scholarly journals Generating In-Between Images Through Learned Latent Space Representation Using Variational Autoencoders

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 149456-149467
Author(s):  
Paulino Cristovao ◽  
Hidemoto Nakada ◽  
Yusuke Tanimura ◽  
Hideki Asoh
Keyword(s):  
Space Representation ◽  
Latent Space

scholarly journals Non-negative sparse Laplacian regularized latent multi-view subspace clustering

2021 ◽  
Vol 15 ◽  
pp. 174830262110249
Author(s):  
Cong-Zhe You ◽  
Zhen-Qiu Shu ◽  
Hong-Hui Fan
Keyword(s):  
Subspace Clustering ◽  
Structural Features ◽  
Space Representation ◽  
Graph Regularization ◽  
Structure Information ◽  
Cluster Data ◽  
Latent Space ◽  
Low Dimensional ◽  
Relationship Of ◽  
The Relationship

Recently, in the area of artificial intelligence and machine learning, subspace clustering of multi-view data is a research hotspot. The goal is to divide data samples from different sources into different groups. We proposed a new subspace clustering method for multi-view data which termed as Non-negative Sparse Laplacian regularized Latent Multi-view Subspace Clustering (NSL2MSC) in this paper. The method proposed in this paper learns the latent space representation of multi view data samples, and performs the data reconstruction on the latent space. The algorithm can cluster data in the latent representation space and use the relationship of different views. However, the traditional representation-based method does not consider the non-linear geometry inside the data, and may lose the local and similar information between the data in the learning process. By using the graph regularization method, we can not only capture the global low dimensional structural features of data, but also fully capture the nonlinear geometric structure information of data. The experimental results show that the proposed method is effective and its performance is better than most of the existing alternatives.

Speed Adaptation in Learning from Demonstration through Latent Space Formulation

Robotica ◽  
2019 ◽  
Vol 38 (10) ◽  
pp. 1867-1879 ◽  
Author(s):  
Maria Koskinopoulou ◽  
Michail Maniadakis ◽  
Panos Trahanias
Keyword(s):  
Human Robot Interaction ◽  
Space Representation ◽  
Learning From Demonstration ◽  
Level Control ◽  
Physical Constraints ◽  
Spatial Features ◽  
Spatial Consistency ◽  
Latent Space ◽  
Space Formulation ◽  
High Level

SUMMARYPerforming actions in a timely manner is an indispensable aspect in everyday human activities. Accordingly, it has to be present in robotic systems if they are going to seamlessly interact with humans. The current work addresses the problem of learning both the spatial and temporal characteristics of human motions from observation. We formulate learning as a mapping between two worlds (the observed and the action ones). This mapping is realized via an abstract intermediate representation termed “Latent Space.” Learned actions can be subsequently invoked in the context of more complex human–robot interaction (HRI) scenarios. Unlike previous learning from demonstration (LfD) methods that cope only with the spatial features of an action, the formulated scheme effectively encompasses spatial and temporal aspects. Learned actions are reproduced under the high-level control of a time-informed task planner. During the implementation of the studied scenarios, temporal and physical constraints may impose speed adaptations in the reproduced actions. The employed latent space representation readily supports such variations, giving rise to novel actions in the temporal domain. Experimental results demonstrate the effectiveness of the proposed scheme in the implementation of HRI scenarios. Finally, a set of well-defined evaluation metrics are introduced to assess the validity of the proposed approach considering the temporal and spatial consistency of the reproduced behaviors.

scholarly journals INTRUSION DETECTION IN COMPUTER NETWORKS USING LATENT SPACE REPRESENTATION AND MACHINE LEARNING

2020 ◽  
pp. 442-448
Author(s):  
Vladyslav Hamolia ◽  
Viktor Melnyk ◽  
Pavlo Zhezhnych ◽  
Anna Shilinh
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Short Term Memory ◽  
Detection System ◽  
Feature Space ◽  
Space Representation ◽  
History Of Research ◽  
Latent Space ◽  
History Of

Anomaly detection (AD) identifies samples that are not related to the overall distribution in the feature space. This problem has a long history of research through diverse methods, including statistical and modern Deep Neural Networks (DNN) methods. Non-trivial tasks such as covering ambiguous user actions and the complexity of standard algorithms challenged researchers. This article discusses the results of introducing an intrusion detection system using a machine learning (ML) approach. We compared these results with the characteristics of the most common existing rule-based Snort system. Signature Based Intrusion Detection System (SBIDS) has critical limitations well observed in a large number of previous studies. The crucial disadvantage is the limited variety of the same attack type due to the predetermination of all the rules. DNN solves this problem with long short-term memory (LSTM). However, requiring the amount of data and resources for training, this solution is not suitable for a real-world system. This necessitated a compromise solution based on DNN and latent space techniques.

scholarly journals Deciphering protein evolution and fitness landscapes with latent space models

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
Xinqiang Ding ◽  
Zhengting Zou ◽  
Charles L. Brooks III
Keyword(s):  
Protein Evolution ◽  
Fitness Landscape ◽  
Dimensional Space ◽  
Gaussian Process Regression ◽  
Protein Sequences ◽  
Fitness Landscapes ◽  
Space Representation ◽  
Latent Space ◽  
Low Dimensional ◽  
Latent Space Models

AbstractProtein sequences contain rich information about protein evolution, fitness landscapes, and stability. Here we investigate how latent space models trained using variational auto-encoders can infer these properties from sequences. Using both simulated and real sequences, we show that the low dimensional latent space representation of sequences, calculated using the encoder model, captures both evolutionary and ancestral relationships between sequences. Together with experimental fitness data and Gaussian process regression, the latent space representation also enables learning the protein fitness landscape in a continuous low dimensional space. Moreover, the model is also useful in predicting protein mutational stability landscapes and quantifying the importance of stability in shaping protein evolution. Overall, we illustrate that the latent space models learned using variational auto-encoders provide a mechanism for exploration of the rich data contained in protein sequences regarding evolution, fitness and stability and hence are well-suited to help guide protein engineering efforts.

scholarly journals Non-linearity matters: a deep learning solution to generalization of hidden brain patterns across population cohorts

2021 ◽  
Author(s):  
Mariam Zabihi ◽  
Seyed Mostafa Kia ◽  
Thomas Wolfers ◽  
Richard Dinga ◽  
Alberto Llera ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fmri Data ◽  
Space Representation ◽  
Model Parameters ◽  
Independent Dataset ◽  
Latent Space ◽  
Human Connectome Project ◽  
Nonlinear Features ◽  
Latent Representations ◽  
High Level

AbstractThe increasing number of neuroimaging scans in recent years has facilitated the use of complex nonlinear approaches to analyzing such data. More specifically, deep learning, which has been previously hindered by the curse of dimensionality is now feasible. However, it remains challenging to use these techniques develop reliable biomarkers and find an optimal representation of data that explains the biological underpinnings of the mental disorders Here, we employed a 3-dimensional autoencoder with an architecture designed from the ground up for task-fMRI data. Our study presented a coherent strategy for optimizing model parameters and architecture and a method for visualizing and interpreting the latent space representation. We trained our model with multi-task fMRI data derived from the Human Connectome Project (HCP) that provides whole-brain coverage across a range of cognitive tasks. Next, in a transfer learning setting, we tested the generalization of our latent space on UK Biobank data as an independent dataset. We showed that the model did not only learn salient features such as age but also high-level behavioral characteristics and that this representation was highly generic and generalizable to an independent dataset. Furthermore, we demonstrated that the projection of latent space back into the original space is meaningful and interpretable. Finally, our results show that with careful implementation, nonlinear features can provide complementary information that accessible to purely linear methods. Our results provide an important step toward learning interpretable and generalizable latent representations that link cognition with underlying brain systems.

Sign in / Sign up

Export Citation Format

Share Document