# US 2025/0053780 A1 · Scalable and compressive neural network data storage system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0053780 A1
- Document ID: US20250053780A1
- Status: Published application
- Kind: A1
- Application number: 18/662,972
- Filed: 2024-05-13
- Published: 2025-02-13
- Earliest claimed: 2018-09-27
- Assignees: DeepMind Technologies Limited
- Applicants: DeepMind Technologies Limited
- Inventors: Jack William Rae; Timothy Paul Lillicrap; Sergey Bartunov
- Web page: https://patentgrep.com/patent/US20250053780A1

## CPC

- G06N 3/045: Combinations of networks
- G06F 16/2272: {Management thereof}
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/096: Transfer learning
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 3/048: Activation functions
- G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system for compressed data storage using a neural network. The system comprises a memory comprising a plurality of memory locations configured to store data; a query neural network configured to process a representation of an input data item to generate a query; an immutable key data store comprising key data for indexing the plurality of memory locations; an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations; a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.

## Claims

### Claim 1

A system for compressed data storage using a neural network comprising:
a memory comprising a plurality of memory locations configured to store data;
a query neural network configured to process a representation of an input data item to generate a query;
an immutable key data store comprising key data for indexing the plurality of memory locations;
an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations;
a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and
a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.