Neural network models learning from examples without training
An MIT study shows how large language models can learn a new task from just a few examples, without the need for any new training data.
Stay updated with breaking news from Ekin Aky. Get real-time updates on events, politics, business, and more. Visit us for reliable news and exclusive interviews.
An MIT study shows how large language models can learn a new task from just a few examples, without the need for any new training data.
Researchers theorise that large language models are able to create and train smaller AI models within themselves to learn new tasks.
MIT researchers have explained how large language models like GPT-3 are able to learn new tasks without updating their parameters, despite not being trained to perform those tasks. They found that these large language models write smaller linear models inside their hidden layers, which the large models can train to complete a new task using simple learning algorithms.
Sometimes, machine learning models learn a new task without seeming to have learned – or been trained – to do it. That’s the findings of researchers at [...]