Back to results
US 2022/0092422 A1Published application
Apparatuses and methods for operating neural networks
AssigneeMicron Technology, Inc.
InventorPerry V. Lea
Life of this patent
Estimating the term…
Abstract
The present disclosure includes apparatuses and methods for operating neural networks. An example apparatus includes a plurality of neural networks, wherein the plurality of neural networks are configured to receive a particular portion of data and wherein each of the plurality of neural networks are configured to operate on the particular portion of data during a particular time period to make a determination regarding a characteristic of the particular portion of data.
Claims21
1-20. (canceled)
An apparatus, comprising:
- a plurality of neural networks, wherein each neural network of the plurality of neural networks operates within a corresponding bank of a plurality of banks of a processing in memory (PIM) device implemented on a chip, and wherein each neural network is configured to:
- receive different training;
- and
- determine, via a plurality of compute components included in the corresponding bank, a characteristic of a particular portion of data.
1 more element
An apparatus, comprising:
- a processing in memory (PIM) device including a plurality of banks, wherein each of the plurality of banks include a plurality of compute components, wherein each of the plurality of banks are configured to operate a neural network, and wherein each neural network is configured to:
- receive different training;
- receive a particular portion of data;
- and
- determine, via the plurality of compute components included in the corresponding bank, a characteristic of the particular portion of data;
- transmit the determined characteristic of the particular portion of data;
- and
- a controller, wherein the controller is coupled to the plurality of neural networks and is configured to:
- receive the determined characteristic of the particular portion of data from each of the plurality of neural networks;
- and
- determine a final characteristic of the particular portion of data based on the determined characteristic of the particular portion of data from each of the plurality of neural networks.
8 more elements
A method comprising:
- training each of a plurality of neural networks differently, wherein each neural network of the plurality of neural networks operates within a corresponding bank of a plurality of banks of a processing in memory (PIM) device implemented on a chip;
- determining, via the plurality of compute components included in the corresponding bank, a characteristic of a particular portion of data at each of the plurality of neural networks;
- and
- determining a final characteristic of the particular portion of data at a controller.
1 more element
Dependencies are inferred from the claim text.