Sign inSign in
ConceptAI & ML

Floating-point precision in deep learning

The bit representation used for numbers in tensors, where default float32 uses 32 bits but deep learning training can tolerate lower precisions to achieve higher performance.
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Computational workloads1Float32 data type1PyTorch tensors1

Lecturers

1

    Connections

    2

    The lectures that define it or assume it, and the concepts next to it.

    1 lecturer. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.