Equation 4 · Edge AI Electronics and Sensor Systems in Practice: Quantization, Power Budgets, and Sensor Front Ends
What does this equation mean?
Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.
This equation states a bound: one expression must stay on the indicated side of the other under the article’s assumptions. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.
Read it piece by piece
Symbol S
S is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
How to interpret it
Read this expression with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
where r is the real-valued number, q is the stored integer, S > 0 is a scale factor, and Z is an integer zero-point chosen so that real zero maps exactly onto a representable integer — a detail that matters because operations like zero-padding and ReLU depend on zero being represented without rounding error. Jacob and colleagues showed that with this scheme, matrix multiplications and convolutions can be carried out using only integer arithmetic, with the more expensive floating-point rescaling deferred to a single fixed-point multiply per output, and reported close to a fourfold reduction in memory footprint against 32-bit floats with accuracy close to the unquantized model on standard…
Read the full surrounding passage
where r is the real-valued number, q is the stored integer, S > 0 is a scale factor, and Z is an integer zero-point chosen so that real zero maps exactly onto a representable integer — a detail that matters because operations like zero-padding and ReLU depend on zero being represented without rounding error. Jacob and colleagues showed that with this scheme, matrix multiplications and convolutions can be carried out using only integer arithmetic, with the more expensive floating-point rescaling deferred to a single fixed-point multiply per output, and reported close to a fourfold reduction in memory footprint against 32-bit floats with accuracy close to the unquantized model on standard image classification and detection benchmarks [ 1 ] .
Sources cited in the surrounding passage
These citations give research context. Read each source to check which claims it supports.