A bio-inspired incremental learning architecture for applied perceptual problems

A Gepperth, C Karaoguz - Cognitive Computation, 2016 - Springer
We present a biologically inspired architecture for incremental learning that remains
resource-efficient even in the face of very high data dimensionalities (> 1000) that are …

Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Maps

H Vaidya, T Desell, A Mali, A Ororbia - arxiv preprint arxiv:2402.12465, 2024 - arxiv.org
An intelligent system capable of continual learning is one that can process and extract
knowledge from potentially infinitely long streams of pattern vectors. The major challenge …

A generative learning approach to sensor fusion and change detection

ART Gepperth, T Hecht, M Gogate - Cognitive Computation, 2016 - Springer
We present a system for performing multi-sensor fusion that learns from experience, ie, from
training data and propose that learning methods are the most appropriate approaches to …

Incremental learning with self-organizing maps

A Gepperth, C Karaoguz - 2017 12th International Workshop …, 2017 - ieeexplore.ieee.org
We present a novel use for self-organizing maps (SOMs) as an essential building block for
incremental learning algorithms. SOMs are very well suited for this purpose because they …

Reducing catastrophic forgetting in self organizing maps with internally-induced generative replay (student abstract)

H Vaidya, T Desell, AG Ororbia - … of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
A lifelong learning agent is able to continually learn from potentially infinite streams of
pattern sensory data. One major historic difficulty in building agents that adapt in this way is …

Incremental learning with a homeostatic self-organizing neural model

A Gepperth - Neural Computing and Applications, 2020 - Springer
We present a new self-organized neural model that we term resilient self-organizing tissue
(ReST), which can be run as a convolutional neural network, possesses ac^ ∞ c∞ energy …

Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay

H Vaidya, T Desell, A Ororbia - arxiv preprint arxiv:2112.04728, 2021 - arxiv.org
A lifelong learning agent is able to continually learn from potentially infinite streams of
pattern sensory data. One major historic difficulty in building agents that adapt in this way is …

[ΒΙΒΛΙΟ][B] Reducing Catastrophic Forgetting in Self-Organizing Maps

HUM Vaidya - 2021 - search.proquest.com
An agent that is capable of continual or lifelong learning is able to continuously learn from
potentially infinite streams of pattern sensory data. One major historic difficulty in building …

New learning paradigms for real-world environment perception

A Gepperth - 2016 - hal.science
In this document, I first analyze some of the reasons why real-world environment perception
is still strongly inferior to human perception in overall accuracy and reliability. In particular, I …