Hierarchical Cognitron
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- NHK Broadcasting Science Research Laboratories
- Organisation type
- Industry
- Country
- Japan
- Published
- 1 April 1984
- Authors
- K. Fukushima
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Other
- Task
- Pattern recognition
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 9.3K
- Training data
- 5 tokens
Parameters 5*5*9*3*3 + 3*3*9*3*3*9 + 9*3*3*9 = 9315 "The numbers of excitatory cells in these four layers were: 7x7 in U0, 5x5 in U1, 3x3 in U2, and 9 in U3" "Each feature-extracting cell in layer U1 receives excitatory modifiable afferent connections from 3x3 cells in layer U0" "On the other hand, each feature, each extracting cell in layers U2 and U3 receives excitatory modifiable connections from all 9 cells in each of the 3 x 3 hypercolumns in the layer preceding it. Therefore, it receives …
"Five training patterns used for the self-organization are shown in Fig. 4"
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- Historical significance
- Record confidence
- Speculative
Sources
Where this record came from and when it was last checked.
- Reference
- A hierarchical neural network model for associative memory
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Hierarchical Cognitron was published by NHK Broadcasting Science Research Laboratories, in the country recorded as Japan, during April 1984. The category the publisher falls under is industry.
It works in the domain of Other, and is recorded as performing the task of pattern recognition.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
The training set ran to roughly 5 tokens of text.
It is tracked in the underlying dataset for one reason in particular: historical significance.
Answers
Hierarchical Cognitron — common questions
Hierarchical Cognitron— what is it used for?
It works in the domain of Other, and is recorded as handling the task of pattern recognition. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Hierarchical Cognitron— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Hierarchical Cognitron— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
Hierarchical Cognitron— how many parameters does it have?
It has a parameter count of 9.3K. Parameters 5*5*9*3*3 + 3*3*9*3*3*9 + 9*3*3*9 = 9315 "The numbers of excitatory cells in these four layers were: 7x7 in U0, 5x5 in U1, 3x3 in U2, and 9 in U3" "Each feature-extracting cell in layer U1 receives excitatory modifiable afferent connections from 3x3 cells in layer U0" "On the other hand, each feature, each extracting cell in layers U2 and U3 receives excitatory modifiable connections from all 9 cells in each of the 3 x 3 hypercolumns in the layer preceding it. Therefore, it receives 3 x 3 x 9 afferent excitatory modifiable connections altogether". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Hierarchical Cognitron— who created it?
It was published by NHK Broadcasting Science Research Laboratories, based in Japan, an organisation categorised as industry.
Hierarchical Cognitron— when was it released?
It was published in April 1984. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.