As the complexity of machine learning (ML) models increases, resulting in a lack of prediction explainability, several methods have been developed to explain a model's behavior in terms of the training data points that most influence the model. However, these methods tend to mark outliers as highly influential points, limiting the insights that practitioners can draw from points that are not representative of the training data. In this work, we take a step towards finding influential training points that also represent the training data well. We first review methods for assigning importance scores to training points. Given importance scores, we propose a method to select a set of DIVerse INfluEntial (DIVINE) training points as a useful explanation of model behavior. As practitioners might not only be interested in finding data points influential with respect to model accuracy, but also with respect to other important metrics, we show how to evaluate training data points on the basis of group fairness. Our method can identify unfairness-inducing training points, which can be removed to improve fairness outcomes. Our quantitative experiments and user studies show that visualizing DIVINE points helps practitioners understand and explain model behavior better than earlier approaches.

The ROC (Receiver Operating Characteristic) curve is a way to visualise the performance of a binary classifier. Here, you can interpret 0 as negative and 1 as positive. In order to classify whether a data item is negative or positive, we need to first decide on the classification threshold. For instance, suppose we have trained a model like logistic regression, and this model predicted a $0.4$ probability that a particular observation is negative, and a $0.6$ probability that the observation is positive. If we set the classification threshold to be $0.5$,

The sample business proposal for early detection of Breast Cancer which includes defining business goal, success metric, data collection, model selection and eventually deploying model. In Pakistan, it's getting harder and harder to detect breast cancer due to social factors and the availability of radiologists, even then this process requires focus and time which is a luxury if you are in the middle of a pandemic. The radiologist takes a mammogram and then detect tumor or cancer with the naked eye which can be difficult sometimes and error rates are quite high if you are under stress. Out of one thousand women, about one hundred are recalled for additional diagnostic imaging, and of these one hundred women, four or five are diagnosed with breast cancer (nih.gov) (See Figure 1).

The Controller Area Network (CAN) bus works as an important protocol in the real-time In-Vehicle Network (IVN) systems for its simple, suitable, and robust architecture. The risk of IVN devices has still been insecure and vulnerable due to the complex data-intensive architectures which greatly increase the accessibility to unauthorized networks and the possibility of various types of cyberattacks. Therefore, the detection of cyberattacks in IVN devices has become a growing interest. With the rapid development of IVNs and evolving threat types, the traditional machine learning-based IDS has to update to cope with the security requirements of the current environment. Nowadays, the progression of deep learning, deep transfer learning, and its impactful outcome in several areas has guided as an effective solution for network intrusion detection. This manuscript proposes a deep transfer learning-based IDS model for IVN along with improved performance in comparison to several other existing models. The unique contributions include effective attribute selection which is best suited to identify malicious CAN messages and accurately detect the normal and abnormal activities, designing a deep transfer learning-based LeNet model, and evaluating considering real-world data. To this end, an extensive experimental performance evaluation has been conducted. The architecture along with empirical analyses shows that the proposed IDS greatly improves the detection accuracy over the mainstream machine learning, deep learning, and benchmark deep transfer learning models and has demonstrated better performance for real-time IVN security.

Machine learning algorithms often produce models considered as complex black-box models by both end users and developers. They fail to explain the model in terms of the domain they are designed for. The proposed Iterative Visual Logical Classifier (IVLC) is an interpretable machine learning algorithm that allows end users to design a model and classify data with more confidence and without having to compromise on the accuracy. Such technique is especially helpful when dealing with sensitive and crucial data like cancer data in the medical domain with high cost of errors. With the help of the proposed interactive and lossless multidimensional visualization, end users can identify the pattern in the data based on which they can make explainable decisions. Such options would not be possible in black box machine learning methodologies. The interpretable IVLC algorithm is supported by the Interactive Shifted Paired Coordinates Software System (SPCVis). It is a lossless multidimensional data visualization system with user interactive features. The interactive approach provides flexibility to the end user to perform data classification as self-service without having to rely on a machine learning expert. Interactive pattern discovery becomes challenging while dealing with large data sets with hundreds of dimensions/features. To overcome this problem, this chapter proposes an automated classification approach combined with new Coordinate Order Optimizer (COO) algorithm and a Genetic algorithm. The COO algorithm automatically generates the coordinate pair sequences that best represent the data separation and the genetic algorithm helps optimizing the proposed IVLC algorithm by automatically generating the areas for data classification. The feasibility of the approach is shown by experiments on benchmark datasets covering both interactive and automated processes used for data classification.

We feed the test image to the trained model, compares the predicted output with test image's label to evaluate either it's correct or wrong prediction. At the end, we will have the count of correct matches and the incorrect matches. The key realization we need to make, is that in the real world not all incorrect and correct matches hold equal value. Also in the real world, a single metric won't tell the complete story, that's why previously mentioned four metrics are used to evaluate the model. We could organize our predicted values compared to the real values in a confusion matrix.

In this post, you learn how to create a MLOps project to automate the deployment of an Amazon SageMaker endpoint with multiple production variants for A/B testing. You also deploy a general purpose API and testing infrastructure that includes a multi-armed bandit experiment framework. This testing infrastructure will automatically optimize traffic to the best-performing model over time based on user feedback. Amazon SageMaker MLOps projects are a new capability recently released with Amazon SageMaker Pipelines, the first purpose-built, easy-to-use, continuous integration and continuous delivery (CI/CD) service for ML. The MLOps project template provisions the initial setup required for a complete end-to-end MLOps system, including model building, training, and deployment, and can be customized to support your own organizations requirements.

Butt rot (BR) damages associated with Norway spruce (Picea abies [L.] Karst.) account for considerable economic losses in timber production across the northern hemisphere. While information on BR damages is critical for optimal decision-making in forest management, the maps of BR damages are typically lacking in forest information systems. We predicted timber volume damaged by BR at the stand-level in Norway using harvester information of 186,026 stems (clear-cuts), remotely sensed, and environmental data (e.g. climate and terrain characteristics). We utilized random forest (RF) models with two sets of predictor variables: (1) predictor variables available after harvest (theoretical case) and (2) predictor variables available prior to harvest (mapping case). We found that forest attributes characterizing the maturity of forest, such as remote sensing-based height, harvested timber volume and quadratic mean diameter at breast height, were among the most important predictor variables. Remotely sensed predictor variables obtained from airborne laser scanning data and Sentinel-2 imagery were more important than the environmental variables. The theoretical case with a leave-stand-out cross-validation achieved an RMSE of 11.4 $m^3ha^{-1}$ (pseudo $R^2$: 0.66) whereas the mapping case resulted in a pseudo $R^2$ of 0.60. When the spatially distinct k-means clusters of harvested forest stands were used as units in the cross-validation, the RMSE value and pseudo $R^2$ associated with the mapping case were 15.6 $m^3ha^{-1}$ and 0.37, respectively. This indicates that the knowledge about the BR status of spatially close stands is of high importance for obtaining satisfactory error rates in the mapping of BR damages.

Many modern machine learning applications come with complex and nuanced design goals such as minimizing the worst-case error, satisfying a given precision or recall target, or enforcing group-fairness constraints. Popular techniques for optimizing such non-decomposable objectives reduce the problem into a sequence of cost-sensitive learning tasks, each of which is then solved by re-weighting the training loss with example-specific costs. We point out that the standard approach of re-weighting the loss to incorporate label costs can produce unsatisfactory results when used to train over-parameterized models. As a remedy, we propose new cost-sensitive losses that extend the classical idea of logit adjustment to handle more general cost matrices. Our losses are calibrated, and can be further improved with distilled labels from a teacher model. Through experiments on benchmark image datasets, we showcase the effectiveness of our approach in training ResNet models with common robust and constrained optimization objectives.

This paper analyses the fundamental ingredients behind surrogate explanations to provide a better understanding of their inner workings. We start our exposition by considering global surrogates, describing the trade-off between complexity of the surrogate and fidelity to the black-box being modelled. We show that transitioning from global to local - reducing coverage - allows for more favourable conditions on the Pareto frontier of fidelity-complexity of a surrogate. We discuss the interplay between complexity, fidelity and coverage, and consider how different user needs can lead to problem formulations where these are either constraints or penalties. We also present experiments that demonstrate how the local surrogate interpretability procedure can be made interactive and lead to better explanations.