ML Synthesis Runtime Prediction via Outlier Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning-based synthesis runtime prediction methods for IC design use full training data without filtering, leading to inaccurate predictions due to outliers, which is not suitable for real-time IC design runtime prediction.
Innovation Solution
A machine learning-based synthesis runtime prediction method that collects initial training data, selects featured data, builds a machine learning model, measures loss and accuracy, and recursively filters out outliers through standardization, normalization, clustering, and dimensionality reduction to generate filtered training data, thereby improving model accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If full training data is used without filtering, then the training process is simple and fast, but the prediction accuracy deteriorates due to outliers
Solution Approach 1:
The patent applies preliminary action by performing data filtering, standardization, and normalization before training the machine learning model. The system pre-processes the training data to remove outliers and transform features into appropriate ranges, which prevents inaccurate predictions while maintaining a relatively simple overall process structure.
Solution Approach 2:
The patent extracts and removes outlier data points from the training set through clustering analysis and statistical methods. By taking out only the problematic data points rather than processing all data uniformly, the system improves prediction accuracy without significantly increasing computational complexity.
2Measurement precision
If multiple processing steps are added to filter data, then the prediction accuracy improves, but the processing time and complexity increase
Solution Approach 1:
The patent implements feedback mechanisms where the system evaluates prediction accuracy and loss after each processing stage. Based on this feedback, the system dynamically adjusts the filtering and transformation parameters to achieve optimal accuracy with minimal processing time, avoiding unnecessary computational steps.
Solution Approach 2:
The patent changes parameters such as clustering thresholds, standardization factors, and normalization ranges based on the characteristics of the training data. By adapting these parameters to the specific dataset, the system achieves high prediction accuracy while minimizing the time required for data processing.
Data Source
AI summary
A machine learning-based synthesis runtime prediction method includes collecting initial training data from a database, selecting featured training data from the initial training data useful for predicting runtimes, building a machine learning model for predicting the runtimes based on the featured training data, measuring a loss and an accuracy of the machine learning model, performing standardization and/or normalization on the featured training data of the training data to generate updated training data if the loss and/or the accuracy fails to meet predefined criteria, performing clustering at least once on the updated training data to generate clustered training data, identifying at least one outlier from the clustered training data, removing the at least one outlier to generate filtered training data, and preprocessing, training and testing the machine learning model based on the filtered training data until the loss and the accuracy meet the predefined criteria.