Learn Before
Maximum Probability Decision Rule
In probabilistic classification, a model's output is a probability distribution over a set of possible labels. To determine the final prediction, a decision rule is applied which selects the single label that corresponds to the highest probability within this distribution.
0
1
Tags
Ch.1 Pre-training - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Sample Calculation of Softmax Output Layer
Example of a SoftMax activation transformation
Maximum Probability Decision Rule
Consider a 4-class classification problem where the final layer of a model produces the following pre-activation scores for a single input:
[1.0, 2.0, 1.5, 5.0]. The model then uses an activation function that exponentiates each score and normalizes the results to produce a probability distribution. Without performing the full calculation, which of the following statements best describes the resulting probability distribution?Calculating an Output Probability
Classifier Output Analysis
Computational Cost of Fully Connected Layers
Learn After
Inference Process with a Fine-Tuned Model
A probabilistic model is designed to classify news headlines into one of four categories: 'Business', 'Technology', 'Sports', or 'Health'. For a new headline, the model outputs the following probability distribution:
- Business: 0.12
- Technology: 0.25
- Sports: 0.55
- Health: 0.08
Based on the most common decision rule for converting these probabilities into a single prediction, which category will be assigned to the headline?
Customer Support Ticket Classification
Explaining the Prediction Rule