A Connectionist Model of False Memories (original) (raw)
Related papers
Building on the human memory model that consider LTM to be similar to a distributed network , and informed by the recent solutions to catastrophic forgetting that suppose memories are dynamically maintained in a dual architecture through a memory self-refreshing mechanism (checked whether false memories of never seen (target) items can be created in humans by exposure to "pseudo-patterns" generated from random input in an artificial neural network (previously trained on the target items). In a behavioral experiment using an opposition method it is shown that the answer is yes: Though the pseudo-patterns presented to the participants were selected so as to resemble (both at the exemplar and the prototype level) more the control items than the target items, the participants exhibited more familiarity for the target items previously learned by the artificial neural network. This behavioral result analogous to the one found in simulations indicates that humans, like distributed neural networks, are able to make use of the information the memory self-refreshing mechanism is based upon. The implications of these findings are discussed in the framework of memory consolidation.
A Study on Associative neural memories
International Journal, 2010
Networks. Without memory, Neural Network can not be learned itself. One of the primary concepts of memory in neural networks is Associative neural memories. A survey has been made on associative neural memories such as Simple associative memories (SAM), Dynamic associative memories (DAM), Bidirectional Associative memories (BAM), Hopfield memories, Context Sensitive Auto-associative memories (CSAM) and so on. These memories can be applied in various fields to get the effective outcomes. We present a study on these associative memories in artificial neural networks.
An entropic associative memory
Scientific Reports, 2021
Natural memories are associative, declarative and distributed, and memory retrieval is a constructive operation. In addition, cues of objects that are not contained in the memory are rejected directly. Symbolic computing memories resemble natural memories in their declarative character, and information can be stored and recovered explicitly; however, they are reproductive rather than constructive, and lack the associative and distributed properties. Sub-symbolic memories developed within the connectionist or artificial neural networks paradigm are associative and distributed, but lack the declarative property, the capability of rejecting objects that are not included in the memory, and memory retrieval is also reproductive. In this paper we present a memory model that sustains the five properties of natural memories. We use Relational-Indeterminate Computing to model associative memory registers that hold distributed representations of individual objects. This mode of computing has ...
Neural network modeling of associative memory: Beyond the Hopfield model
Physica A: Statistical Mechanics and its Applications, 1992
A number of neural network models, in which fixed-point and limit-cycle attractors of the underlying dynamics are used to store and associatively recall information, are described. In the first class of models, a hierarchical structure is used to store an exponentially large number of strongly correlated memories. The second class of models uses limit cycles to store and retrieve individual memories. A neurobiologically plausible network that generates low-amplitude periodic variations of activity, similar to the oscillations observed in electroencephalographic recordings, is also described. Results obtained from analytic and numerical studies of the properties of these networks are discussed.
1997
Despite of processing elements which are thousands of times faster than the neurons in the brain, modern computers still cannot match quite a few processing capabilities of the brain, many of which we even consider trivial (such as recognizing faces or voices, or following a conversation). A common principle for those capabilities lies in the use of correlations between patterns in order to identify patterns which are similar. Looking at the brain as an information processing mechanism with { maybe among others { associative processing capabilities together with the converse view of associative memories as certain types of arti cial neural networks initiated a number of interesting results, ranging from theoretical considerations to insights in the functioning of neurons, as well as parallel hardware implementations of neural associative memories. This paper discusses three main aspects of neural associative memories: theoretical investigations, e.g. on the information storage capacity, local learning rules, e ective retrieval strategies, and encoding schemes implementation aspects, in particular for parallel hardware and applications One important outcome of our analytical considerations is that the combination of binary synaptic weights, sparsely encoded memory patterns, and local learning rules | in particular Hebbian learning | leads to favorable representation and access schemes.
1999
Abstract. The model of Hopfield for a neural network with associative memory is modified by the introduction of a maximum value for the synaptic strength; in this way old patterns are automatically forgotten and the memory recalls only the most recent ones. If the parameters are correctly chosen, the memory never goes into the state of total confusion characteristic of the Hopfield model.
Uninformative memories will prevail: The storage of correlated representations and its consequences
HFSP Journal, 2007
Autoassociative networks were proposed in the 80's as simplified models of memory function in the brain, using recurrent connectivity with Hebbian plasticity to store patterns of neural activity that can be later recalled. This type of computation has been suggested to take place in the CA3 region of the hippocampus and at several levels in the cortex. One of the weaknesses of these models is their apparent inability to store correlated patterns of activity. We show, however, that a small and biologically plausible modification in the "learning rule" "associating to each neuron a plasticity threshold that reflects its popularity… enables the network to handle correlations. We study the stability properties of the resulting memories "in terms of their resistance to the damage of neurons or synapses…, finding a novel property of autoassociative networks: not all memories are equally robust, and the most informative are also the most sensitive to damage. We relate these results to category-specific effects in semantic memory patients, where concepts related to "non-living things" are usually more resistant to brain damage than those related to "living things," a phenomenon suspected to be rooted in the correlation between representations of concepts in the cortex.
The current experiment measured recognition of increasingly complete repicturings of four-piece ensembles of furniture: a lamp, a sofa, a chair, and a wall-hanging. As each of the four pieces was cumulatively added to its ensemble, subjects judged whether the pieces repictured thus far came from a previously studied ensemble of furniture or a new ensemble. It was found that knowing the order in which the four pieces would be added to the increasingly complete repicturings improved recognition confidence. It is argued that this outcome supports a reconstructive memory model, in which remembrances are reconstructed feature by feature, through a process of: a) sampling features from their innately organized locations; and b) retaining those features with appropriate and equivalent time-tags. Opposing models of reconstructive memory, which imply that the memory process is seldom accurate, and opposing models of associative memory, which imply that the component features of a studied object must be either stored together or connected together, are discussed. Although most twentieth-century students of memory have attributed remembrance to associative processes, a small but significant group of psychologists has drawn attention to the role of imagination in the process of reconstructing epi-sodic memories. In opting for reconstructive memory over associative memory, however, Bartlett in the 1930s, Bransford and Frank in the 1970s, and Loftus in the 1990s have implied that imaginatively reconstructed memories are usually inaccurate [1-5]. The current article develops and tests a new model of recon-structive memory, which redefines the association instead of overriding it and, thereby, allows for the imaginative reconstruction of accurate memories.