Leabra¶

Leabra is heavily influenced by and contributes to neural network designs and models, including emergent.

Version: v1 · 2026-09-28 · History
Domain-specific #: 10341
Domain group: Interdisciplinary & Synthetic
Origin domain: Cognitive Science
Subdomains: Computational Cognitive Neuroscience, Neural Network Models → Cognitive Science

Core Idea¶

Leabra is treated here as the recurring computer_science_and_information identity summarized by this source-grounded definition: Leabra is heavily influenced by and contributes to neural network designs and models, including emergent.

Leabra stands for local, error-driven and associative, biologically realistic algorithm. It is a model of learning which is a balance between Hebbian and error-driven learning with other network-derived characteristics. This model is used to mathematically predict outcomes based on inputs and previous learning influences.

Leabra is heavily influenced by and contributes to neural network designs and models, including emergent. The net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions. It is the default algorithm in emergent (successor of PDP++) when making a new project, and is extensively used in various simulations.

For Leabra, the abstraction is narrower than the article's general subject matter: a positive case must preserve Leabra is heavily influenced by and contributes to neural network designs and models, including emergent. Retaining only the name, a familiar example, or a downstream effect is insufficient. The specialist roles and tests remain anchored in computer_science_and_information, which is why this identity is domain-specific rather than prime.

Structural Signature¶

Sig role-phrases:

Defining carrier — The net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions.
Constitutive relation — Hebbian learning is performed using conditional principal components analysis (CPCA) algorithm with correction factor for sparse expected activity levels.
Operating condition — Error-driven learning is performed using GeneRec, which is a generalization of the recirculation algorithm, and approximates Almeida–Pineda recurrent backpropagation.
Recognition evidence — Layer or unit-group level inhibition can be computed directly using a k-winners-take-all (KWTA) function, producing sparse distributed representations.
Admissible variation — FFFB inhibition can be efficiently implemented by using the average excitatory input and activity levels in a given layer.
Characteristic consequence — Automatic scaling is performed to compensate for differences in expected activity level in the different projections.
Failure boundary — Documentation about this algorithm can be found in the book "Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain" published by MIT press. and in the Emergent Documentation.

What It Is Not¶

Not the whole field of computer_science_and_information. The node requires the specific identity stated by Leabra is heavily influenced by and contributes to neural network designs and models, including emergent.
Not an over-broad reading. The net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions.
Not an over-broad reading. Automatic scaling is performed to compensate for differences in expected activity level in the different projections.
Not an over-broad reading. The MATLAB and R versions are not suited for constructing very large networks, but they can be installed quickly and (with some programming background) are easy to use.
Not automatically Error-driven learning. Retrieval proximity does not establish equivalence; the two identities must be compared by carrier, operation, and failure boundary.

Scope of Application¶

Leabra applies literally inside computer_science_and_information wherever the source-defined carrier and relation can be established. Its documented habitats include:

Background. It is the default algorithm in emergent (successor of PDP++) when making a new project, and is extensively used in various simulations.
Background. The symmetric, midpoint version of GeneRec is used, which is equivalent to the contrastive Hebbian learning algorithm (CHL).
Background. The activation function is a point-neuron approximation with both discrete spiking and continuous rate-code output.
Background. Layer or unit-group level inhibition can be computed directly using a k-winners-take-all (KWTA) function, producing sparse distributed representations.
Implementations. There is also an R version available, that can be easily installed via install.packages("leabRa") in R and has a short introduction to how the package is used.
Special algorithms. Temporal differences (TD) is widely used as a model of midbrain dopaminergic firing.

Outside computer_science_and_information, the name should be retained only when these same operational conditions survive; otherwise the comparison belongs to the broader parent Theory or should be marked as analogy.

Clarity¶

A clear use of Leabra names the carrier, the operative relation, and the conditions under which the source treats the identity as present. The minimal definition is Leabra is heavily influenced by and contributes to neural network designs and models, including emergent. The strongest recognition evidence in the frozen account is: Layer or unit-group level inhibition can be computed directly using a k-winners-take-all (KWTA) function, producing sparse distributed representations. A report should distinguish that evidence from a proxy, consequence, or common implementation. It should also state the qualification The net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions. so that a reader can reproduce the classification rather than infer it from topical resemblance.

Manages Complexity¶

Leabra compresses multiple computer_science_and_information details into a stable diagnostic relation. The source shows both the central mechanism—hebbian learning is performed using conditional principal components analysis (CPCA) algorithm with correction factor for sparse expected activity levels.—and the practical consequence—automatic scaling is performed to compensate for differences in expected activity level in the different projections. This compression makes cases comparable while leaving parameters, conventions, exceptions, and evidential quality explicit. It is lossy by design: local history and implementation details may be omitted only when they do not alter the defining relation.

Abstract Reasoning¶

Type the carrier. Identify the computer_science_and_information entities to which the claim applies.
State the relation. Use the source-grounded identity: Leabra is heavily influenced by and contributes to neural network designs and models, including emergent.
Check operation and conditions. Error-driven learning is performed using GeneRec, which is a generalization of the recirculation algorithm, and approximates Almeida–Pineda recurrent backpropagation.
Demand recognition evidence. Layer or unit-group level inhibition can be computed directly using a k-winners-take-all (KWTA) function, producing sparse distributed representations.
Test variation. Change an implementation or setting while preserving fFFB inhibition can be efficiently implemented by using the average excitatory input and activity levels in a given layer.
Run the collapse test. Remove the defining operation; if the label still seems equally apt, only a topic or correlate was retained.
Reduce cautiously. When the specialist conditions cannot be carried, route the residual comparison to Theory.

Knowledge Transfer¶

Within the home domain. Knowledge about Leabra transfers literally when a new case preserves the same carrier type, relation, and recognition test. It is the default algorithm in emergent (successor of PDP++) when making a new project, and is extensively used in various simulations. The symmetric, midpoint version of GeneRec is used, which is equivalent to the contrastive Hebbian learning algorithm (CHL).

Beyond the home domain. No canonical parent is asserted for Leabra. An outside case receives the specialist name only when the same typed roles and rejection conditions can be filled literally; otherwise the comparison remains an analogy pending later graph densification.

Examples¶

Canonical¶

Leabra is heavily influenced by and contributes to neural network designs and models, including emergent. This case is canonical because it supplies a concrete carrier and lets the defining relation be checked rather than merely named.

Mapped back: carrier → the entities in the documented case; operation → Leabra is heavily influenced by and contributes to neural network designs and models, including emergent; recognition evidence → Layer or unit-group level inhibition can be computed directly using a k-winners-take-all (KWTA) function, producing sparse distributed representations

Applied / In Practice¶

It is the default algorithm in emergent (successor of PDP++) when making a new project, and is extensively used in various simulations. The applied case shows how the identity is used under a second setting or qualification while keeping the same operative relation.

Mapped back: changed setting → Background; invariant → Leabra is heavily influenced by and contributes to neural network designs and models, including emergent; boundary → the case exits the class when the net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions

Structural Tensions¶

T1 — Stable identity versus admissible variation. The net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions. The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Which changes preserve the defining relation, and which replace it?

T2 — Recognition versus proxy. Automatic scaling is performed to compensate for differences in expected activity level in the different projections. The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Does the cited evidence establish the identity or only a correlated sign?

T3 — Definition versus implementation. The MATLAB and R versions are not suited for constructing very large networks, but they can be installed quickly and (with some programming background) are easy to use. The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Is the observed implementation constitutive, optional, or merely common?

T4 — Scope versus overextension. It is the default algorithm in emergent (successor of PDP++) when making a new project, and is extensively used in various simulations. The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Can every claimed application fill the same typed roles without metaphor?

T5 — Transfer versus domain accent. The net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions. The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: Does the receiving case instantiate Leabra literally, co-instantiate Theory, or only resemble it?

T6 — Autonomy versus reduction. Hebbian learning is performed using conditional principal components analysis (CPCA) algorithm with correction factor for sparse expected activity levels. The tension matters because emphasizing only one side either dissolves the identity or overstates what the evidence and domain conventions warrant.

Diagnostic: What does Leabra distinguish that the broader parent Theory leaves together?

Structural–Framed Character¶

Leabra is structural-leaning. Its structural side is the repeatable organization summarized by Leabra is heavily influenced by and contributes to neural network designs and models, including emergent. Its framed side is the computer_science_and_information vocabulary that fixes the carrier, evidence, exceptions, and admissible transformations.

Evaluative weight: the identity can be stated descriptively even when applications carry practical stakes. Human-practice dependence: the source-grounded carrier determines whether the relation exists independently or is constituted by a practice. Institutional origin: disciplinary conventions stabilize the name and test. Vocabulary portability: Error-driven learning is performed using GeneRec, which is a generalization of the recirculation algorithm, and approximates Almeida–Pineda recurrent backpropagation. Import versus recognition: literal transfer requires the same mechanism; shape alone is analogy.

Its portable skeleton is Theory. Its character: a recurring specialist identity whose thin organization can be abstracted, while its operational meaning remains domain-bound.

Structural Core vs. Domain Accent¶

What is skeletal. Leabra is heavily influenced by and contributes to neural network designs and models, including emergent. The stable skeleton is the typed relation expressed in that definition and the entry's recognition and collapse tests. The source identifies these operative conditions: The net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions. Hebbian learning is performed using conditional principal components analysis (CPCA) algorithm with correction factor for sparse expected activity levels. It further constrains recognition and variation through: Error-driven learning is performed using GeneRec, which is a generalization of the recirculation algorithm, and approximates Almeida–Pineda recurrent backpropagation. Layer or unit-group level inhibition can be computed directly using a k-winners-take-all (KWTA) function, producing sparse distributed representations.

What is domain-bound. computer science and information supplies the operative entities, technical vocabulary, warrants, and exceptions that make Leabra literal. Its documented scope includes the condition that It is the default algorithm in emergent (successor of PDP++) when making a new project, and is extensively used in various simulations. Another bounded application condition is that The symmetric, midpoint version of GeneRec is used, which is equivalent to the contrastive Hebbian learning algorithm (CHL). These are not decorative examples; they determine which carrier and evidence can fill the abstraction's roles.

Why no parent is asserted. Removing those specialist details does not currently yield one live catalog node that is a necessary genus for every instance. The entry is therefore approved as unparented rather than attached by topical resemblance. Its collapse evidence remains specific—FFFB inhibition can be efficiently implemented by using the average excitatory input and activity levels in a given layer.—and future graph densification may discover a defensible relation only if it preserves that boundary.

Approved unparented node. No current live node supplies a defensible necessary genus or structural prerequisite for Leabra. The reviewed identity is: Leabra is heavily influenced by and contributes to neural network designs and models, including emergent. The accelerated suggestion was declined because topical or lexical similarity does not establish hierarchy; the node is admitted without a parent pending later graph densification.
Related reasoning operations. Evidence, representation, comparison, classification, transformation, or evaluation may participate in particular cases, but participation does not make any one of them a necessary parent of every instance.

Neighborhood in Abstraction Space¶

Leabra sits in a sparse region of the domain-specific corpus (66^th percentile for distinctiveness): few abstractions share its structure, so a faithful description tends to retrieve it precisely.

Family — Unclustered & Miscellaneous (2551 abstractions)

Nearest neighbors

Computed from structural-signature embeddings · 2026-10-08

Not to Be Confused With¶

Theory. The parent omits the specialist differentia. Tell: Can the case establish Leabra is heavily influenced by and contributes to neural network designs and models, including emergent?
Error-driven learning. Learning that updates expectations or parameters in proportion to a discrepancy between predicted and observed outcomes, so surprising events produce larger representational change. Tell: Which entry's carrier, operation, and failure condition are satisfied?
Evolutionary Computation. Evolutionary Computation is a recurring identity in computer science and information systems, formal models and representations, mathematics, logic, and statistics defined by: Subfield of artificial intelligence. Tell: Which entry's carrier, operation, and failure condition are satisfied?
Evolutionary acquisition of neural topologies. An evolutionary reinforcement-learning method that jointly evolves artificial-neural-network structure and weights, using structural mutation and evolution-strategy parameter optimization. Tell: Which entry's carrier, operation, and failure condition are satisfied?
A measurement, proxy, or consequence. Those may provide evidence without being the identity. Tell: Would Leabra remain present if the detector or downstream effect changed?
A metaphorical analogue. A similar shape outside computer_science_and_information lacks the specialist mechanism. Tell: Do the native roles transfer literally, or only the parent Theory?

References¶

Frozen Wikipedia discovery revision: https://en.wikipedia.org/wiki/Leabra (revision 1323841045).
Preserved source candidate: https://compcogneuro.org/book
Preserved source candidate: http://grey.colorado.edu/emergent/index.php/Leabra
Preserved source candidate: https://web.archive.org/web/20090416044236/http://grey.colorado.edu/emergent/index.php/Leabra
Preserved source candidate: https://grey.colorado.edu/emergent/index.php/Main_Page
Preserved source candidate: https://web.archive.org/web/20151003234738/https://grey.colorado.edu/emergent/index.php/Main_Page
Preserved source candidate: https://psychology.ucdavis.edu/people/oreilly
Preserved source candidate: https://grey.colorado.edu/svn/emergent/emergent/trunk/Matlab/
Preserved source candidate: https://cran.r-project.org/web/packages/leabRa/

The frozen Wikipedia revision is discovery provenance. The retained source set was reviewed for identity, formal or operational relation, and scope. The encyclopedia's structural synthesis is bounded to those claims; a thin authority surface is recorded as a nonblocking source-strengthening repair rather than concealed.