Topic
Encoding (memory)
About: Encoding (memory) is a research topic. Over the lifetime, 7547 publications have been published within this topic receiving 120214 citations. The topic is also known as: memory encoding & encoding of memories.
Papers published on a yearly basis
1 / 2
Papers
1 Jan 1985
TL;DR: In this paper, the problem of infinite-state memory is addressed in the context of biological memory using an adaptive filtering approach based on the classical laws of association, which is used for the purpose and nature of the biological memory.
Abstract: 1 Various Aspects of Memory- 11 On the Purpose and Nature of Biological Memory- 111 Some Fundamental Concepts- 112 The Classical Laws of Association- 113 On Different Levels of Modelling- 12 Questions Concerning the Fundamental Mechanisms of Memory- 121 Where Do the Signals Relating to Memory Act Upon?- 122 What Kind of Encoding is Used for Neural Signals?- 123 What are the Variable Memory Elements?- 124 How are Neural Signals Addressed in Memory?- 13 Elementary Operations Implemented by Associative Memory- 131 Associative Recall- 132 Production of Sequences from the Associative Memory- 133 On the Meaning of Background and Context- 14 More Abstract Aspects of Memory- 141 The Problem of Infinite-State Memory- 142 Invariant Representations- 143 Symbolic Representations- 144 Virtual Images- 145 The Logic of Stored Knowledge- 2 Pattern Mathematics- 21 Mathematical Notations and Methods- 211 Vector Space Concepts- 212 Matrix Notations- 213 Further Properties of Matrices- 214 Matrix Equations- 215 Projection Operators- 216 On Matrix Differential Calculus- 22 Distance Measures for Patterns- 221 Measures of Similarity and Distance in Vector Spaces- 222 Measures of Similarity and Distance Between Symbol Strings- 223 More Accurate Distance Measures for Text- 3 Classical Learning Systems- 31 The Adaptive Linear Element (Adaline)- 311 Description of Adaptation by the Stochastic Approximation- 32 The Perceptron- 33 The Learning Matrix- 34 Physical Realization of Adaptive Weights- 341 Perceptron and Adaline- 342 Classical Conditioning- 343 Conjunction Learning Switches- 344 Digital Representation of Adaptive Circuits- 345 Biological Components- 4 A New Approach to Adaptive Filters- 41 Survey of Some Necessary Functions- 42 On the "Transfer Function" of the Neuron- 43 Models for Basic Adaptive Units- 431 On the Linearization of the Basic Unit- 432 Various Cases of Adaptation Laws- 433 Two Limit Theorems- 434 The Novelty Detector- 44 Adaptive Feedback Networks- 441 The Autocorrelation Matrix Memory- 442 The Novelty Filter- 5 Self-Organizing Feature Maps- 51 On the Feature Maps of the Brain- 52 Formation of Localized Responses by Lateral Feedback- 53 Computational Simplification of the Process- 531 Definition of the Topology-Preserving Mapping- 532 A Simple Two-Dimensional Self-Organizing System- 54 Demonstrations of Simple Topology-Preserving Mappings- 541 Images of Various Distributions of Input Vectors- 542 "The Magic TV"- 543 Mapping by a Feeler Mechanism- 55 Tonotopic Map- 56 Formation of Hierarchical Representations- 561 Taxonomy Example- 562 Phoneme Map- 57 Mathematical Treatment of Self-Organization- 571 Ordering of Weights- 572 Convergence Phase- 58 Automatic Selection of Feature Dimensions- 6 Optimal Associative Mappings- 61 Transfer Function of an Associative Network- 62 Autoassociative Recall as an Orthogonal Projection- 621 Orthogonal Projections- 622 Error-Correcting Properties of Projections- 63 The Novelty Filter- 631 Two Examples of Novelty Filter- 632 Novelty Filter as an Autoassociative Memory- 64 Autoassociative Encoding- 641 An Example of Autoassociative Encoding- 65 Optimal Associative Mappings- 651 The Optimal Linear Associative Mapping- 652 Optimal Nonlinear Associative Mappings- 66 Relationship Between Associative Mapping, Linear Regression, and Linear Estimation- 661 Relationship of the Associative Mapping to Linear Regression- 662 Relationship of the Regression Solution to the Linear Estimator- 67 Recursive Computation of the Optimal Associative Mapping- 671 Linear Corrective Algorithms- 672 Best Exact Solution (Gradient Projection)- 673 Best Approximate Solution (Regression)- 674 Recursive Solution in the General Case- 68 Special Cases- 681 The Correlation Matrix Memory- 682 Relationship Between Conditional Averages and Optimal Estimator- 7 Pattern Recognition- 71 Discriminant Functions- 72 Statistical Formulation of Pattern Classification- 73 Comparison Methods- 74 The Subspace Methods of Classification- 741 The Basic Subspace Method- 742 The Learning Subspace Method (LSM)- 75 Learning Vector Quantization- 76 Feature Extraction- 77 Clustering- 771 Simple Clustering (Optimization Approach)- 772 Hierarchical Clustering (Taxonomy Approach)- 78 Structural Pattern Recognition Methods- 8 More About Biological Memory- 81 Physiological Foundations of Memory- 811 On the Mechanisms of Memory in Biological Systems- 812 Structural Features of Some Neural Networks- 813 Functional Features of Neurons- 814 Modelling of the Synaptic Plasticity- 815 Can the Memory Capacity Ensue from Synaptic Changes?- 82 The Unified Cortical Memory Model- 821 The Laminar Network Organization- 822 On the Roles of Interneurons- 823 Representation of Knowledge Over Memory Fields- 824 Self-Controlled Operation of Memory- 83 Collateral Reading- 831 Physiological Results Relevant to Modelling- 832 Related Modelling- 9 Notes on Neural Computing- 91 First Theoretical Views of Neural Networks- 92 Motives for the Neural Computing Research- 93 What Could the Purpose of the Neural Networks be?- 94 Definitions of Artificial "Neural Computing" and General Notes on Neural Modelling- 95 Are the Biological Neural Functions Localized or Distributed?- 96 Is Nonlinearity Essential to Neural Computing?- 97 Characteristic Differences Between Neural and Digital Computers- 971 The Degree of Parallelism of the Neural Networks is Still Higher than that of any "Massively Parallel" Digital Computer- 972 Why the Neural Signals Cannot be Approximated by Boolean Variables- 973 The Neural Circuits do not Implement Finite Automata- 974 Undue Views of the Logic Equivalence of the Brain and Computers on a High Level- 98 "Connectionist Models"- 99 How can the Neural Computers be Programmed?- 10 Optical Associative Memories- 101 Nonholographic Methods- 102 General Aspects of Holographic Memories- 103 A Simple Principle of Holographic Associative Memory- 104 Addressing in Holographic Memories- 105 Recent Advances of Optical Associative Memories- Bibliography on Pattern Recognition- References
3,562 citations
TL;DR: A new optical encoding method of images for security applications is proposed and it is shown that the encoding converts the input signal to stationary white noise and that the reconstruction method is robust.
Abstract: We propose a new optical encoding method of images for security applications. The encoded image is obtained by random-phase encoding in both the input and the Fourier planes. We analyze the statistical properties of this technique and show that the encoding converts the input signal to stationary white noise and that the reconstruction method is robust.
2,632 citations
TL;DR: This review aims to comprehensively cover the field of "sleep and memory" research by providing a historical perspective on concepts and a discussion of more recent key findings.
Abstract: Over more than a century of research has established the fact that sleep benefits the retention of memory. In this review we aim to comprehensively cover the field of "sleep and memory" research by providing a historical perspective on concepts and a discussion of more recent key findings. Whereas initial theories posed a passive role for sleep enhancing memories by protecting them from interfering stimuli, current theories highlight an active role for sleep in which memories undergo a process of system consolidation during sleep. Whereas older research concentrated on the role of rapid-eye-movement (REM) sleep, recent work has revealed the importance of slow-wave sleep (SWS) for memory consolidation and also enlightened some of the underlying electrophysiological, neurochemical, and genetic mechanisms, as well as developmental aspects in these processes. Specifically, newer findings characterize sleep as a brain state optimizing memory consolidation, in opposition to the waking brain being optimized for encoding of memories. Consolidation originates from reactivation of recently encoded neuronal memory representations, which occur during SWS and transform respective representations for integration into long-term memory. Ensuing REM sleep may stabilize transformed memories. While elaborated with respect to hippocampus-dependent memories, the concept of an active redistribution of memory representations from networks serving as temporary store into long-term stores might hold also for non-hippocampus-dependent memory, and even for nonneuronal, i.e., immunological memories, giving rise to the idea that the offline consolidation of memory during sleep represents a principle of long-term memory formation established in quite different physiological systems.
2,566 citations
TL;DR: This work provides electrophysiological evidence for lateralized activity in humans that reflects the encoding and maintenance of items in visual memory and provides a strong neurophysiological predictor of an individual's capacity, allowing a direct relationship between neural activity and memory capacity.
Abstract: Contrary to our rich phenomenological visual experience, our visual short-term memory system can maintain representations of only three to four objects at any given moment. For over a century, the capacity of visual memory has been shown to vary substantially across individuals, ranging from 1.5 to about 5 objects. Although numerous studies have recently begun to characterize the neural substrates of visual memory processes, a neurophysiological index of storage capacity limitations has not yet been established. Here, we provide electrophysiological evidence for lateralized activity in humans that reflects the encoding and maintenance of items in visual memory. The amplitude of this activity is strongly modulated by the number of objects being held in the memory at the time, but approaches a limit asymptotically for arrays that meet or exceed storage capacity. Indeed, the precise limit is determined by each individual's memory capacity, such that the activity from low-capacity individuals reaches this plateau much sooner than that from high-capacity individuals. Consequently, this measure provides a strong neurophysiological predictor of an individual's capacity, allowing the demonstration of a direct relationship between neural activity and memory capacity.
1,921 citations
1 Jan 2019
TL;DR: The proposed memory-augmented autoencoder called MemAE is free of assumptions on the data type and thus general to be applied to different tasks and proves the excellent generalization and high effectiveness of the proposed MemAE.
Abstract: Deep autoencoder has been extensively used for anomaly detection. Training on the normal data, the autoencoder is expected to produce higher reconstruction error for the abnormal inputs than the normal ones, which is adopted as a criterion for identifying anomalies. However, this assumption does not always hold in practice. It has been observed that sometimes the autoencoder "generalizes" so well that it can also reconstruct anomalies well, leading to the miss detection of anomalies. To mitigate this drawback for autoencoder based anomaly detector, we propose to augment the autoencoder with a memory module and develop an improved autoencoder called memory-augmented autoencoder, i.e. MemAE. Given an input, MemAE firstly obtains the encoding from the encoder and then uses it as a query to retrieve the most relevant memory items for reconstruction. At the training stage, the memory contents are updated and are encouraged to represent the prototypical elements of the normal data. At the test stage, the learned memory will be fixed, and the reconstruction is obtained from a few selected memory records of the normal data. The reconstruction will thus tend to be close to a normal sample. Thus the reconstructed errors on anomalies will be strengthened for anomaly detection. MemAE is free of assumptions on the data type and thus general to be applied to different tasks. Experiments on various datasets prove the excellent generalization and high effectiveness of the proposed MemAE.
1,737 citations
Related Topics (5)
Performance Metrics
| Year | Papers |
|---|---|
| 2026 | 17 |
| 2025 | 1,394 |
| 2024 | 2,006 |
| 2023 | 1,907 |
| 2022 | 2,770 |
| 2021 | 564 |