Ceramic-MLP
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
- Sapienza Università di Roma
- Organisation type
- Academia
- Country
- Italy
- Published
- 7 January 1994
- Authors
- G. Bonifazi, P. Burrascano
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Materials science
- Task
- Pattern classification
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
- 1.9K
- Training data
- 80 tokens
- Epochs
- 5,000
Parameters: 100*16 + 16*16 + 16*2 = 1888 Architecture: "The topology of the classifier was X-Y-Y-2, where X is the number of input components, Y is the number of neurons in each hidden layer and the number of neurons in the output layer is two, which is the number of classes. The two hidden layers were considered to have the same number of nodes for simplification purposes. " Input size: "Each pattern consists of a 10 x 10 pixel sub-image." Hidden size: "Experiments have been made on networks wi…
After the pre-processing phase, a training set of 80 patterns and a testing set of 64 patterns were available.
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 4.5 × 10⁹ FLOP
- How it was established
- Operation counting
Compute estimate: 2*1888*3*400000=4531200000=4.53e9 Training steps: "In Fig. 6 we report the classification results obtained on the testing set in the 12 and 16 component compressed data after 400000 training iterations"
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
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Ceramic powder characterization by multilayer perceptron (MLP) data compression and classification
- Last updated
- 28 November 2025
What the numbers mean
What this model is
Ceramic-MLP was published by Sapienza Università di Roma, in Italy, in January 1994. academia is the category the publisher falls under.
It works in Materials science, and is recorded as doing pattern classification.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training run consumed about 4.5 × 10⁹ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
The training set ran to roughly 80 tokens.
The reason it appears in this catalogue at all is historical significance.
Answers
Ceramic-MLP — common questions
What GPU do I need to run Ceramic-MLP?
None. Ceramic-MLP 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.
Is Ceramic-MLP open source?
The licensing for Ceramic-MLP was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does Ceramic-MLP have?
Ceramic-MLP has 1.9K parameters. Parameters: 100*16 + 16*16 + 16*2 = 1888 Architecture: "The topology of the classifier was X-Y-Y-2, where X is the number of input components, Y is the number of neurons in each hidden layer and the number of neurons in the output layer is two, which is the number of classes. The two hidden layers were considered to have the same number of nodes for simplification purposes. " Input size: "Each pattern consists of a 10 x 10 pixel sub-image." Hidden size: "Experiments have been made on networks with 6, 9, 12 and 16 hidden nodes. ". 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.
Who created Ceramic-MLP?
Ceramic-MLP was published by Sapienza Università di Roma, based in Italy, categorised as academia.
When was Ceramic-MLP released?
Ceramic-MLP was published in January 1994. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Ceramic-MLP used for?
Ceramic-MLP works in Materials science, and is recorded as handling pattern classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train Ceramic-MLP?
Around 4.5 × 10⁹ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
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.