The last decade has seen tremendous progress in AI technology and applications. With such widespread adoption, ensuring the reliability of the AI models is crucial. In past, we took the first step of creating a testing framework called AITEST for metamorphic properties such as fairness, robustness properties for tabular, time-series, and text classification models. In this paper, we extend the capability of the AITEST tool to include the testing techniques for Image and Speech-to-text models along with interpretability testing for tabular models. These novel extensions make AITEST a comprehensive framework for testing AI models.

Several queries and scores have been proposed to explain individual predictions made by ML models. Examples include queries based on "anchors", which are parts of an instance that are sufficient to justify its classification, and "featureperturbation" scores such as SHAP. Given the need for flexible, reliable, and easy-toapply interpretability methods for ML models, we foresee the need for developing declarative languages to naturally specify different explainability queries. We do this in a principled way by rooting such a language in a logic called FOIL, that allows for expressing many simple but important explainability queries, and might serve as a core for more expressive interpretability languages. We study the computational complexity of FOIL queries over classes of ML models often deemed to be easily interpretable: decision trees and more general decision diagrams. Since the number of possible inputs for an ML model is exponential in its dimension, tractability of the FOIL evaluation problem is delicate, but can be achieved by either restricting the structure of the models, or the fragment of FOIL being evaluated. We also present a prototype implementation of FOIL wrapped in a high-level declarative language, and perform experiments showing that such a language can be used in practice.

Treeging combines the flexible mean structure of regression trees with the covariance-based prediction strategy of kriging into the base learner of an ensemble prediction algorithm. In so doing, it combines the strengths of the two primary types of spatial and space-time prediction models: (1) models with flexible mean structures (often machine learning algorithms) that assume independently distributed data, and (2) kriging or Gaussian Process (GP) prediction models with rich covariance structures but simple mean structures. We investigate the predictive accuracy of treeging across a thorough and widely varied battery of spatial and space-time simulation scenarios, comparing it to ordinary kriging, random forest and ensembles of ordinary kriging base learners. Treeging performs well across the board, whereas kriging suffers when dependence is weak or in the presence of spurious covariates, and random forest suffers when the covariates are less informative. Treeging also outperforms these competitors in predicting atmospheric pollutants (ozone and PM$_{2.5}$) in several case studies. We examine sensitivity to tuning parameters (number of base learners and training data sampling proportion), finding they follow the familiar intuition of their random forest counterparts. We include a discussion of scaleability, noting that any covariance approximation techniques that expedite kriging (GP) may be similarly applied to expedite treeging.

If you've heard of "random forests" as a hot, sexy machine learning algorithm and you want to implement it, great! But if you're not sure exactly what happens in a random forest, or how random forests make their classification decisions, then read on:) We'll find that we can break down random forests into smaller, more digestible pieces. As a forest is made of trees, so a random forest is made of a bunch of randomly sampled sub-components called decision trees. So first let's try to understand what a decision tree is, and how it comes to its prediction. For now, we'll just look at classification decision trees.

If we summarize what we've done so far in the "Addressing the problem of overfitting" article series, we've discussed three different techniques that can be used to mitigate overfitting. As you already know, Cross-validation (discussed in Part 1), Regularization (discussed in Part 2) and Dimensionality Reduction (discussed in Part 3) can effectively mitigate overfitting. In Part 4, today we discuss another useful technique called Creating Ensembles. However, this technique is limited to tree-based models. Someone can attempt to build a decision tree model (Step 1) without limiting the tree growth (without early stopping or without doing any hyperparameter tuning).

This transformation of food delivery businesses to online platforms has gained high attention in recent years. This due to the availability of customizing ordering experiences, easy payment methods, fast delivery, and others. The competition between online food delivery providers has intensified to attain a wider range of customers. Hence, they should have a better understanding of their customers' needs and predict their purchasing decisions. Machine learning has a significant impact on companies' bottom line. They are used to construct models and strategies in industries that rely on big data and need a system to evaluate it fast and effectively. Predictive modeling is a type of machine learning that uses various regression algorithms, analytics, and statistics to estimate the probability of an occurrence. The incorporation of predictive models helps online food delivery providers to understand their customers. In this study, a dataset collected from 388 consumers in Bangalore, India was provided to predict their purchasing decisions. Four prediction models are considered: CART and C4.5 decision trees, random forest, and rule-based classifiers, and their accuracies in providing the correct class label are evaluated. The findings show that all models perform similarly, but the C4.5 outperforms them all with an accuracy of 91.67%.

Rule-based models, e.g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity. However, rule-based models are hard to optimize, especially on large data sets, due to their discrete parameters and structures. Ensemble methods and fuzzy/soft rules are commonly used to improve performance, but they sacrifice the model interpretability. To obtain both good scalability and interpretability, we propose a new classifier, named Rule-based Representation Learner (RRL), that automatically learns interpretable non-fuzzy rules for data representation and classification. To train the non-differentiable RRL effectively, we project it to a continuous space and propose a novel training method, called Gradient Grafting, that can directly optimize the discrete model using gradient descent. An improved design of logical activation functions is also devised to increase the scalability of RRL and enable it to discretize the continuous features end-to-end. Exhaustive experiments on nine small and four large data sets show that RRL outperforms the competitive interpretable approaches and can be easily adjusted to obtain a trade-off between classification accuracy and model complexity for different scenarios. Our code is available at: https://github.com/12wang3/rrl.

Hyperparameters are parameters that are defined before training to specify how we want model training to happen. We have full control over hyperparameter settings and by doing that we control the learning process. For example in the random forest model n_estimators (number of decision trees we want to have) is a hyperparameter. It can be set to any integer value but of course, setting it to 10 or 1000 changes the learning process significantly. Parameters, on the other hand, are found during the training. We have no control over parameter values as they are the result of model training.

Once, on a crisp cloudless morning in early fall, a machine learning engineer left her home to seek the answers that she could not find, even in the newly-optimized Google results. She closed her laptop, put on her backpack and hiking boots, and walked quietly out her door and past her mailbox, down a dusty path that led past a stream, until the houses around her gave way to broad fields full of ripening corn. She walked past farms where cows grazed peacefully underneath enormous data silos, until the rows of crops gave way to a smattering of graceful pines and oaks, and she found herself in a forest clearing, headed into the woods. She went deeper through the decision trees and finally stopped near a data stream around midday to have lunch and stretch her legs. The sun made its way through the sky and eventually, she walked further, out of the forest.

In [12], Mourtada, Ga\"{i}ffas and Scornet showed that, under proper tuning of the complexity parameters, random trees and forests built from the Mondrian process in $\mathbb{R}^d$ achieve the minimax rate for $\beta$-H\"{o}lder continuous functions, and random forests achieve the minimax rate for $(1+\beta)$-H\"{o}lder functions in arbitrary dimension. In this work, we show that a much larger class of random forests built from random partitions of $\mathbb{R}^d$ also achieve these minimax rates. This class includes STIT random forests, the most general class of random forests built from a self-similar and stationary partition of $\mathbb{R}^d$ by hyperplane cuts possible, as well as forests derived from Poisson hyperplane tessellations. Our proof technique relies on classical results as well as recent advances on stationary random tessellations in stochastic geometry.