Spiking Neuron Model Time Interval Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Spiking neural networks face inefficiencies in data processing due to the need to wait for previous data processing to complete before inputting new data, leading to prolonged processing times and reduced throughput.
Innovation Solution
A computation apparatus and method that varies signal output index values based on input conditions across time intervals, detects occurrence timings of events, and outputs signals within a predetermined time interval, allowing for simultaneous processing and output of data without waiting for previous data to be fully processed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the neural network waits for previous data processing to complete before inputting new data, then processing accuracy is maintained, but processing time increases and throughput decreases
Solution Approach 1:
The processing time is divided into discrete time intervals, with each interval dedicated to processing specific input data. This segmentation allows the system to systematically manage multiple data processing tasks in sequence while maintaining clear temporal boundaries for each processing operation.
Solution Approach 2:
The system determines in advance which time interval should be used for processing each input data based on the data's input timing. This preliminary assignment of processing intervals enables the network to efficiently schedule and execute multiple processing tasks without waiting for previous operations to fully complete, thereby improving throughput while maintaining processing accuracy.
2Productivity
If spike signal inputs are concentrated near the ends of time intervals, then processing efficiency improves, but timing precision deteriorates
Solution Approach 1:
The system applies different handling strategies for spike signals depending on their position within the time interval. By identifying and specially processing signals that occur near interval boundaries versus those in the middle portions, the system maintains timing precision for boundary signals while achieving efficient processing for signals in optimal positions.
Solution Approach 2:
The system changes the temporal parameter of spike signal processing by adjusting which time intervals are used for processing different input data. This dynamic parameter adjustment allows the network to optimize processing efficiency while distributing signal inputs across different time intervals to avoid harmful concentration near interval ends.
Data Source
AI summary
A computation apparatus includes a spiking neuron model that: varies, for each of a plurality of time intervals, an index value of a signal output based on an input condition of a signal in the time interval; detects an occurrence timing of a prescribed event relating to the index value; and outputs a signal at a timing that is within a first time interval and that is in accordance with the occurrence timing of the prescribed event within a second time interval. The first time interval is included in the plurality of time intervals. The second time interval is included in the plurality of time intervals and is a time interval further in past than the first time interval.