How do you decide which algorithm to use?

Here are some important considerations while choosing an algorithm.

1. Size of the training data. It is usually recommended to gather a good amount of data to get reliable predictions.
2. Accuracy and/or Interpretability of the output.
3. Speed or Training time.
4. Linearity.
5. Number of features.

How do you compare two learning algorithms?

The key to a fair comparison of machine learning algorithms is ensuring that each algorithm is evaluated in the same way on the same data. You can achieve this by forcing each algorithm to be evaluated on a consistent test harness. In the example below 6 different algorithms are compared: Logistic Regression.

Why do we perform a hypothesis test when we compare two algorithms in machine learning?

Machine learning models are chosen based on their mean performance, often calculated using k-fold cross-validation. The solution is to use a statistical hypothesis test to evaluate whether the difference in the mean performance between any two algorithms is real or not.

What is the significance of comparing algorithms?

To measure growth of a solution, we often compare size to either the space required by the solution or the time required by the solution. (Frequently it turns out that there is a tradeoff between these two quantities; an algorithm that is relatively fast will use more space than one that is slower.)

Can we design different algorithms for a same problem?

we use different algos for same problem depending upon our requirement. e.g. sorting algorithms : There are lots of sorting algorithms e.g. quick sort, merge sort, bubble sort, bucket sort, insertion sort, selection sort etc etc.

What are different algorithms?

Here is a list of the types of Algorithms to begin with:

• Brute Force algorithm.
• Greedy algorithm.
• Recursive algorithm.
• Backtracking algorithm.
• Divide & Conquer algorithm.
• Dynamic programming algorithm.
• Randomised algorithm.