Sequential Covering and Ant Miner Flashcards
1
Q
What 2 ways can ML be used to optimise algorithms?
A
Model parameters -> ML can be used to model parameters.
Algorithm -> Can be used to optimise the algorithm itself.
2
Q
What is rule-based classification?
A
- A technique for creating a classification model by deriving classification rules from data.
3
Q
Explain how Sequential Covering works…
A
- An algorithm for creating a classification model by deriving classification rules from discrete data.
- Processes data and iteratively adds rules to a set of learned rules. These learned rules can then be used for classification on unseen data instances.
4
Q
What is the benefit of using Ant Miner over sequential covering?
A
- EAs are better at dealing with large data.
- EAs can operate in parallel over a large search space E.g ACO.
5
Q
Explain the process of Ant Miner
A
- Create the Ant Miner graph. Create node for every attribute and perform discretization as needed.
- Connect all attributes except for ones of the same type.
- Send ants along graph
- Assess fitness and adjust pheromones
- Repeat until termination criteria
- Select a set of classification rules (paths) with greatest pheromone values.
6
Q
Explain what the discretization step is and why it’s needed…
A
The process of transforming continuous data into discrete data.
This enables Ant Miner to operate on continuous data.