Diffractive Deep Neural Network

Closed weights University of California Los Angeles (UCLA) 8B parameters April 2018

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
University of California Los Angeles (UCLA)
Organisation type
Academia
Country
United States of America
Published
14 April 2018
Authors
Xing Lin, Yair Rivenson, Nezih T Yardimci, Muhammed Veli, Yi Luo, Mona Jarrahi, and Aydogan Ozcan

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Digit recognition
Approach
Supervised

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
8B

"For example, using five 3D-printed transmission layers, containing a total of 0.2 million neurons and ~8.0 billion connections that are trained using deep learning, we experimentally demonstrated the function of a handwritten digit classifier." My understanding is that every connection correspond to the parameter to learn.

Training data
55,000 tokens

size of MNIST "For this task, phase-only transmission masks were designed by training a 5-layer D2NN with ~55,000 images from MNIST handwritten digit database (14). "

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Likely
Citations
2,190

Sources

Where this record came from and when it was last checked.

Reference
All-Optical Machine Learning Using Diffractive Deep Neural Networks
Last updated
25 May 2026

What the numbers mean

What this model is

Diffractive Deep Neural Network was published by University of California Los Angeles (UCLA), in the country recorded as United States of America, during April 2018. It comes out of an organisation categorised as academia.

It works in the domain of Vision, and is recorded as performing the task of digit recognition.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

It was trained on a corpus of about 55,000 tokens of text.

Answers

Diffractive Deep Neural Network — common questions

01

Diffractive Deep Neural Network— how many parameters does it have?

It has a parameter count of 8B. "For example, using five 3D-printed transmission layers, containing a total of 0.2 million neurons and ~8.0 billion connections that are trained using deep learning, we experimentally demonstrated the function of a handwritten digit classifier." My understanding is that every connection correspond to the parameter to learn. 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.

02

Diffractive Deep Neural Network— who created it?

It was published by University of California Los Angeles (UCLA), based in United States of America, an organisation categorised as academia.

03

Diffractive Deep Neural Network— when was it released?

It was published in April 2018. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

Diffractive Deep Neural Network— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of digit recognition. These are the areas it was designed around; they describe intent rather than a hard boundary.

05

Diffractive Deep Neural Network— 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.

06

Diffractive Deep Neural Network— 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.

Source

Original publication

Record last updated 25 May 2026

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.