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.
Autoencoders compress and reconstruct data for various applications.
Imbalanced data classification problem has always been a popular topic in the field of machine learning research. In order to balance the samples between majority and minority class. Oversampling algorithm is used to synthesize new minority class samples, but it could bring in noise. Pointing to the noise problems, thi…
Spectrum management and resource allocation (RA) problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks. The traditional approaches for solving such problems usually consume time and memory, especially for large size problems. Recently different ma…
Sigmoid autoencoders can implement associative memory with certain conditions.
Random forest and deep neural network are two schools of effective classification methods in machine learning. While the random forest is robust irrespective of the data domain, the deep neural network has advantages in handling high dimensional data. In view that a differentiable neural decision forest can be added to…
Detects adversarial examples using autoencoders at hidden layers.
The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of inductive bias that constrains the functions learned through the optimization process to concentrate a…
Variational autoencoders often collapse, showing latent variables are non-identifiable.
A new model for multiview data analysis using graph autoencoders.
Currently there are two predominant ways to train deep neural networks. The first one uses restricted Boltzmann machine (RBM) and the second one autoencoders. RBMs are stacked in layers to form deep belief network (DBN); the final representation layer is attached to the target to complete the deep neural network. Autoe…
Regularization preserves topological data structure in autoencoders.
In this short paper, a neural network that is able to form a low dimensional topological hidden representation is explained. The neural network can be trained as an autoencoder, a classifier or mix of both, and produces different low dimensional topological map for each of them. When it is trained as an autoencoder, th…
AEGCN uses autoencoder constraints to improve graph node classification.
Probabilistic deep learning uses neural networks and models to handle uncertainty.
Improves stability in hyperbolic neural networks for complex data generation.
The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoencoders) to fit deep neural networks. From a machine learning perspective, the resulting structure, an atlas of a manifold, may be viewed as …
Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep neural networks trained using standard optimization methods implement such a mechanism for real-valued…
New method denoises and fills in missing image data without clean training data.
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop…
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our method masks the autoencoder's parameters to respect autoregressive constraints: ea…
DefenseVGAE defends graph neural networks against adversarial attacks.
Neuro-Evolution is a field of study that has recently gained significantly increased traction in the deep learning community. It combines deep neural networks and evolutionary algorithms to improve and/or automate the construction of neural networks. Recent Neuro-Evolution approaches have shown promising results, rival…
Customer temporal behavioral data was represented as images in order to perform churn prediction by leveraging deep learning architectures prominent in image classification. Supervised learning was performed on labeled data of over 6 million customers using deep convolutional neural networks, which achieved an AUC of 0…
ALF reduces network parameters and operations by 70% and 61%, respectively, on embedded hardware.
FisherNet extends Autoencoder using Fisher information for better data reconstruction.
Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based attacks: The Fast Gradient Sign attack and Fast Gradient attack. First we use an …
Study on dynamics of non-linear autoencoders learning principal components.
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…
Autoencoder neural networks reconstruct missing indoor environment data.
Superposition in autoencoders leads to loss in simple models.
In this paper we describe the problem of painter classification, and propose a novel approach based on deep convolutional autoencoder neural networks. While previous approaches relied on image processing and manual feature extraction from paintings, our approach operates on the raw pixel level, without any preprocessin…
Study introduces UEBA framework using Deep Autoencoders for anomaly detection.
SidAE combines autoencoders and Siamese networks for self-supervised feature extraction.
This paper introduces structure learning for autoencoder recommenders to improve performance and generalization.
Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental…
A new deep clustering model learns both clustering and embedding simultaneously.
The study explores the compressive power of Boolean threshold autoencoders, finding that seven layers are necessary but three are not.
Batch normalization with regularization turns deterministic autoencoders into generative models.
Proposes a neural network autoencoder for smoothing and representation learning of functional data.
Gene expression profiles have been widely used to characterize patterns of cellular responses to diseases. As data becomes available, scalable learning toolkits become essential to processing large datasets using deep learning models to model complex biological processes. We present an autoencoder to capture nonlinear …
DMAE uses neural networks to cluster data with flexible dissimilarity functions.
Smooth embedding space improves NAS performance.
Bidirectional VAE reduces parameters and improves image tasks.
Autoencoders misidentify anomalies due to data topology.
VAEs analyzed using harmonic analysis, showing how variance controls frequency content and robustness.
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…
Proposes CXNs for neural network computations on cell complexes.
Inspired by the success of deep learning techniques in the physical and chemical sciences, we apply a modification of an autoencoder type deep neural network to the task of dimension reduction of molecular dynamics data. We can show that our time-lagged autoencoder reliably finds low-dimensional embeddings for high-dim…