A Modulation Layer to Increase Neural Network Robustness Against Data Quality Issues

M Abdelhack, J Zhang, S Tripathi, BA Fritz… - arXiv preprint arXiv …, 2021 - arxiv.org
Data missingness and quality are common problems in machine learning, especially for
high-stakes applications such as healthcare. Developers often train machine learning …

Combined model for sensory-based and feedback-based task switching: Solving hierarchical reinforcement learning problems statically and dynamically with transfer …

N Khan, J Phillips - … on Tools with Artificial Intelligence (ICTAI), 2020 - ieeexplore.ieee.org
An integral function of fully autonomous robots and humans is the ability to focus attention
on a few relevant percepts to reach a certain goal while disregarding irrelevant percepts …

A Neurobiologically-inspired Deep Learning Framework for Autonomous Context Learning

DW Ludwig, LW Remedios… - 2021 IEEE 33rd …, 2021 - ieeexplore.ieee.org
Neurobiologically-inspired working memory models demonstrate human/animal capabilities
to rapidly adapt and alter responses to the environment via context-switching and error …

Combined Model for Partially-Observable and Non-Observable Task Switching: Solving Hierarchical Reinforcement Learning Problems Statically and Dynamically …

N Khan, J Phillips - arXiv preprint arXiv:1911.10425, 2019 - arxiv.org
An integral function of fully autonomous robots and humans is the ability to focus attention
on a few relevant percepts to reach a certain goal while disregarding irrelevant percepts …

Holographic Reduced Representations for Dimensional Attention Learning

H Wang - 2019 - search.proquest.com
One aspect of machine learning is that it has sought to mimic how the brain learns. In 1992,
Kruschke published a computer model called ALCOVE which sought to model category …

[引用][C] Microagent Convergence Testing using Stacked Holographic Reduced Representations

J Goble