Omgwtfpeoplestopandcountalready!

Omgwtfpeoplestopandcountalready! You know how decades work, right? No. Obviously not.

独家优惠奖金 100% 高达 1 BTC + 180 免费旋转

Choosing ML Algorithms for Real World Applications

Choosing good machine learning algorithm comes easily with experience but for a beginner it can be daunting

A machine learning algorithm is method to understand your data and occasionally predict future events based on it. Phrases like deep learning, CNNs, recommendation systems, clustering can often be seen being thrown around in companies, startups and by professors.

As a beginner with real world data, where does one start?

There are broadly 3 metrics that drive your choice

There are 2 aspects of the data that affect your choice of algorithm. The first is the form of data e.g. whether it is labelled or not. Supervised algorithms are best suited for well-labelled data. Algorithms like linear regression, logistic regression, neural networks, random forests etc. are all examples of supervised algorithms.

On the other hand if your data has no labels or has sparse labels then one can use unsupervised learning algorithms like clustering.

The second aspect of input data that affects your choice of algorithm is the inherent problems with the data e.g. missing data, a lot of noise in the data, lack of enough data etc.

So for example there are a lot of outliers in your data then linear regression will perform extremely poorly but decision trees would be a fairly stable solution.

Similarly missing data affects Naive Bayes much more than it affects Neural Networks. SVM would perform much better than a Deep Neural Network when there is not enough of training data.

Omgwtfpeoplestopandcountalready!

Choosing ML Algorithms for Real World Applications

Choosing good machine learning algorithm comes easily with experience but for a beginner it can be daunting

Add a comment

Related posts:

Some Thoughts on DAO Structures

Visualize OD data with Flowmap.blue

Aranhas