Sparse distributed memory
Sparse distributed memory (SDM) is a mathematical model of human long-term memory introduced by Pentti Kanerva in 1988 while he was at NASA Ames Research Center. It is a generalized random-access memory (RAM) for long (e.g., 1,000 bit) binary words. These words serve as both addresses to and data for the memory. The main attribute of the memory is sensitivity to similarity, meaning that a word can be read back not only by giving the original write address but also by giving one close to it, as measured by the number of mismatched bits (i.e., the Hamming distance between memory addresses).
- Comment
- enSparse distributed memory (SDM) is a mathematical model of human long-term memory introduced by Pentti Kanerva in 1988 while he was at NASA Ames Research Center. It is a generalized random-access memory (RAM) for long (e.g., 1,000 bit) binary words. These words serve as both addresses to and data for the memory. The main attribute of the memory is sensitivity to similarity, meaning that a word can be read back not only by giving the original write address but also by giving one close to it, as measured by the number of mismatched bits (i.e., the Hamming distance between memory addresses).
- Has abstract
- enSparse distributed memory (SDM) is a mathematical model of human long-term memory introduced by Pentti Kanerva in 1988 while he was at NASA Ames Research Center. It is a generalized random-access memory (RAM) for long (e.g., 1,000 bit) binary words. These words serve as both addresses to and data for the memory. The main attribute of the memory is sensitivity to similarity, meaning that a word can be read back not only by giving the original write address but also by giving one close to it, as measured by the number of mismatched bits (i.e., the Hamming distance between memory addresses). SDM implements transformation from logical space to physical space using distributed data representation and storage, similarly to encoding processes in human memory. A value corresponding to a logical address is stored into many physical addresses. This way of storing is robust and not deterministic. A memory cell is not addressed directly. If input data (logical addresses) are partially damaged at all, we can still get correct output data. The theory of the memory is mathematically complete and has been verified by computer simulation. It arose from the observation that the distances between points of a high-dimensional space resemble the proximity relations between concepts in human memory. The theory is also practical in that memories based on it can be implemented with conventional random-access memory elements.
- Hypernym
- Model
- Is primary topic of
- Sparse distributed memory
- Label
- enSparse distributed memory
- Link from a Wikipage to an external page
- cstk.sourceforge.net/%3Cref%3EBerchtold,
- pendicular.net/cbvs.php%3Cref%3E
- ccrg.cs.memphis.edu/framework.html
- urn.kb.se/resolve%3Furn=urn:nbn:se:ltu:diva-14994%7C
- github.com/msbrogli/sdm%3Cref
- github.com/msbrogli/sdm-framework%3Cref
- github.com/bit-player/sdm-julia
- Link from a Wikipage to another Wikipage
- Active vision
- Adaptive control
- Ames Research Center
- APL (programming language)
- Artificial consciousness
- Artificial General Intelligence
- Associative memory (psychology)
- Associative neural memories
- Autoassociative memory
- Autoencoder
- Automorphism
- Axon
- Bayesian inference
- Binary search
- Binary spatter codes
- Binomial coefficient
- Binomial distribution
- Biological neuron model
- Boolean function
- Brain
- Brian Hayes (scientist)
- C (programming language)
- C++
- Category:Cognitive architecture
- Category:Memory
- Cerebellar model articulation controller
- Circumference
- Clustering high-dimensional data
- CMatie
- Cognition
- Cognitive architecture
- Computer memory
- Computer simulation
- Computer vision
- Concept
- Conditional probability
- Connection Machine
- Content-addressable memory
- Correlation-matrix memories
- Curse of dimensionality
- Dana H. Ballard
- Decision support system
- Deep learning
- Dendrites
- Drosophila
- Dynamic memory networks
- Encoding (memory)
- Euclidean distance
- Euclidean space
- Excitatory
- Exclusive or
- Feedforward neural network
- File:Exponential decay mechanism.svg
- File:Negated sigmoid function.png
- FPGA
- Function approximation
- GABAergic
- Generalization error
- Genetic algorithm
- Genetic memory (computer science)
- Gero Miesenböck
- Hamming distance
- Hierarchical temporal memory
- High-dimensional space
- Holographic associative memory
- Holographic reduced representation
- Human Brain Project
- Importance sampling
- Inhibitory
- Instance-based learning
- Java (programming language)
- Joint probability distribution
- Julia (programming language)
- Kenyon cell
- Lancaster University
- Language
- Learning
- LIDA (cognitive architecture)
- LISP
- Locality sensitive hashing
- Locality-sensitive hashing
- Long-term memory
- Low-density parity-check code
- Luleå University of Technology
- Machine learning
- Manifolds
- Memory
- Memory address
- Memory networks
- Memory-prediction framework
- Monte Carlo method
- Multiple trace theory
- Mushroom bodies
- NASA
- Nearest neighbor search
- Neural coding
- Neural ensemble
- Neural Turing machine
- Neuromorphic engineering
- Neuron
- Neurons
- Normal distribution
- Olfactory system
- OpenCL
- Pentti Kanerva
- Perceptron
- Prediction
- Principal component analysis
- Python (programming language)
- Random-access memory
- Random indexing
- Recursive auto-associative memory
- Robotics
- Science (journal)
- Self-organizing map
- Semantic folding
- Semantic hashing
- Semantic memory
- Semantic network
- Semantic pointer architecture
- Sequence memory
- Sigmoid function
- Signal processing
- Sparse coding
- Speech recognition
- Sphere
- SpiNNaker
- Standard deviation
- Stan Franklin
- State space
- Steve Furber
- Synapses
- Texas Instruments
- Translation (geometry)
- Turing machines
- Universities Space Research Association
- University of Manchester
- University of Memphis
- University of Oxford
- Variance
- Vector space model
- Vector symbolic architecture
- Virtual memory
- SameAs
- 4vGgh
- m.0hgr2c0
- Memoria distribuida con baja densidad
- Q7573790
- 稀疏分布式存储器
- Subject
- Category:Cognitive architecture
- Category:Memory
- WasDerivedFrom
- Sparse distributed memory?oldid=1121140027&ns=0
- WikiPageLength
- 59884
- Wikipage page ID
- 33547203
- Wikipage revision ID
- 1121140027
- WikiPageUsesTemplate
- Template:Cite journal
- Template:Clarify
- Template:Reflist
- Template:Snd
