AI, Machine Learning, Reinforcement Learning, and MLOps Articles

Learn more about AI, machine learning, reinforcement learning, and MLOps with our insight-packed articles. Our AI blog delves into industrial use of AI, the machine learning blog is more technical, the reinforcement learning blog is industrially renowned, and our mlops blog discusses operational ML.

Principal Component Analysis

Published
Author

Dimensionality Reduction - Principal Component Analysis

Welcome! This workshop is from Winder.ai. Sign up to receive more free workshops, training and videos.

Sometimes data has redundant dimensions. For example, when predicting weight from height data you would expect that information about their eye colour provides no predictive power. In this simple case we can simply remove that feature from the data.

With more complex data it is usual to have combinations of features that provide predictive power. Dimensionality reduction methods attempt to apply a mathematical transformation to the data to shift the data into orthogonal dimensions. In other words they attempt to map data from complex combinations of dimensions (e.g. 3-D) into lower numbers of dimensions (e.g. 1-D).

Read more

Distance Measures with Large Datasets

Published
Author

Distance Measures for Similarity Matching with Large Datasets

Today I had an interesting question from a client that was using a distance metric for similarity matching.

The problem I face is that given one vector v and a list of vectors X how do I calculate the Euclidean distance between v and each vector in X in the most efficient way possible in order to get the top matching vectors?

A distance measure is the measure of how similar one observation is compared to a set of other observations. This is most commonly used in nearest-neighbour models, but is used as a measure of similarity across a range of clustering and classification algorithms.

Read more

603: Nearest Neighbour Tips and Tricks

Published
Author

Dimensionality and domain knowledge

  • Is it right to use the same distance measure for all features?

E.g. height and sex? CPU and Disk space?

  • Some features will have more of an effect than others due to their scales.

???

In this version of the algorithm all features are used in the distance calculation.

This treats all features the same. So a measure of height has the same effect as the measure of sex.

Read more

602: Nearest Neighbour Classification and Regression

Published
Author

More than just similarities

  • Classification: Predict the same class as the nearest observations
  • Regression: Predict the same value as the nearest observations

???

Remember for classification tasks, we want to predict a class for a new observation.

What we could do is predict a class that is the same as the nearest neighbour. Simple!

For regression tasks, we need to predict a value. Again, we could use the value of the nearest neighbour! Simple again!

Read more

601: Similarity and Nearest Neighbours

Published
Author

This section introduces the idea of “similarity”.

Why?:

  • Simplicity
  • Many business tasks require a measure of “similarity”
  • Works well

Business reasoning

Why would businesses want to use a measure of similarity? What business problems map well to similarity classifiers?

  • Find similar companies on a CRM
  • Find similar people in an online dating app
  • Find similar configurations of machines in a data centre
  • Find pictures of cats that look like this cat
  • Recommend products to buy from similar customers
  • Find similar wines

Similarity

What is similarity?

Read more

503: Visualising Overfitting in High Dimensional Problems

Published
Author

Validation curve

One simple method of visualising overfitting is with a validation curve, (a.k.a fitting curve).

This is a plot of a score (e.g. accuracy) verses some parameter in the model.

Let’s compare the make_circles dataset again and vary the SVM->RBF->gamma value.

Validation curve

???

Performance of the SVM->RBF algorithm when altering the parameters of the RBF.

We can see that we are underfitting at low values of \(\gamma\). So we can make the model more complex by allowing the SVM to fit smaller and smaller kernels.

Read more

502: Preventing Overfitting with Holdout

Published
Author

Holdout

We have been using:

  • Training data

Not representative of production.

We want to pretend like we are seeing new data:

  • Hold back some data

???

When we train the model, we do so on some data. This is called training data.

Up to now, we have been using the same training data to measure our accuracy.

If we create a lookup table, our accuracy will be 100%. But this doesn’t generalise to new examples.

Read more

501: Over and Underfitting

Published
Author

Generalisation and overfitting

“enough rope to hang yourself with”

  • We can create classifiers that have a decision boundary of any shape.

Very easy to overfit the data.

This section is all about what overfitting is and why it is bad.

???

Speaking generally, we can create classifiers that correspond to any shape. We have so much flexibility that we could end up overfitting the data.

This is where chance data, data that is noise, is considered a valid part of the model.

Read more

404: Nonlinear, Linear Classification

Published
Author

Nonlinear functions

  • Sometimes data cannot be separated by a simple threshold or linear boundary.

We can also use nonlinear functions as a decision boundary.

???

To represent more complex data, we can introduce nonlinearities. Before we do, bear in mind:

  • More complex interactions between features yield solutions that overfit data; to compensate we will need more data.
  • More complex solutions take a greater amount of computational power
  • Anti-KISS

The simplest way of adding a nonlinearities is to add various permutations of the original features. For example, some feature squared.

Read more

403: Linear Classification

Published
Author

Classification via a model

  • Decision trees created a one-dimensional decision boundary
  • We could easily imagine using a linear model to define a decision boundary

???

Previously we used fixed decision boundaries to segment the data based upon how informative the segmentation would be.

The decision boundary represents a one-dimensional rule that separates the data. We could easily increase the number or complexity of the parameters used to define the boundary.

Read more
}