AI is all about data, and the representation of the data matters strongly. But after focusing primarily on 8-bit integers and 32‑bit floating-point numbers, the industry is now looking at new formats.

AI/ML training traditionally has been performed using floating point data formats, primarily because that is what was available. But this usually isn’t a viable option for inference on the edge, where ...

I currently have a list of floating point data where successive values are very similar. (The data is just a function sampled at small, regular intervals.) Rather than storing all the values directly, ...

Why floating point is important for developing machine-learning models. What floating-point formats are used with machine learning? Over the last two decades, compute-intensive artificial-intelligence ...