latent representation
An intermediate internal encoding of an input that preserves its information in a form the model can transform into a different output.
As defined in Jeremiah Lowin: Explaining the New AI Paradigm - [Invest Like the Best, EP.307]
Where it comes up · 1
Most important claims · 5 of 5Search all claims for “latent representation” →
- The core idea of modern machine learning, taking an input, transforming it through a latent representation, and outputting it, has not dramatically changed in roughly 15 to 20 years; the progress has come from making models bigger and from refinements and enhancements of the architecture.Jeremiah Lowin: Explaining the New AI Paradigm - [Invest Like the Best, EP.307]
- In a well-built latent space each concept (such as hand count, character color, or watermelon color) sits in its own numeric dimension, so changing one number, for example turning a watermelon from green to orange, changes only that attribute in the output and makes the output step far easier.Jeremiah Lowin: Explaining the New AI Paradigm - [Invest Like the Best, EP.307]
- Going directly from text to pixel coordinates, which expand from a few bytes of characters to thousands or tens of thousands of pixel coordinates, is too large a transformation to be done with precision, so models must pass through intermediate latent representations that preserve the input's meaning.Jeremiah Lowin: Explaining the New AI Paradigm - [Invest Like the Best, EP.307]
- Whether AI behaves like a utility depends on what is produced: an API returning finished images or text is too close to the end product to be a utility, while producing weights or latent representations would be a raw material but would be incredibly difficult to use.Jeremiah Lowin: Explaining the New AI Paradigm - [Invest Like the Best, EP.307]
- A pretrained model can take in any known input type, including text, images, or time series, and convert it into a latent representation that fully describes the input before deciding what output form to produce, so the output format is not fixed at input time.Jeremiah Lowin: Explaining the New AI Paradigm - [Invest Like the Best, EP.307]