates high-quality IPD without manual input or intervention, achieving superior accuracy.
Generative LLE modifies LLE to generate stochastic embeddings.
problem Nonlinear dimensionality reduction and manifold learning.
method Generative LLE modifies LLE by using stochastic linear reconstruction.
result Generative LLE can generate various LLE embeddings stochastically.
We present convolutional neural network (CNN) based approaches for unsupervised multimodal subspace clustering. The proposed framework consists of three main stages - multimodal encoder, self-expressive layer, and multimodal decoder. The encoder takes multimodal data as input and fuses them to a latent space representa…