Memory-prediction framework
Encyclopedia
The memory-prediction framework is a theory of brain
function that was created by Jeff Hawkins
and described in his 2004 book On Intelligence
. This theory concerns the role of the mammalian neocortex
and its associations with the hippocampus
and the thalamus
in matching sensory inputs to stored memory
patterns and how this process leads to predictions of what will happen in the future.
tissue) that are used for a wide range of behaviours available to mammals. The theory posits that the remarkably uniform physical arrangement of cortical tissue reflects a single principle or algorithm which underlies all cortical information processing. The basic processing principle is hypothesized to be a feedback/recall loop
which involves both cortical
and extra-cortical participation (the latter from the thalamus
and the hippocampus
in particular).
The memory-prediction framework provides a unified basis for thinking about the adaptive control of complex behavior. Although certain brain structures are identified as participants in the core 'algorithm' of prediction-from-memory, these details are less important than the set of principles that are proposed as basis for all high-level cognitive processing.
of recognition, and evoke a series of top-down expectations encoded as potentiations. These expectations interact with the bottom-up signals to both analyse those inputs and generate prediction
s of subsequent expected inputs. Each hierarchy level remembers frequently observed temporal sequences of input patterns and generates labels or 'names' for these sequences. When an input sequence matches a memorized sequence at a given layer of the hierarchy, a label or 'name' is propagated up the hierarchy - thus eliminating details at higher levels and enabling them to learn higher-order sequences. This process produces increased invariance
at higher levels. Higher levels predict future input by matching partial sequences and projecting their expectations to the lower levels. However, when a mismatch between input and memorized/predicted sequences occurs, a more complete representation propagates upwards. This causes alternative 'interpretations' to be activated at higher levels, which in turn generates other predictions at lower levels.
Consider, for example, the process of vision
. Bottom-up information starts as low-level retina
l signals (indicating the presence of simple visual elements and contrasts). At higher levels of the hierarchy, increasingly meaningful information is extracted, regarding the presence of lines, region
s, motion
s, etc. Even further up the hierarchy, activity corresponds to the presence of specific objects - and then to behaviours of these objects. Top-down information fills in details about the recognized objects, and also about their expected behaviour as time progresses.
The sensory hierarchy induces a number of differences between the various layers. As one moves up the hierarchy, representations
have increased:
The relationship between sensory and motor processing is an important aspect of the basic theory. It is proposed that the motor areas of cortex
consist of a behavioural hierarchy similar to the sensory hierarchy, with the lowest levels consisting of explicit motor commands to musculature and the highest levels corresponding to abstract prescriptions (e.g. 'resize the browser'). The sensory and motor hierarchies are tightly coupled, with behaviour giving rise to sensory expectations and sensory perception
s driving motor processes.
Finally, it is important to note that all the memories in the cortical hierarchy have to be learnt - this information is not pre-wired in the brain. Hence, the process of extracting this representation
from the flow of inputs and behaviours is theorized as a process that happens continually during cognition
.
hierarchy
of feed forward stochastic
state machines. In this view, the brain is analyzed as an encoding problem, not too dissimilar from future-predicting error-correction codes. The hierarchy is a hierarchy of abstraction
, with the higher level machines' states representing more abstract conditions or events, and these states predisposing lower-level machines to perform certain transitions. The lower level machines model limited domains of experience, or control or interpret sensors or effectors. The whole system actually controls the organism's behavior. Since the state machine is "feed forward", the organism responds to future events predicted from past data. Since it is hierarchical, the system exhibits behavioral flexibility, easily producing new sequences of behavior in response to new sensory data. Since the system learns, the new behavior adapts to changing conditions.
That is, the evolutionary purpose of the brain is to predict the future, in admittedly limited ways, so as to change it.
(as surmised also by Vernon Benjamin Mountcastle from anatomical and theoretical considerations). Each column is attuned to a particular feature at a given level in a hierarchy. It receives bottom-up inputs from lower levels, and top-down inputs from higher levels. (Other columns at the same level also feed into a given column, and serve mostly to inhibit the activiation exclusive representations.) When an input is recognized - that is, acceptable agreement is obtained between the bottom-up and top-down sources - a column generates outputs which in turn propagate to both lower and higher levels.
acts as a 'delay line' - that is, L5 activates this brain area, which re-activates L1 after a slight delay. Thus, the output of one column generates L1 activity, which will coincide with the input to a column which is temporally subsequent within a sequence. This time ordering operates in conjunction with the higher-level identification of the sequence, which does not change in time; hence, activation of the sequence representation causes the lower-level components to be predicted one after the other. (Besides this role in sequencing, the thalamus is also active as sensory waystation - these roles apparently involve distinct regions of this anatomically non-uniform structure.)
. It is well known that damage to the hippocampus impairs the formation of long-term declarative memory; individuals with such damage are unable to form new memories of episodic nature, although they can recall earlier memories without difficulties and can also learn new skills. In the current theory, the hippocampus is thought as the top level of the cortical hierarchy; it is specialized to retain memories of events that propagate all the way to the top. As such events fit into predictable patterns, they become memorizable at lower levels in the hierarchy. (Such movement of memories down the hierarchy is, incidentally, a general prediction of the theory.) Thus, the hippocampus continually memorizes 'unexpected' events (that is, those not predicted at lower levels); if it is damaged, the entire process of memorization through the hierarchy is compromised.
' to 'understanding
' is readily understandable as a result of the matching of top-down and bottom-up expectation
s. Mismatches, in contrast, generate the exquisite ability of biological cognition to detect unexpected perceptions and situations. (Deficiencies in this regard are a common characteristic of current approaches to artificial intelligence.)
Besides these subjectively satisfying explanations, the framework also makes a number of testable prediction
s. For example, the important role that prediction plays throughout the sensory hierarchies calls for anticipatory neural activity in certain cells throughout sensory cortex. In addition, cells that 'name' certain invariants should remain active throughout the presence of those invariants, even if the underlying inputs change. The predicted patterns of bottom-up and top-down activity - with former being more complex when expectations are not met - may be detectable, for example by functional magnetic resonance imaging (fMRI).
Although these predictions are not highly specific to the proposed theory, they are sufficiently unambiguous to make verification or rejection of its central tenets possible. See On Intelligence
for details on the predictions and findings.
and Mountcastle
. On the other hand, the novel separation of the conceptual machinery of bidirectional processing and invariant recognition from the biological details of neural layers, columns and structures lays the foundation for abstract thinking about a wide range of cognitive processes.
The most significant limitation of this theory is its current lack of detail. For example, the concept of invariance
plays a crucial role; Hawkins posits "name cells" for at least some of these invariant
s. (See also Neural ensemble#Encoding for grandmother neurons which perform this type of function, and mirror neuron
s for a somatosensory system
viewpoint.) But it is far from obvious how to develop a mathematically rigorous definition, which will carry the required conceptual load across the domains presented by Hawkins. Similarly, a complete theory will require credible details on both the short-term dynamics and the learning processes that will enable the cortical layers to behave as advertised.
in singly connected Bayesian network
s.
Brain
The brain is the center of the nervous system in all vertebrate and most invertebrate animals—only a few primitive invertebrates such as sponges, jellyfish, sea squirts and starfishes do not have one. It is located in the head, usually close to primary sensory apparatus such as vision, hearing,...
function that was created by Jeff Hawkins
Jeff Hawkins
Jeffrey Hawkins is the founder of Palm Computing and Handspring...
and described in his 2004 book On Intelligence
On Intelligence
On Intelligence: How a New Understanding of the Brain will Lead to the Creation of Truly Intelligent Machines is a book by Palm Pilot-inventor Jeff Hawkins with New York Times science writer Sandra Blakeslee. The book explains Hawkins' memory-prediction framework theory of the brain and describes...
. This theory concerns the role of the mammalian neocortex
Neocortex
The neocortex , also called the neopallium and isocortex , is a part of the brain of mammals. It is the outer layer of the cerebral hemispheres, and made up of six layers, labelled I to VI...
and its associations with the hippocampus
Hippocampus
The hippocampus is a major component of the brains of humans and other vertebrates. It belongs to the limbic system and plays important roles in the consolidation of information from short-term memory to long-term memory and spatial navigation. Humans and other mammals have two hippocampi, one in...
and the thalamus
Thalamus
The thalamus is a midline paired symmetrical structure within the brains of vertebrates, including humans. It is situated between the cerebral cortex and midbrain, both in terms of location and neurological connections...
in matching sensory inputs to stored memory
Memory
In psychology, memory is an organism's ability to store, retain, and recall information and experiences. Traditional studies of memory began in the fields of philosophy, including techniques of artificially enhancing memory....
patterns and how this process leads to predictions of what will happen in the future.
Overview
The theory is motivated by the observed similarities between the brain structures (especially neocorticalCerebral cortex
The cerebral cortex is a sheet of neural tissue that is outermost to the cerebrum of the mammalian brain. It plays a key role in memory, attention, perceptual awareness, thought, language, and consciousness. It is constituted of up to six horizontal layers, each of which has a different...
tissue) that are used for a wide range of behaviours available to mammals. The theory posits that the remarkably uniform physical arrangement of cortical tissue reflects a single principle or algorithm which underlies all cortical information processing. The basic processing principle is hypothesized to be a feedback/recall loop
Feedback
Feedback describes the situation when output from an event or phenomenon in the past will influence an occurrence or occurrences of the same Feedback describes the situation when output from (or information about the result of) an event or phenomenon in the past will influence an occurrence or...
which involves both cortical
Cerebral cortex
The cerebral cortex is a sheet of neural tissue that is outermost to the cerebrum of the mammalian brain. It plays a key role in memory, attention, perceptual awareness, thought, language, and consciousness. It is constituted of up to six horizontal layers, each of which has a different...
and extra-cortical participation (the latter from the thalamus
Thalamus
The thalamus is a midline paired symmetrical structure within the brains of vertebrates, including humans. It is situated between the cerebral cortex and midbrain, both in terms of location and neurological connections...
and the hippocampus
Hippocampus
The hippocampus is a major component of the brains of humans and other vertebrates. It belongs to the limbic system and plays important roles in the consolidation of information from short-term memory to long-term memory and spatial navigation. Humans and other mammals have two hippocampi, one in...
in particular).
The memory-prediction framework provides a unified basis for thinking about the adaptive control of complex behavior. Although certain brain structures are identified as participants in the core 'algorithm' of prediction-from-memory, these details are less important than the set of principles that are proposed as basis for all high-level cognitive processing.
The basic theory: recognition and prediction in bi-directional hierarchies
The central concept of the memory-prediction framework is that bottom-up inputs are matched in a hierarchyHierarchy
A hierarchy is an arrangement of items in which the items are represented as being "above," "below," or "at the same level as" one another...
of recognition, and evoke a series of top-down expectations encoded as potentiations. These expectations interact with the bottom-up signals to both analyse those inputs and generate prediction
Prediction
A prediction or forecast is a statement about the way things will happen in the future, often but not always based on experience or knowledge...
s of subsequent expected inputs. Each hierarchy level remembers frequently observed temporal sequences of input patterns and generates labels or 'names' for these sequences. When an input sequence matches a memorized sequence at a given layer of the hierarchy, a label or 'name' is propagated up the hierarchy - thus eliminating details at higher levels and enabling them to learn higher-order sequences. This process produces increased invariance
Invariance
Invariance is a French magazine edited by Jacques Camatte, published since 1968.It emerged from the Italian left-communist tradition associated with Amadeo Bordiga and it originally bore the subtitle "Invariance of the theory of the proletariat", indicating Bordiga's notion of the unchanging nature...
at higher levels. Higher levels predict future input by matching partial sequences and projecting their expectations to the lower levels. However, when a mismatch between input and memorized/predicted sequences occurs, a more complete representation propagates upwards. This causes alternative 'interpretations' to be activated at higher levels, which in turn generates other predictions at lower levels.
Consider, for example, the process of vision
Visual perception
Visual perception is the ability to interpret information and surroundings from the effects of visible light reaching the eye. The resulting perception is also known as eyesight, sight, or vision...
. Bottom-up information starts as low-level retina
Retina
The vertebrate retina is a light-sensitive tissue lining the inner surface of the eye. The optics of the eye create an image of the visual world on the retina, which serves much the same function as the film in a camera. Light striking the retina initiates a cascade of chemical and electrical...
l signals (indicating the presence of simple visual elements and contrasts). At higher levels of the hierarchy, increasingly meaningful information is extracted, regarding the presence of lines, region
Region
Region is most commonly found as a term used in terrestrial and astrophysics sciences also an area, notably among the different sub-disciplines of geography, studied by regional geographers. Regions consist of subregions that contain clusters of like areas that are distinctive by their uniformity...
s, motion
Motion (physics)
In physics, motion is a change in position of an object with respect to time. Change in action is the result of an unbalanced force. Motion is typically described in terms of velocity, acceleration, displacement and time . An object's velocity cannot change unless it is acted upon by a force, as...
s, etc. Even further up the hierarchy, activity corresponds to the presence of specific objects - and then to behaviours of these objects. Top-down information fills in details about the recognized objects, and also about their expected behaviour as time progresses.
The sensory hierarchy induces a number of differences between the various layers. As one moves up the hierarchy, representations
Knowledge representation
Knowledge representation is an area of artificial intelligence research aimed at representing knowledge in symbols to facilitate inferencing from those knowledge elements, creating new elements of knowledge...
have increased:
- Extent - for example, larger areas of the visual field, or more extensive tactile regions.
- Temporal stability - lower-level entities change quickly, whereas, higher-level percepts tend to be more stable.
- AbstractionAbstractionAbstraction is a process by which higher concepts are derived from the usage and classification of literal concepts, first principles, or other methods....
- through the process of successive extraction of invariantInvariantInvariant and invariance may have several meanings, among which are:- Computer science :* Invariant , an Expression whose value doesn't change during program execution* A type in overriding that is neither covariant nor contravariant...
features, increasingly abstract entities are recognized.
The relationship between sensory and motor processing is an important aspect of the basic theory. It is proposed that the motor areas of cortex
Cerebral cortex
The cerebral cortex is a sheet of neural tissue that is outermost to the cerebrum of the mammalian brain. It plays a key role in memory, attention, perceptual awareness, thought, language, and consciousness. It is constituted of up to six horizontal layers, each of which has a different...
consist of a behavioural hierarchy similar to the sensory hierarchy, with the lowest levels consisting of explicit motor commands to musculature and the highest levels corresponding to abstract prescriptions (e.g. 'resize the browser'). The sensory and motor hierarchies are tightly coupled, with behaviour giving rise to sensory expectations and sensory perception
Perception
Perception is the process of attaining awareness or understanding of the environment by organizing and interpreting sensory information. All perception involves signals in the nervous system, which in turn result from physical stimulation of the sense organs...
s driving motor processes.
Finally, it is important to note that all the memories in the cortical hierarchy have to be learnt - this information is not pre-wired in the brain. Hence, the process of extracting this representation
Knowledge representation
Knowledge representation is an area of artificial intelligence research aimed at representing knowledge in symbols to facilitate inferencing from those knowledge elements, creating new elements of knowledge...
from the flow of inputs and behaviours is theorized as a process that happens continually during cognition
Cognition
In science, cognition refers to mental processes. These processes include attention, remembering, producing and understanding language, solving problems, and making decisions. Cognition is studied in various disciplines such as psychology, philosophy, linguistics, and computer science...
.
Other terms
Hawkins has extensive training as an electrical engineer. Another way to describe the theory (hinted at in his book) is as a learningLearning theory
Learning theory may refer to:* Learning theory , the process of how humans learn** Behaviorism** Cognitivism** Constructivism** Connectivism* Computational learning theory, a mathematical theory to analyze machine learning algorithms...
hierarchy
Hierarchy
A hierarchy is an arrangement of items in which the items are represented as being "above," "below," or "at the same level as" one another...
of feed forward stochastic
Stochastic
Stochastic refers to systems whose behaviour is intrinsically non-deterministic. A stochastic process is one whose behavior is non-deterministic, in that a system's subsequent state is determined both by the process's predictable actions and by a random element. However, according to M. Kac and E...
state machines. In this view, the brain is analyzed as an encoding problem, not too dissimilar from future-predicting error-correction codes. The hierarchy is a hierarchy of abstraction
Abstraction
Abstraction is a process by which higher concepts are derived from the usage and classification of literal concepts, first principles, or other methods....
, with the higher level machines' states representing more abstract conditions or events, and these states predisposing lower-level machines to perform certain transitions. The lower level machines model limited domains of experience, or control or interpret sensors or effectors. The whole system actually controls the organism's behavior. Since the state machine is "feed forward", the organism responds to future events predicted from past data. Since it is hierarchical, the system exhibits behavioral flexibility, easily producing new sequences of behavior in response to new sensory data. Since the system learns, the new behavior adapts to changing conditions.
That is, the evolutionary purpose of the brain is to predict the future, in admittedly limited ways, so as to change it.
Neurophysiological implementation
The hierarchies described above are theorized to occur primarily in mammalian neocortex. In particular, neocortex is assumed to consist of a large number of columnsCortical column
A cortical column, also called hypercolumn or sometimes cortical module, is a group of neurons in the brain cortex which can be successively penetrated by a probe inserted perpendicularly to the cortical surface, and which have nearly identical receptive fields...
(as surmised also by Vernon Benjamin Mountcastle from anatomical and theoretical considerations). Each column is attuned to a particular feature at a given level in a hierarchy. It receives bottom-up inputs from lower levels, and top-down inputs from higher levels. (Other columns at the same level also feed into a given column, and serve mostly to inhibit the activiation exclusive representations.) When an input is recognized - that is, acceptable agreement is obtained between the bottom-up and top-down sources - a column generates outputs which in turn propagate to both lower and higher levels.
Cortex
These processes map well to specific layers within mammalian cortex. (The cortical layers should not be confused with different levels of the processing hierarchy: all the layers in a single column participate as one element in a single hierarchical level). Bottom-up input arrives at layer 4 (L4), whence it propagates to L2 and L3 for recognition of the invariant content. Top-down activation arrives to L2 and L3 via L1 (the mostly axonal layer that distributes activation locally across columns. L2 and L3 compare bottom up and top-down information, and generate either the invariant 'names' when sufficient match is achieved, or the more variable signals that occur when this fails. These signals are propagated up the hierarchy (via L5) and also down the hierarchy (via L6 and L1).Thalamus
To account for storage and recognition of sequences of patterns, a combination of two processes is suggested. The nonspecific thalamusThalamus
The thalamus is a midline paired symmetrical structure within the brains of vertebrates, including humans. It is situated between the cerebral cortex and midbrain, both in terms of location and neurological connections...
acts as a 'delay line' - that is, L5 activates this brain area, which re-activates L1 after a slight delay. Thus, the output of one column generates L1 activity, which will coincide with the input to a column which is temporally subsequent within a sequence. This time ordering operates in conjunction with the higher-level identification of the sequence, which does not change in time; hence, activation of the sequence representation causes the lower-level components to be predicted one after the other. (Besides this role in sequencing, the thalamus is also active as sensory waystation - these roles apparently involve distinct regions of this anatomically non-uniform structure.)
Hippocampus
Another anatomically diverse brain structure which is hypothesized to play an important role in hierarchical cognition is the hippocampusHippocampus
The hippocampus is a major component of the brains of humans and other vertebrates. It belongs to the limbic system and plays important roles in the consolidation of information from short-term memory to long-term memory and spatial navigation. Humans and other mammals have two hippocampi, one in...
. It is well known that damage to the hippocampus impairs the formation of long-term declarative memory; individuals with such damage are unable to form new memories of episodic nature, although they can recall earlier memories without difficulties and can also learn new skills. In the current theory, the hippocampus is thought as the top level of the cortical hierarchy; it is specialized to retain memories of events that propagate all the way to the top. As such events fit into predictable patterns, they become memorizable at lower levels in the hierarchy. (Such movement of memories down the hierarchy is, incidentally, a general prediction of the theory.) Thus, the hippocampus continually memorizes 'unexpected' events (that is, those not predicted at lower levels); if it is damaged, the entire process of memorization through the hierarchy is compromised.
Explanatory successes and predictions
The memory-prediction framework explains a number of psychologically salient aspects of cognition. For example, the ability of experts in any field to effortlessly analyze and remember complex problems within their field is a natural consequence of their formation of increasingly refined conceptual hierarchies. Also, the procession from 'perceptionPerception
Perception is the process of attaining awareness or understanding of the environment by organizing and interpreting sensory information. All perception involves signals in the nervous system, which in turn result from physical stimulation of the sense organs...
' to 'understanding
Understanding
Understanding is a psychological process related to an abstract or physical object, such as a person, situation, or message whereby one is able to think about it and use concepts to deal adequately with that object....
' is readily understandable as a result of the matching of top-down and bottom-up expectation
Expectation
In the case of uncertainty, expectation is what is considered the most likely to happen. An expectation, which is a belief that is centered on the future, may or may not be realistic. A less advantageous result gives rise to the emotion of disappointment. If something happens that is not at all...
s. Mismatches, in contrast, generate the exquisite ability of biological cognition to detect unexpected perceptions and situations. (Deficiencies in this regard are a common characteristic of current approaches to artificial intelligence.)
Besides these subjectively satisfying explanations, the framework also makes a number of testable prediction
Prediction
A prediction or forecast is a statement about the way things will happen in the future, often but not always based on experience or knowledge...
s. For example, the important role that prediction plays throughout the sensory hierarchies calls for anticipatory neural activity in certain cells throughout sensory cortex. In addition, cells that 'name' certain invariants should remain active throughout the presence of those invariants, even if the underlying inputs change. The predicted patterns of bottom-up and top-down activity - with former being more complex when expectations are not met - may be detectable, for example by functional magnetic resonance imaging (fMRI).
Although these predictions are not highly specific to the proposed theory, they are sufficiently unambiguous to make verification or rejection of its central tenets possible. See On Intelligence
On Intelligence
On Intelligence: How a New Understanding of the Brain will Lead to the Creation of Truly Intelligent Machines is a book by Palm Pilot-inventor Jeff Hawkins with New York Times science writer Sandra Blakeslee. The book explains Hawkins' memory-prediction framework theory of the brain and describes...
for details on the predictions and findings.
Contribution and limitations
By design, the current theory builds on the work of numerous neurobiologists, and it may be argued that most of these ideas have already been proposed by researchers such as GrossbergStephen Grossberg
Stephen Grossberg is a cognitive scientist, neuroscientist, biomedical engineer, mathematician, and neuromorphic technologist. He is the Wang Professor of Cognitive and Neural Systems and a Professor of Mathematics, Psychology, and Biomedical Engineering at Boston University.Grossberg's work...
and Mountcastle
Vernon Mountcastle
Vernon Benjamin Mountcastle is Professor Emeritus of Neuroscience at Johns Hopkins University.He discovered and characterized the columnar organization of the cerebral cortex in the 1950s...
. On the other hand, the novel separation of the conceptual machinery of bidirectional processing and invariant recognition from the biological details of neural layers, columns and structures lays the foundation for abstract thinking about a wide range of cognitive processes.
The most significant limitation of this theory is its current lack of detail. For example, the concept of invariance
Invariant
Invariant and invariance may have several meanings, among which are:- Computer science :* Invariant , an Expression whose value doesn't change during program execution* A type in overriding that is neither covariant nor contravariant...
plays a crucial role; Hawkins posits "name cells" for at least some of these invariant
Invariant
Invariant and invariance may have several meanings, among which are:- Computer science :* Invariant , an Expression whose value doesn't change during program execution* A type in overriding that is neither covariant nor contravariant...
s. (See also Neural ensemble#Encoding for grandmother neurons which perform this type of function, and mirror neuron
Mirror neuron
A mirror neuron is a neuron that fires both when an animal acts and when the animal observes the same action performed by another. Thus, the neuron "mirrors" the behaviour of the other, as though the observer were itself acting. Such neurons have been directly observed in primate and other...
s for a somatosensory system
Somatosensory system
The somatosensory system is a diverse sensory system composed of the receptors and processing centres to produce the sensory modalities such as touch, temperature, proprioception , and nociception . The sensory receptors cover the skin and epithelia, skeletal muscles, bones and joints, internal...
viewpoint.) But it is far from obvious how to develop a mathematically rigorous definition, which will carry the required conceptual load across the domains presented by Hawkins. Similarly, a complete theory will require credible details on both the short-term dynamics and the learning processes that will enable the cortical layers to behave as advertised.
Machine learning models
The memory-prediction theory claims a common algorithm is employed by all regions in the neocortex. The theory has given rise to a number of software models aiming to simulate this common algorithm using a hierarchical memory structure. The year in the list below indicates when the model was last updated.Models based on Bayesian networks
The following models use belief propagation or belief revisionBelief revision
Belief revision is the process of changing beliefs to take into account a new piece of information. The logical formalization of belief revision is researched in philosophy, in databases, and in artificial intelligence for the design of rational agents....
in singly connected Bayesian network
Bayesian network
A Bayesian network, Bayes network, belief network or directed acyclic graphical model is a probabilistic graphical model that represents a set of random variables and their conditional dependencies via a directed acyclic graph . For example, a Bayesian network could represent the probabilistic...
s.
- Hierarchical Temporal MemoryHierarchical Temporal MemoryHierarchical temporal memory is a machine learning model developed by Jeff Hawkins and Dileep George of Numenta, Inc. that models some of the structural and algorithmic properties of the neocortex. HTM is a biomimetic model based on the memory-prediction theory of brain function described by Jeff...
(HTM), a model, a related development platform and source code by Numenta, Inc.NumentaNumenta is a company founded March 24, 2005, by Palm founder Jeff Hawkins with his longtime business partner Donna Dubinsky and Stanford graduate student Dileep George. It is headquartered in Redwood City, California.-Origin:...
(2008). - HtmLib, an alternative implementation of HTM algorithms by Greg Kochaniak with a number of modifications for improving the recognition accuracy and speed (2008).
- Project Neocortex, an open source project for modeling memory-prediction framework (2008).
- Saulius Garalevicius' research page, research papers and programs presenting experimental results with a model of the memory-prediction framework, a basis for the Neocortex project (2007).
- A Hierarchical Bayesian Model of Invariant Pattern Recognition in the Visual Cortex, a paper describing earlier pre-HTM Bayesian model by Dileep George, co-founder of Numenta, Inc.NumentaNumenta is a company founded March 24, 2005, by Palm founder Jeff Hawkins with his longtime business partner Donna Dubinsky and Stanford graduate student Dileep George. It is headquartered in Redwood City, California.-Origin:...
(2005). This is the first model of memory-prediction framework that uses Bayesian networks and all the above models are based on these initial ideas. Matlab source code of this model had been freely available for download for a number of years.
Other models
- Implementation of MPF, a paper by Saulius Garalevicius describing a method of classification and prediction in a model that stores temporal sequences and employs unsupervised learning (2005).
- M5, a pattern machine for Palm OS that stores pattern sequences and recalls the patterns relevant to its present environment (2007).
- BrainGame, open source predictor class which learns patterns and can be linked to other predictors (2005).
See also
- Vernon MountcastleVernon MountcastleVernon Benjamin Mountcastle is Professor Emeritus of Neuroscience at Johns Hopkins University.He discovered and characterized the columnar organization of the cerebral cortex in the 1950s...
, the neuroscientist who discovered and characterized the columnar organization of the cerebral cortex. - Adaptive resonance theoryAdaptive resonance theoryAdaptive Resonance Theory is a theory developed by Stephen Grossberg and Gail Carpenter on aspects of how the brain processes information. It describes a number of neural network models which use supervised and unsupervised learning methods, and address problems such as pattern recognition and...
, a neural network architecture developed by Stephen GrossbergStephen GrossbergStephen Grossberg is a cognitive scientist, neuroscientist, biomedical engineer, mathematician, and neuromorphic technologist. He is the Wang Professor of Cognitive and Neural Systems and a Professor of Mathematics, Psychology, and Biomedical Engineering at Boston University.Grossberg's work...
. - Computational neuroscienceComputational neuroscienceComputational neuroscience is the study of brain function in terms of the information processing properties of the structures that make up the nervous system...
- Neural DarwinismNeural DarwinismNeural Darwinism, a large scale theory of brain function by Gerald Edelman, was initially published in 1978, in a book called The Mindful Brain...
- Predictive learningPredictive learningPredictive learning is a technique of machine learning in which an agent tries to build a model of its environment by trying out different actions in various circumstances. It uses knowledge of the effects its actions appear to have, turning them into planning operators. These allow the agent to...
Further reading
- Jeff Hawkins (2004), On IntelligenceOn IntelligenceOn Intelligence: How a New Understanding of the Brain will Lead to the Creation of Truly Intelligent Machines is a book by Palm Pilot-inventor Jeff Hawkins with New York Times science writer Sandra Blakeslee. The book explains Hawkins' memory-prediction framework theory of the brain and describes...
, New York: Henry Holt. Bibliography, Index, 251 pages. ISBN 0-8050-7456-2
External links
- Hierarchical vision algorithm source code & data
- similar to the Memory-Prediction Framework (from MIT Center for Biological & Computational Learning) - Group of articles about neuroscience and AI
- Group of articles and papers supporting Jeff's MPF theory. - MIT Technology Review Monday, February 12, 2007: Building the Cortex in Silicon