In recent years, we've seen a resurgence in AI, or artificial intelligence, and machine learning. Machine learning has led to some amazing results, like being able to analyze medical images and predict diseases on-par with human experts. Google's AlphaGo program was able to beat a world champion in the strategy game go using deep reinforcement learning. Machine learning is even being used to program self driving cars, which is going to change the automotive industry forever. Imagine a world with drastically reduced car accidents, simply by removing the element of human error.

Machine learning is now pervasive in every field of inquiry and has lead to breakthroughs in various fields from medical diagnoses to online advertising. Practical machine learning is quite computationally intensive, whether it involves millions of repetitions of simple mathematical methods such as Euclidian Distance or more intricate optimizers or backpropagation algorithms. Such computationally intensive techniques need a fast and expressive language – one that enables scientists to write simple, readable code that performs well. In this post, we introduce a simple machine learning algorithm called K Nearest Neighbors, and demonstrate certain Julia features that allow for its easy and efficient implementation. We will demonstrate that the code we write is inherently generic, and show the use of the same code to run on GPUs via the ArrayFire package.

Last time we investigated the k-nearest-neighbors algorithm and the underlying idea that one can learn a classification rule by copying the known classification of nearby data points. This required that we view our data as sitting inside a metric space; that is, we imposed a kind of geometric structure on our data. One glaring problem is that there may be no reasonable way to do this. While we mentioned scaling issues and provided a number of possible metrics in our primer, a more common problem is that the data simply isn't numeric. For instance, a poll of US citizens might ask the respondent to select which of a number of issues he cares most about. There could be 50 choices, and there is no reasonable way to assign these numerical values so that all are equidistant in the resulting metric space. Another issue is that the quality of the data could be bad. For instance, there may be missing values for some attributes (e.g., a respondent may neglect to answer one or more questions).

K-nearest neighbors, or KNN, is a supervised learning algorithm for either classification or regression. It's super intuitive and has been applied to many types of problems. To make a personalized offer to one customer, you might employ KNN to find similar customers and base your offer on their purchase behaviors. KNN has also been applied to medical diagnosis and credit scoring. This is a post about the K-nearest neighbors algorithm and Python.

In an earlier post, I described work that I had initially done as an Insight Data Engineering Fellow. That work, now merged into Flink's master branch, was to do an efficient exact k-nearest neighbors (KNN) query using quadtrees. I have since worked on an approximate version of the KNN algorithm, and I will discuss one method I used for the approximate version using Z-value based hashing. For large and high dimensional data sets, an exact k-nearest neighbors query can become infeasible. There are many algorithms that reduce the dimensionality of the points by hashing them to lower dimensions.

The result of standardization (or Z-score normalization) is that the features will be rescaled so that they'll have the properties of a standard normal distribution with Standardizing the features so that they are centered around 0 with a standard deviation of 1 is not only important if we are comparing measurements that have different units, but it is also a general requirement for many machine learning algorithms. Intuitively, we can think of gradient descent as a prominent example (an optimization algorithm often used in logistic regression, SVMs, perceptrons, neural networks etc.); with features being on different scales, certain weights may update faster than others since the feature values play a role in the weight updates Other intuitive examples include K-Nearest Neighbor algorithms and clustering algorithms that use, for example, Euclidean distance measures – in fact, tree-based classifier are probably the only classifiers where feature scaling doesn't make a difference. In fact, the only family of algorithms that I could think of being scale-invariant are tree-based methods. Let's take the general CART decision tree algorithm. Without going into much depth regarding information gain and impurity measures, we can think of the decision as "is feature x_i some_val?"

From May to July 2016, over one thousand Kagglers competed in Facebook's fifth recruitment competition: Predicting Check-Ins. In this challenge, Kagglers were required to predict the most probable check-in locations occurring in artificial time and space. As the first place winner, Tom Van de Wiele, notes in this winner's interview, the uniquely designed test dataset contained about one trillion place-observation combinations, posing a huge difficulty to competitors. Tom describes how he quickly rocketed from his first getting started competition on Kaggle to first place in Facebook V through his remarkable insight into data consisting only of x,y coordinates, time, and accuracy using k-nearest neighbors and XGBoost. I have completed two Master programs at two different Belgian universities (Leuven and Ghent), one in Computer Science (2010) and one in Statistics (2016).

Unsupervised nearest neighbors is the foundation of many other learning methods, notably manifold learning and spectral clustering. Supervised neighbors-based learning comes in two flavors: classification for data with discrete labels, and regression for data with continuous labels. The principle behind nearest neighbor methods is to find a predefined number of training samples closest in distance to the new point, and predict the label from these. The number of samples can be a user-defined constant (k-nearest neighbor learning), or vary based on the local density of points (radius-based neighbor learning). The distance can, in general, be any metric measure: standard Euclidean distance is the most common choice. Neighbors-based methods are known as non-generalizing machine learning methods, since they simply "remember" all of its training data (possibly transformed into a fast indexing structure such as a Ball Tree or KD Tree.). Despite its simplicity, nearest neighbors has been successful in a large number of classification and regression problems, including handwritten digits or satellite image scenes.

Techniques such as clusterization, neural networks and decision making usually rely on algorithms that are not well suited to deal with missing values. However, real world data frequently contains such cases. The simplest solution is to either substitute them by a best guess value or completely disregard the missing values. Unfortunately, both approaches can lead to biased results. In this paper, we propose a technique for dealing with missing values in heterogeneous data using imputation based on the k-nearest neighbors algorithm. It can handle real (which we refer to as crisp henceforward), interval and fuzzy data. The effectiveness of the algorithm is tested on several datasets and the numerical results are promising.

This paper functions as a tutorial for individuals interested to enter the field of information retrieval but wouldn't know where to begin from. It describes two fundamental yet efficient image retrieval techniques, the first being k - nearest neighbors (knn) and the second support vector machines(svm). The goal is to provide the reader with both the theoretical and practical aspects in order to acquire a better understanding. Along with this tutorial we have also developed the equivalent software1 using the MATLAB environment in order to illustrate the techniques, so that the reader can have a hands-on experience.