Google patents method to automatically search for best machine learning algorithm
Google has been granted a patent for a method that automatically searches for the best machine learning algorithm to perform a specific task. The system generates a sequence of candidate algorithms, trains each one using provided examples, and evaluates their performance to select the most effective option.
In the filing’s own words
A method for searching for an output machine learning (ML) algorithm to perform an ML task is described. The method includes: receiving a set of training examples and a set of validation examples, and generating a sequence of candidate ML algorithms to perform the task. For each candidate ML algorithm in the sequence, the method includes: setting up one or more training parameters for the candidate ML algorithm by executing a respective candidate setup function, training the candidate ML algorithm by processing the set of training examples using a respective candidate predict function and a respective candidate learn function, and evaluating a performance of the trained candidate ML algorithm by executing the respective candidate predict function on the set of validation examples to determine a performance metric. The method includes selecting a trained candidate ML algorithm with the best performance metric as the output ML algorithm for the task.
What exactly they claim (claim 1)
1. A method for searching for an output machine learning algorithm to perform a particular machine learning task, the method comprising: receiving a set of training examples, each training example in the set of training examples comprising an example input and an example output; receiving a set of validation examples, each validation example in the set of validation examples comprising a validation input and a validation output; generating a sequence of candidate machine learning algorithms to perform the particular machine learning task, comprising searching for one or more candidate machine learning algorithms through a machine learning algorithm search space, wherein each candidate machine learning algorithm in the sequence is represented as a computer program comprising (i) a respective candidate setup function that initializes one or more training parameters of the candidate machine learning algorithm, (ii) a respective candidate learn function that adjusts training parameters of the candidate machine learning algorithm, and (iii) a respective candidate predict function that predicts an output for a given input using the adjusted training parameters, and wherein the machine learning algorithm search space is defined by instructions that act on addresses in a virtual memory to specify mathematical operations that define respective logic for the setup function, the learn function, and the predict function; for each candidate machine learning algorithm in the sequence: setting up one or more training parameters for the candidate machine learning algorithm by executing the candidate setup function, training the candidate machine learning algorithm to adjust the one or more training parameters by processing the set of training examples using the candidate predict function and the candidate learn function, and evaluating a performance of the trained candidate machine learning algorithm by executing the candidate predict function on the set of validation examples to determine a performance metric for the trained candidate machine learning algorithm; and selecting a trained candidate machine learning algorithm with the best performance metric among the trained candidate machine learning algorithms as the output machine learning algorithm for the particular machine learning task.
Facts
- Company
- Google (Google LLC)
- Official title
- Machine learning algorithm search
- Patent number
- US12801979B2
- Application number
- 17795087
- Filed
- Feb 8, 2021
- Granted
- Nov 17, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06N 20/00 Physics & computingG06F 18/217 Physics & computingG06F 18/285 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents method for LLMs to self-correct and learn from mistakes Oct 27, 2026
- Google patents search results that mix real clips with AI-made video Nov 10, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.
