Difference between revisions of "Hybrid Compute-in-Memory: abstract simplified (17695824)"

From WikiPatents
Jump to navigation Jump to search
(Creating a new page)
 
(Creating a new page)
 
(2 intermediate revisions by the same user not shown)
Line 1: Line 1:
−
A compute-in-memory array is a technology that combines computing and memory functions in a single system. In this case, the array is used to implement a filter for a specific layer in a neural network.
+
A compute-in-memory array is described in the abstract. This array is designed to implement a filter for a specific layer in a neural network. The purpose of this filter is to process data by multiplying a set of activation bits with a set of filter weight bits. This multiplication process is performed for each channel within a group of channels. The resulting products are then accumulated through a charge accumulation process using multiple capacitors. Finally, the accumulated charge is digitized to produce the output of the filter.
−
 
 
−
The purpose of the filter is to process data in the form of activation bits. These activation bits are multiplied by filter weight bits for each channel in a set of channels. The multiplication process is carried out using a charge accumulation method, which involves storing and combining charges in a group of capacitors.
 
−
 
 
−
Once the charges have been accumulated, they are digitized, meaning they are converted into a digital representation. This digitized output represents the result of the filter operation.
 
−
 
 
−
Overall, this technology enables efficient and parallel processing of data within a neural network layer by performing the filtering operation directly within the memory array.
 

Latest revision as of 16:20, 1 October 2023

A compute-in-memory array is described in the abstract. This array is designed to implement a filter for a specific layer in a neural network. The purpose of this filter is to process data by multiplying a set of activation bits with a set of filter weight bits. This multiplication process is performed for each channel within a group of channels. The resulting products are then accumulated through a charge accumulation process using multiple capacitors. Finally, the accumulated charge is digitized to produce the output of the filter.

Retrieved from "http://wikipatents.org/index.php?title=Hybrid_Compute-in-Memory:_abstract_simplified_(17695824)&oldid=416"