What is a quantization?
Overloaded term that could be used in any of the following ways: Reducing the number of bits used to store a model's parameters.
quantization explained in plain English
Overloaded term that could be used in any of the following ways: Reducing the number of bits used to store a model's parameters. For example, suppose a model's parameters are stored as 32-bit floating-point numbers. Quantization converts those parameters from 32 bits down to 4, 8, or 16 bits. Quantization reduces the following: - Compute, memory, disk, and network usage - Time to infer a predication - Power consumption
Example
Practitioners refer to quantization when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- accelerator chip
A category of specialized hardware components designed to perform key computations needed for deep learning algorithms.
- batch inference
The process of inferring predictions on multiple unlabeled examples divided into smaller subsets ("batches").
- checkpoint
Data that captures the state of a model's parameters either during training or after training is completed.
- compute
(Noun) The computational resources used by a model or system, such as processing power, memory, and storage.
- perceptron
A system (either hardware or software) that takes in one or more input values, runs a function on the weighted sum of the inputs, and computes a single output value.
- pure function
A function whose outputs are based only on its inputs, and that has no side effects.
- shard
A logical division of the training set or the model.