We propose a deep-learning based method for obtaining standardized data coordinates from scientific measurements.Data observations are modeled as samples from an unknown, non-linear deformation of an underlying Riemannian manifold, which is parametrized by a few normalized latent variables. By leveraging a repeated measurement sampling strategy, we present a method for learning an embedding in $\mathbb{R}^d$ that is isometric to the latent variables of the manifold. These data coordinates, being invariant under smooth changes of variables, enable matching between different instrumental observations of the same phenomenon. Our embedding is obtained using a LOcal Conformal Autoencoder (LOCA), an algorithm that constructs an embedding to rectify deformations by using a local z-scoring procedure while preserving relevant geometric information. We demonstrate the isometric embedding properties of LOCA on various model settings and observe that it exhibits promising interpolation and extrapolation capabilities. Finally, we apply LOCA to single-site Wi-Fi localization data, and to $3$-dimensional curved surface estimation based on a $2$-dimensional projection.
Recent increase in popularity of indoor climbing allows possible applications of deep learning algorthms to classify and generate climbing routes. In this work, we employ a variational autoencoder to climbing routes in a standardized training apparatus MoonBoard, a well-known training tool within the climbing community. By sampling the encoded latent space, it is observed that the algorithm can generate high quality climbing routes. 22 generated problems are uploaded to the Moonboard app for user review. This algorithm could serve as a first step to facilitate indoor climbing route setting.
Southwest Jiaotong University（西南交通大学）；Sichuan University（四川大学）；University of Macau（澳门大学）
The excellent performance of representation learning of autoencoders have attracted considerable interest in various applications. However, the structure and multi-local collaborative relationships of unlabeled data are ignored in their encoding procedure that limits the capability of feature extraction. This paper presents a Multi-local Collaborative AutoEncoder (MC-AE), which consists of novel multi-local collaborative representation RBM (mcrRBM) and multi-local collaborative representation GRBM (mcrGRBM) models. Here, the Locality Sensitive Hashing (LSH) method is used to divide the input d…
ECG Latent Feature Extraction with Autoencoders for Downstream Prediction Tasks
Department of Cardiovascular Medicine, The University of Kansas Medical Center（心血管医学系，堪萨斯医学院）；Department of Electrical Engineering and Computer Science, The University of Kansas（电气工程与计算机科学系，堪萨斯大学）
Amirkabir University of Technology（阿米尔卡比尔理工大学）；Persian Gulf University（波斯湾大学）
Nowadays, deep neural networks are being used in many domains because of their high accuracy results. However, they are considered as "black box", means that they are not explainable for humans. On the other hand, in some tasks such as medical, economic, and self-driving cars, users want the model to be interpretable to decide if they can trust these results or not. In this work, we present a modified version of an autoencoder-based approach for local interpretability called ALIME. The ALIME itself is inspired by a famous method called Local Interpretable Model-agnostic Explanations (LIME). LI…
Local causal states are latent representations that capture organized pattern and structure in complex spatiotemporal systems. We expand their functionality, framing them as spacetime autoencoders. Previously, they were only considered as maps from observable spacetime fields to latent local causal state fields. Here, we show that there is a stochastic decoding that maps back from the latent fields to observable fields. Furthermore, their Markovian properties define a stochastic dynamic in the latent space. Combined with stochastic decoding, this gives a new method for forecasting spacetime fi…
Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples. Inspired by the success of geodesic distance approximators such as ISOMAP, we propose to use a minimum spanning tree (MST), a graph-based algorithm, to approximat…
School of Computer Science（计算机科学学院）；The Interdisciplinary Center, Herzliya（赫兹利亚跨学科中心）
Autoencoders represent an effective approach for computing the underlying factors characterizing datasets of different types. The latent representation of autoencoders have been studied in the context of enabling interpolation between data points by decoding convex combinations of latent vectors. This interpolation, however, often leads to artifacts or produces unrealistic results during reconstruction. We argue that these incongruities are due to the structure of the latent space and because such naively interpolated latent vectors deviate from the data manifold. In this paper, we propose a r…
Top-N recommendation is a challenging problem because complex and sparse user-item interactions should be adequately addressed to achieve high-quality recommendation results. The local latent factor approach has been successfully used with multiple local models to capture diverse user preferences with different sub-communities. However, previous studies have not fully explored the potential of local models, and failed to identify many small and coherent sub-communities. In this paper, we present Local Collaborative Autoencoders (LOCA), a generalized local latent factor framework. Specifically,…
Variational Autoencoders (VAEs) have experienced recent success as data-generating models by using simple architectures that do not require significant fine-tuning of hyperparameters. However, VAEs are known to suffer from over-regularization which can lead to failure to escape local maxima. This phenomenon, known as posterior collapse, prevents learning a meaningful latent encoding of the data. Recent methods have mitigated this issue by deterministically moment-matching an aggregated posterior distribution to an aggregate prior. However, abandoning a probabilistic framework (and thus relying…
This paper presents a parametric variational autoencoder-based human target detection and localization framework working directly with the raw analog-to-digital converter data from the frequency modulated continous wave radar. We propose a parametrically constrained variational autoencoder, with residual and skip connections, capable of generating the clustered and localized target detections on the range-angle image. Furthermore, to circumvent the problem of training the proposed neural network on all possible scenarios using real radar data, we propose domain adaptation strategies whereby we…
Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems
Chandar Research Lab（钱达尔研究实验室）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；University of Pennsylvania（宾夕法尼亚大学）；NVIDIA（英伟达）；Polytechnique Montréal（蒙特利尔理工学院）
Université de Sherbrooke（舍布鲁克大学）；Université Bordeaux（波尔多大学）；CNRS（法国国家科学研究中心）；CEA（法国原子能和替代能源委员会）；Imeka Solutions inc.（Imeka解决方案公司）
Current tractography methods use the local orientation information to propagate streamlines from seed locations. Many such seeds provide streamlines that stop prematurely or fail to map the true white matter pathways because some bundles are "harder-to-track" than others. This results in tractography reconstructions with poor white and gray matter spatial coverage. In this work, we propose a generative, autoencoder-based method, named GESTA (Generative Sampling in Bundle Tractography using Autoencoders), that produces streamlines achieving better spatial coverage. Compared to other deep learni…
Feature selection reduces the dimensionality of data by identifying a subset of the most informative features. In this paper, we propose an innovative framework for unsupervised feature selection, called fractal autoencoders (FAE). It trains a neural network to pinpoint informative features for global exploring of representability and for local excavating of diversity. Architecturally, FAE extends autoencoders by adding a one-to-one scoring layer and a small sub-neural network for feature selection in an unsupervised fashion. With such a concise architecture, FAE achieves state-of-the-art perf…
Leveraging the framework of Optimal Transport, we introduce a new family of generative autoencoders with a learnable prior, called Symmetric Wasserstein Autoencoders (SWAEs). We propose to symmetrically match the joint distributions of the observed data and the latent representation induced by the encoder and the decoder. The resulting algorithm jointly optimizes the modelling losses in both the data and the latent spaces with the loss in the data space leading to the denoising effect. With the symmetric treatment of the data and the latent representation, the algorithm implicitly preserves th…
A Multi-Fidelity Convolutional Autoencoder-Transfer Learning Framework for Guided-Wave-Based Damage Diagnosis Using Large Simulated and Limited Experimental Datasets
Korea University（高丽大学）；Ericsson Research（爱立信研究院）；KTH Royal Institute of Technology（瑞典皇家理工学院）
This letter introduces a new denoiser that modifies the structure of denoising autoencoder (DAE), namely noise learning based DAE (nlDAE). The proposed nlDAE learns the noise of the input data. Then, the denoising is performed by subtracting the regenerated noise from the noisy input. Hence, nlDAE is more effective than DAE when the noise is simpler to regenerate than the original data. To validate the performance of nlDAE, we provide three case studies: signal restoration, symbol demodulation, and precise localization. Numerical results suggest that nlDAE requires smaller latent space dimensi…
UvA-Bosch Delta Lab（阿姆斯特丹大学-博世三角洲实验室）；University of Amsterdam（阿姆斯特丹大学）；ChemEngAI Lab（化学工程人工智能实验室）；Delft University of Technology（代尔夫特理工大学）
Category-selectivity in the brain describes the observation that certain spatially localized areas of the cerebral cortex tend to respond robustly and selectively to stimuli from specific limited categories. One of the most well known examples of category-selectivity is the Fusiform Face Area (FFA), an area of the inferior temporal cortex in primates which responds preferentially to images of faces when compared with objects or other generic stimuli. In this work, we leverage the newly introduced Topographic Variational Autoencoder to model the emergence of such localized category-selectivity …
Enabled by the increasing availability of sensor data monitored from production machinery, condition monitoring and predictive maintenance methods are key pillars for an efficient and robust manufacturing production cycle in the Industrial Internet of Things. The employment of machine learning models to detect and predict deteriorating behavior by analyzing a variety of data collected across several industrial environments shows promising results in recent works, yet also often requires transferring the sensor data to centralized servers located in the cloud. Moreover, although collaborating a…
Kratom (KT) typically exerts antidepressant (AD) effects. However, evaluating which form of KT extracts possesses AD properties similar to the standard AD fluoxetine (flu) remained challenging. Here, we adopted an autoencoder (AE)-based anomaly detector called ANet to measure the similarity of mice's local field potential (LFP) features that responded to KT leave extracts and AD flu. The features that responded to KT syrup had the highest similarity to those that responded to the AD flu at 85.62 $\pm$ 0.29%. This finding presents the higher feasibility of using KT syrup as an alternative subst…
Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approach
University of Cambridge（剑桥大学）；Real-Time and Embedded Computing Systems Research Centre (CISTER)（实时与嵌入式计算系统研究中心（CISTER））；CyLab Security and Privacy Institute, Carnegie Mellon University（卡内基梅隆大学CyLab安全与隐私研究所）；Commonwealth Scientific and Industrial Research Organization (CSIRO)（联邦科学与工业研究组织（CSIRO））；Koç University（科奇大学）；Princeton University（普林斯顿大学）
The classical sparse coding model represents visual stimuli as a linear combination of a handful of learned basis functions that are Gabor-like when trained on natural image data. However, the Gabor-like filters learned by classical sparse coding far overpredict well-tuned simple cell receptive field (SCRF) profiles. A number of subsequent models have either discarded the sparse dictionary learning framework entirely or have yet to take advantage of the surge in unrolled, neural dictionary learning architectures. A key missing theme of these updates is a stronger notion of \emph{structured spa…
A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder
CyLab Security and Privacy Institute, Carnegie Mellon University（卡内基梅隆大学CyLab安全与隐私研究所）；Real-Time and Embedded Computing Systems Research Centre (CISTER)（实时与嵌入式计算系统研究中心（CISTER））；Commonwealth Scientific and Industrial Research Organization (CSIRO)（英联邦科学与工业研究组织（CSIRO））；University of Cambridge（剑桥大学）；Alan Turing Institute（阿兰·图灵研究所）
