AIMC Topic: Association Learning

Clear Filters Showing 1 to 10 of 26 articles

Generalization and differentiation of affective associative memory circuit based on memristive neural network with emotion transfer.

Neural networks : the official journal of the International Neural Network Society
Most existing research on affective associative memory neural network circuits has predominantly concentrated on reinforcement and extinction, with insufficient attention given to the integration of emotion transfer alongside the principles of genera...

On robust learning of memory attractors with noisy deep associative memory networks.

Neural networks : the official journal of the International Neural Network Society
Developing the computational mechanism for memory systems is a long-standing focus in machine learning and neuroscience. Recent studies have shown that overparameterized autoencoders (OAEs) implement associative memory (AM) by encoding training data ...

Design and Implementation of Pavlovian Associative Memory Based on DNA Neurons.

IEEE transactions on neural networks and learning systems
In the field of biocomputing and neural networks, deoxyribonucleic acid (DNA) strand displacement (DSD) technology performs well in computation, programming, and information processing. In this article, the multiplication gate, addition gate, and thr...

Machine learning analysis of cortical activity in visual associative learning tasks with differing stimulus complexity.

Physiology international
Associative learning tests are cognitive assessments that evaluate the ability of individuals to learn and remember relationships between pairs of stimuli. The Rutgers Acquired Equivalence Test (RAET) is an associative learning test that utilizes ima...

Concurrent Associative Memories With Synaptic Delays.

IEEE transactions on neural networks and learning systems
This article presents concurrent associative memories with synaptic delays useful for processing sequences of real vectors. Associative memories with synaptic delays were introduced by the authors for symbolic sequential inputs and demonstrated sever...

Living systems are smarter bots: Slime mold semiosis versus AI symbol manipulation.

Bio Systems
Although machines may be good at mimicking, they are not currently able, as organisms are, to act creatively. We offer an understanding of the emergent qualities of biological sign processing in terms of generalization, association, and encryption. W...

Associated Learning: Decomposing End-to-End Backpropagation Based on Autoencoders and Target Propagation.

Neural computation
Backpropagation (BP) is the cornerstone of today's deep learning algorithms, but it is inefficient partially because of backward locking, which means updating the weights of one layer locks the weight updates in the other layers. Consequently, it is ...

Probing the neural dynamics of mnemonic representations after the initial consolidation.

NeuroImage
Memories are not stored as static engrams, but as dynamic representations affected by processes occurring after initial encoding. Previous studies revealed changes in activity and mnemonic representations in visual processing areas, parietal lobe, an...

Sparse coding with a somato-dendritic rule.

Neural networks : the official journal of the International Neural Network Society
Cortical neurons are silent most of the time: sparse activity enables low-energy computation in the brain, and promises to do the same in neuromorphic hardware. Beyond power efficiency, sparse codes have favourable properties for associative learning...

Probabilistic associative learning suffices for learning the temporal structure of multiple sequences.

PloS one
From memorizing a musical tune to navigating a well known route, many of our underlying behaviors have a strong temporal component. While the mechanisms behind the sequential nature of the underlying brain activity are likely multifarious and multi-s...