Spatial-Temporal Spike Signal Encoding Circuit
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for encoding spike signals from neurons fail to accurately capture and represent both spatial and temporal information, leading to inefficiencies in processing and storing neural network data.
Innovation Solution
An electronic device comprising cells that receive spatial-temporal input signals, a summation circuit to generate summation signals, and an encoding circuit that compares these signals with a threshold to encode the data into logic values, effectively dividing the data into event units and storing them in a memory cell array.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If spike signals are simplified to logic values (0 or 1), then processing complexity is reduced, but spatial-temporal information is lost
Solution Approach 1:
The time window is divided into multiple unit times, and the event object is divided into multiple event units. This segmentation allows the system to process temporal information in discrete steps while preserving the spatial distribution of spike signals across different neurons, thus maintaining spatial-temporal information while keeping processing manageable through structured division.
Solution Approach 2:
The patent introduces a temporal dimension by dividing the time window into unit times and creating event units that span multiple time steps. This transforms the simple logic value representation into a multi-dimensional structure where each event unit contains temporal sequences, preserving spatial-temporal information while maintaining logical processing capabilities.
2Measurement precision
If precise formation process of spike signals is modeled using electrical circuits, then accuracy is improved, but device complexity increases
Solution Approach 1:
The patent uses simple logic values (0 or 1) to represent spike signals instead of complex electrical circuit models. This disposable approximation approach sacrifices some physiological accuracy but dramatically reduces device complexity, making the system practical for large-scale neural network processing while retaining essential functional information.
3Loss of information
If all spike signals are processed in detail, then information completeness is improved, but processing time increases
Solution Approach 1:
The system pre-divides the time window into unit times and defines event units before processing begins. This preliminary structuring allows spike signals to be systematically organized and processed in predetermined temporal segments, reducing processing time by avoiding ad-hoc analysis while maintaining complete spatial-temporal information through the structured framework.
Solution Approach 2:
By segmenting the continuous time window into discrete unit times and organizing spike signals into event units, the system enables parallel processing of different time segments and spatial locations, significantly reducing overall processing time while preserving complete information through the segmented structure.
Data Source
AI summary
An electronic device includes first to n-th cells (‘n’ is an integer of 2 or more) that receive spatial-temporal input signals that indicate an event unit in a time window, a summation circuit that sums first to n-th cell signals recorded in the first to n-th cells for each of first to m-th unit times (‘m’ is an integer of 2 or more) dividing the time window to generate first to m-th summation signals, and an encoding circuit that compares each of the first to m-th summation signals with a threshold value to encode the spatial-temporal input signals into a code of the event unit.