The paper identifies saddlepoints in unsupervised auto-encoding neural nets.
problem The risk landscape of unsupervised least squares in auto-encoding neural nets.
method Established an equivalence between unsupervised least squares and principal manifolds, discussed regularization strategies for auto-encoders.
result All non-trivial critical points in auto-encoding are saddlepoints, which are degenerate in overcomplete auto-encoding.
A novel cross-modal auto-encoder associates different data types efficiently.
problem Cross-modal data association in heterogeneous datasets.
method Bayesian inference framework with variational auto-encoders and associators.
result Successfully associates visual and auditory data with minimal paired data.
Improved neural topic model for semi-supervised learning.
problem Representing textual data in an interpretable manner with limited labeled data.
method Label-Indexed Neural Topic Model (LI-NTM) that combines deep generative models with semi-supervised learning.
result LI-NTM outperforms existing models in document reconstruction and classifier performance.
Auto-encoding is an important task which is typically realized by deep neural networks (DNNs) such as convolutional neural networks (CNN). In this paper, we propose EncoderForest (abbrv. eForest), the first tree ensemble based auto-encoder. We present a procedure for enabling forests to do backward reconstruction by ut…
In this paper, we present a novel approach for initializing deep neural networks, i.e., by turning PCA into neural layers. Usually, the initialization of the weights of a deep neural network is done in one of the three following ways: 1) with random values, 2) layer-wise, usually as Deep Belief Network or as auto-encod…
New method uses neural networks to interpolate stellar atmospheres with high precision.
problem Recover precise stellar model atmospheres from grids of models.
method Deep neural network with 1D convolutional auto-encoder for feature extraction.
result Higher precision compared to traditional methods.
We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Our approach relies on the efficiency of sequential Monte Carlo (SMC) for performing inference in st…
Convolutional auto-encoders learn natural exponential family distributions.
problem Learning latent variables for non-Gaussian data.
method Inspired by CDL, combines CNN and deep learning for natural exponential family data.
result Improved unsupervised and competitive supervised performance.
Paper proposes a new method for learning deep generative models using annealed importance sampling.
problem Learning deep generative models efficiently and accurately.
method Proposes annealed importance sampling as a bridge between variational inference and Markov chain Monte Carlo.
result Demonstrates improved density models and better trade-off between computation and model accuracy.
Paper introduces a new framework combining deep learning and logic for relational data.
problem Scalability and flexibility of deep learning methods for relational data.
method Combines auto-encoding principle with first-order logic and logic programs.
result Latent representations are more accurate, flexible, and interpretable.
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural netw…
Novel framework evaluates deep learning models under distribution shift.
problem Evaluating robustness and generalization of deep learning models under distribution shift.
method Variational Inference, Auto-Encoding Variational Bayes, Variational Gaussian Mixture Model, Wasserstein distance.
result Popular CNN architectures and Bayesian CNN models robustness and generalization under distribution shift are assessed.
Deep neural networks map brain lesions to deficits for better brain function understanding.
problem Mapping the functional brain organization from pathological lesions.
method Deep generative neural network architectures, specifically variational convolutional volumetric auto-encoders.
result Our model outperforms established methods in lesion-deficit inference across various scenarios.
New bounds enable training of probabilistic models for deep networks.
problem Training scalable latent variable models for deep networks.
method Introducing new variational bounds for specific output layers of neural networks.
result Analytical bounds for certain output layers allow training without re-parameterization or Monte Carlo approximations.
WWAE improves deep generative models by minimizing penalized optimal transport.
problem Challenges in learning deep generative models, such as blurriness in variational auto-encoders and instability in generative adversarial networks.
method WWAE formulates as minimization of penalized optimal transport between target and generated distributions. It uses closed-form squared Wasserstein-2 distance for Gaussians.
result WWAE learns better latent structures and generates higher quality samples than VAEs and GANs.
Unbiased gradient estimation improves VAE performance.
problem Training VAEs via maximum likelihood is difficult due to intractable integrals.
method Introduced unbiased estimators of the log-likelihood gradient using coupled Markov chains.
result Unbiased estimators lead to better predictive performance in VAEs.
Researchers use VAEs to create understandable heart beat representations.
problem Lack of explainable models for ECG beat classification.
method Variational Auto-Encoders (VAEs) with linear dense networks.
result Interpretable ECG beat space generated.
The paper investigates instance-based interpretation methods for VAEs.
problem Understanding how VAEs make predictions without supervision.
method Formally framed influence functions for VAEs and developed VAE-TracIn.
result Varying training samples significantly impacts VAE predictions.
RandNet learns from compressed image data, improving efficiency and accuracy.
problem Efficiency and accuracy in training neural networks with large datasets.
method RandNet uses compressed random measurements of images to train neural networks efficiently.
result RandNet achieves comparable accuracy to full data training with minimal loss.
EGAE improves graph clustering by utilizing GAE's representations in a way consistent with relaxed k-means theory.
problem Improving graph clustering performance using unsupervised methods.
method Designing an Embedding Graph Auto-Encoder (EGAE) that aligns with theoretical relaxed k-means to learn explainable representations.
result EGAE achieves superior graph clustering results compared to existing methods.
Neural Physicist learns physical dynamics from images.
problem Learning meaningful physical state representations and accurate state transitions from image sequences.
method Neural Physicist uses VAE for state extraction, NP for parameters, and SSM for dynamics.
result Achieves long-term predictions and identifies system degrees of freedom.
Paper proposes robust generative models using VAEs.
problem Lack of robustness in generative models.
method Formally defined robust lower bound, optimized during training.
result Generative models become more robust to adversarial attacks.
The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiti…
A deep clustering method for hyperspectral images improves clustering performance by constraining intra-class distances.
problem Clustering performance degradation in hyperspectral images due to high dimensionality.
method Intra-class distance constrained deep clustering algorithm using auto-encoder network.
result The proposed algorithm outperforms state-of-the-art methods in clustering hyperspectral images.
New methods improve Fisher Matrix approximations for neural networks at low cost.
problem High cost of solving Fisher Information Matrix (FIM) in neural networks.
method Direct minimization via Kronecker product singular value decomposition.
result Improved approximations to FIM provide more accurate and faster optimization.
Recent works investigated the generalization properties in deep neural networks (DNNs) by studying the Information Bottleneck in DNNs. However, the mea- surement of the mutual information (MI) is often inaccurate due to the density estimation. To address this issue, we propose to measure the dependency instead of MI be…
New distribution on simplex for auto-encoding tasks.
problem Developing a new distribution for sparsity in auto-encoding models.
method Using Kumaraswamy distribution and ordered stick-breaking process.
result The new distribution has an exact and closed form reparameterization.
DCFSC uses a simple auto-encoder for subspace clustering without parameters.
problem Subspace clustering for large-scale high-dimensional datasets.
method Closed-form shallow auto-encoder for data-driven self-expressive layer, no parameters or optimization.
result Significant memory benefits over existing methods on large datasets.
Improved anomaly detection in time series data using kervolutional neural networks.
problem Anomaly detection in time series data.
method Mixed kervolutional and convolutional layers in a temporal auto-encoder.
result The mixed model detects anomalies more sensitively in time series data.
CGDL improves open set recognition by learning conditional Gaussian distributions.
problem Handling unknown samples in real-world recognition tasks.
method Conditional Gaussian Distribution Learning (CGDL) with probabilistic ladder architecture.
result CGDL significantly outperforms baseline methods on standard image datasets.
DIVA clusters dynamic data without needing cluster count, outperforming baselines.
problem Clustering complex, dynamic data without prior knowledge of cluster count.
method Nonparametric Dirichlet Process Mixtures with memoized online variational inference.
result DIVA outperforms state-of-the-art in classifying complex data with changing features.
Deep learning reconstructs pressure fields and classifies leakage rates in CCS storage sites.
problem Monitoring CO2 leakage in CCS storage sites.
method Variational auto-encoder tailored for pressure field reconstruction and leakage rate classification.
result Uncertainty estimates of predictions illustrated on synthetic data.
AEVB improves understanding of latent variable models.
problem Training latent variable models efficiently and understanding their limitations.
method Motivates AEVB from EM, emphasizing approximate E-step and M-step.
result AEVB tightens ELBO, improving model training.
In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in achieving binarization simulation, variable bit rates with multiple networks, entropy-friendly representations, inference-stage code optimiz…
Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper contributes to the mathematical understanding of this phenomenon and helps define better justified sampling algorithms for deep learning based on auto-encoder v…
ODE2VAE learns latent dynamics for sequential data.
problem Learning latent dynamics for high-dimensional sequential data.
method Deep generative second order ODE model with Bayesian neural networks.
result State-of-the-art performance in long-term motion prediction and imputation.
Automatic recognition of human activities from time-series sensor data (referred to as HAR) is a growing area of research in ubiquitous computing. Most recent research in the field adopts supervised deep learning paradigms to automate extraction of intrinsic features from raw signal inputs and addresses HAR as a multi-…
Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation. In modern manufacturing systems, data-driven machine health monitoring is gaining …
Proposes a new method to learn data representations by modeling sample relations.
problem Lack of rich latent structural information in DAEs.
method Explicitly models and leverages sample relations as supervision for representation learning.
result Significantly improves clustering performance on benchmark datasets.
Wind speed prediction improved using a novel deep ensemble learning model inspired by jet aerodynamics.
problem Accurate wind speed forecasting for renewable energy production.
method Proposes a novel Deep Ensemble Learning using Jet-like Architecture (DEL-Jet) to enhance robustness and generalization of a learning system.
result The DEL-Jet technique improves the robustness and generalization of the learning system, as shown by performance evaluations.
Graph neural network constructs a sparse latent point cloud from dense point clouds.
problem Efficiently reconstructing and simulating point clouds with fine details.
method Irregular graph convolutional neural network with non-isotropic operations.
result The model can reconstruct dense point clouds from a sparse latent representation.
Graph auto-encoder predicts unobserved node features from biological networks and omics data.
problem Integrating biological networks and continuous node features for better prediction.
method Graph neural networks and feature auto-encoders trained on feature reconstruction.
result Graph feature auto-encoder outperforms auto-encoders trained on graph reconstruction for predicting unobserved node features.
Graph attention auto-encoder reconstructs graph structure and attributes.
problem Lack of methods to reconstruct graph structure and node attributes in graph auto-encoders.
method Stacked encoder/decoder layers with self-attention mechanisms, regularized node representations to reconstruct graph structure.
result Competitive performance on node classification benchmarks, including inductive learning.
Paper proposes a method to learn structure from data similarities.
problem Learning hidden structures in data beyond low-rank and sparsity.
method Explicitly models data relation, retaining pairwise similarities.
result Framework significantly improves performance on clustering and semisupervised classification.
A new method uses persistent homology to assess auto-encoders' latent manifold quality.
problem Chaos in auto-encoders' latent manifold and failure of current distance measures.
method Persistent Homology for Wasserstein Auto-Encoders (PHom-WAE).
result PHom-WAE improves auto-encoders' performance in credit card transaction data.
Paper improves VAEs using Monte Carlo methods.
problem Improving the Evidence Lower Bound (ELBO) for VAEs.
method Uses Monte Carlo techniques to improve ELBO, specifically Sequential Importance Sampling (SIS) with carefully chosen kernels.
result Demonstrates improved performance on various applications.
This paper proposes a set of new error criteria and learning approaches, Adaptive Normalized Risk-Averting Training (ANRAT), to attack the non-convex optimization problem in training deep neural networks (DNNs). Theoretically, we demonstrate its effectiveness on global and local convexity lower-bounded by the standard …
Machine Learning on graph-structured data is an important and omnipresent task for a vast variety of applications including anomaly detection and dynamic network analysis. In this paper, a deep generative model is introduced to capture continuous probability densities corresponding to the nodes of an arbitrary graph. I…