liveBook · Manning

Mutually exclusive event

As explained in Math and Architectures of Deep Learning

Events that cannot occur together because their pairwise intersections are empty.

Mutually exclusive events cannot occur together: every pair has an empty intersection. If one event occurs, the others do not. When such events are also exhaustive, their union covers every possible outcome. section 5.3.2 section 5.2

For mutually exclusive events, the probability of one event or another is the sum of their probabilities. For an exhaustive collection, that sum equals 1 because one of the events must occur. section 5.3.2 section 5.10

Quantized weights in Statsville

Partition adult weights into S1 (less than 60 kg), S2 (between 60 and 90 kg), and S3 (more than 90 kg). These ranges are mutually exclusive and exhaustive. Their probabilities are 0.25, 0.50, and 0.25, so P(S1 or S2 or S3) = 1. section 5.2 section 5.3.2

The same structure extends to continuous variables. Infinitesimal intervals do not overlap, collectively cover the domain, and replace the discrete probability sum with an integral of the probability density. section 5.6

Table 5.2 Probability distribution for quantized weights of Statsville adults

S1: Less than 60 kg

S2: Between 60 and 90 kg

S3: More than 90 kg

p(X = 1) = 25,000/100,000 = 0.25 p(X = 2) = 50,000/100,000 = 0.5 p(X = 3) = 25,000/100,000 = 0.25

Browse the probability table for the three mutually exclusive weight ranges and their numerical probabilities. section 5.2

How Math and Architectures of Deep Learning covers it

How deep it goes
Defines empty pairwise intersections, relates them to union probabilities, and extends the sum rule from sums to integrals.
Examples
Uses Statsville weight ranges and infinitesimal intervals as discrete and continuous examples.
What you can do after
Evaluate whether events overlap and apply probability addition when events are mutually exclusive.
How it connects
Links mutually exclusive events to exhaustive events, probability distributions, random variables, probability density, and the sum rule.

Also explained in

Compare how 2 books explain mutually exclusive event →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Math and Architectures of Deep Learning. The section links point to the parts of the book it draws on.