Predictive coding, variational autoencoders, and biological connections
J Marino - Neural Computation, 2022 - direct.mit.edu
We present a review of predictive coding, from theoretical neuroscience, and variational
autoencoders, from machine learning, identifying the common origin and mathematical …
autoencoders, from machine learning, identifying the common origin and mathematical …
Human worker activity recognition in a production floor environment through deep learning
A Mastakouris, G Andriosopoulou, D Masouros… - Journal of Manufacturing …, 2023 - Elsevier
One of the aims of the 4th industrial revolution is to seamlessly connect equipment and
personnel to enable a greater level of collaboration, which in turn will result in higher …
personnel to enable a greater level of collaboration, which in turn will result in higher …
Estimating model uncertainty of neural networks in sparse information form
We present a sparse representation of model uncertainty for Deep Neural Networks (DNNs)
where the parameter posterior is approximated with an inverse formulation of the …
where the parameter posterior is approximated with an inverse formulation of the …
On Implicit Regularization in -VAEs
While the impact of variational inference (VI) on posterior inference in a fixed generative
model is well-characterized, its role in regularizing a learned generative model when used …
model is well-characterized, its role in regularizing a learned generative model when used …
Laplacian autoencoders for learning stochastic representations
Established methods for unsupervised representation learning such as variational
autoencoders produce none or poorly calibrated uncertainty estimates making it difficult to …
autoencoders produce none or poorly calibrated uncertainty estimates making it difficult to …
Lifelong generative modelling using dynamic expansion graph model
Abstract Variational Autoencoders (VAEs) suffer from degenerated performance, when
learning several successive tasks. This is caused by catastrophic forgetting. In order to …
learning several successive tasks. This is caused by catastrophic forgetting. In order to …
Evolutionary variational optimization of generative models
J Drefs, E Guiraud, J Lücke - Journal of machine learning research, 2022 - jmlr.org
We combine two popular optimization approaches to derive learning algorithms for
generative models: variational optimization and evolutionary algorithms. The combination is …
generative models: variational optimization and evolutionary algorithms. The combination is …
An efficient difference-of-convex solver for privacy funnel
TH Huang, H El Gamal - 2024 IEEE International Symposium …, 2024 - ieeexplore.ieee.org
We propose an efficient solver for the privacy funnel (PF) method, leveraging its difference-of-
convex (DC) structure. The proposed DC separation results in a closed-form update …
convex (DC) structure. The proposed DC separation results in a closed-form update …
Network intrusion detection system based on conditional variational laplace autoencoder
S Azmin, ABMAA Islam - Proceedings of the 7th International Conference …, 2020 - dl.acm.org
Network Intrusion Detection System (NIDS) is an important tool for network administrators to
detect security breaches in a network. However, due to the diversity of attacks and …
detect security breaches in a network. However, due to the diversity of attacks and …
Isometric autoencoders
High dimensional data is often assumed to be concentrated on or near a low-dimensional
manifold. Autoencoders (AE) is a popular technique to learn representations of such data by …
manifold. Autoencoders (AE) is a popular technique to learn representations of such data by …