Search Results for author:
Found 18 papers, 1 papers with code
Continual Learning: Applications and the Road Forward
Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past.
Large-scale gradient-based training of Mixtures of Factor Analyzers
The Mixture of Factor analyzers (MFA) model is an important extension of GMMs, which allows to smoothly interpolate between diagonal and full CMs based on the number of \textit{factor loadings} $l$.
Adiabatic replay for continual learning
In this proof-of-concept study, we propose a replay-based CL strategy that we term adiabatic replay (AR), which derives its efficiency from the (reasonable) assumption that each new learning phase is adiabatic, i. e., represents only a small addition to existing knowledge.
A Framework for the Automated Parameterization of a Sensorless Bearing Fault Detection Pipeline
The present work contributes to the research of fault detection on rotating machinery in the following terms: (1) Reduction of the human induced bias to the data science process, while still considering expert and task related knowledge, ending in a generic search approach (2) tackling the bearing fault detection task without the need for external sensors (sensorless) (3) learning a domain robust fault detection pipeline applicable to varying motor operating parameters without the need of re-parameterizations or fine-tuning (4) investigations on working condition discrepancies with an excessive degree to determine the pipeline limitations regarding the abstraction of the motor parameters and the pipeline hyperparameters
Beyond Supervised Continual Learning: a Review
Continual Learning (CL, sometimes also termed incremental learning) is a flavor of machine learning where the usual assumption of stationary data distribution is relaxed or omitted.
A Study of Continual Learning Methods for Q-Learning
We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario, which, to the best of our knowledge, has not been described before.
A new perspective on probabilistic image modeling
We present the Deep Convolutional Gaussian Mixture Model (DCGMM), a new probabilistic approach for image modeling capable of density estimation, sampling and tractable inference.
An Investigation of Replay-based Approaches for Continual Learning
We find that the impact of sample selection increases when a smaller number of samples is stored.
Continual Learning with Fully Probabilistic Models
As a concrete realization of generative continual learning, we propose Gaussian Mixture Replay (GMR).
Overcoming Catastrophic Forgetting with Gaussian Mixture Replay
In addition, task boundaries can be detected by applying GMM density estimation.
Image Modeling with Deep Convolutional Gaussian Mixture Models
For generating sharp images with DCGMMs, we introduce a new gradient-based technique for sampling through non-invertible operations like convolution and pooling.
A Rigorous Link Between Self-Organizing Maps and Gaussian Mixture Models
This work presents a mathematical treatment of the relation between Self-Organizing Maps (SOMs) and Gaussian Mixture Models (GMMs).
Gradient-based training of Gaussian Mixture Models for High-Dimensional Streaming Data
We present an approach for efficiently training Gaussian Mixture Model (GMM) by Stochastic Gradient Descent (SGD) with non-stationary, high-dimensional streaming data.
Gradient-based training of Gaussian Mixture Models in High-Dimensional Spaces
We present an approach for efficiently training Gaussian Mixture Models (GMMs) with Stochastic Gradient Descent (SGD) on large amounts of high-dimensional data (e. g., images).
A Study of Deep Learning for Network Traffic Data Forecasting
We present a study of deep learning applied to the domain of network traffic data forecasting.
Marginal Replay vs Conditional Replay for Continual Learning
We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class.
A pragmatic approach to multi-class classification
We present a novel hierarchical approach to multi-class classification which is generic in that it can be applied to different classification models (e. g., support vector machines, perceptrons), and makes no explicit assumptions about the probabilistic structure of the problem as it is usually done in multi-class classification.
A simple technique for improving multi-class classification with neural networks
We present a novel method to perform multi-class pattern classification with neural networks and test it on a challenging 3D hand gesture recognition problem.
