Budget Restricted Incremental Learning with Pre-Trained Convolutional Neural Networks and Binary Associative Memories
Sign Up to like & getrecommendations! Published in 2019 at "Journal of Signal Processing Systems"
DOI: 10.1007/s11265-019-01450-z
Abstract: For the past few years, Deep Neural Networks (DNNs) have achieved state-of-art performance in numerous challenging domains. To reach this performance, DNNs consist in large sets of parameters and complex architectures, which are trained offline… read more here.
Keywords: incremental learning; neural networks; binary associative; associative memories ... See more keywords
Cerebellar plasticity and associative memories are controlled by perineuronal nets
Sign Up to like & getrecommendations! Published in 2020 at "Proceedings of the National Academy of Sciences of the United States of America"
DOI: 10.1073/pnas.1916163117
Abstract: Significance Understanding mechanisms underlying learning and memory is crucial in view of tackling cognitive decline occurring during aging or following neurological disorders. The cerebellum offers an ideal system to achieve this goal because of the… read more here.
Keywords: pnns; cerebellar plasticity; associative memories; motor ... See more keywords
Thermodynamics of bidirectional associative memories
Sign Up to like & getrecommendations! Published in 2022 at "Journal of Physics A: Mathematical and Theoretical"
DOI: 10.1088/1751-8121/accc60
Abstract: In this paper we investigate the equilibrium properties of bidirectional associative memories (BAMs). Introduced by Kosko in 1988 as a generalization of the Hopfield model to a bipartite structure, the simplest architecture is defined by… read more here.
Keywords: physics; thermodynamics; associative memories; thermodynamics bidirectional ... See more keywords
Design and Analysis of Quaternion-Valued Neural Networks for Associative Memories
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Transactions on Systems, Man, and Cybernetics: Systems"
DOI: 10.1109/tsmc.2017.2717866
Abstract: This paper addresses the problem of designing associative memories based on quaternion-valued neural networks (QVNNs). A system designing procedure for QVNNs is developed by employing quaternion matrix decomposition, and a given set of states can… read more here.
Keywords: quaternion; valued neural; neural networks; quaternion valued ... See more keywords