Software quality assurance activities become increasingly difficult as software systems become more and more complex and continuously grow in size. Moreover, testing becomes even more expensive when dealing with large-scale systems. Thus, to effectively allocate quality assurance resources, researchers have proposed fault prediction (FP) which utilizes machine learning (ML) to predict fault-prone code areas. However, ML algorithms typically make use of stochastic elements to increase the prediction models' generalizability and efficiency of the training process. These stochastic elements, also known as nondeterminism-introducing (NI) factors, lead to variance in the training process and as a result, lead to variance in prediction accuracy and training time. This variance poses a challenge for reproducibility in research. More importantly, while fault prediction models may have shown good performance in the lab (e.g., often-times involving multiple runs and averaging outcomes), high variance of results can pose the risk that these models show low performance when applied in practice. In this work, we experimentally analyze the variance of a state-of-the-art fault prediction approach. Our experimental results indicate that NI factors can indeed cause considerable variance in the fault prediction models' accuracy. We observed a maximum variance of 10.10% in terms of the per-class accuracy metric. We thus, also discuss how to deal with such variance.

Every few weeks, it seems, we are treated to another major breakthrough innovation in artificial intelligence. Whether it is Deep Mind's system beating the world champion Go player, GPT-3 dazzling us with Turing test breaking abilities or DALLE-2 generating images that are simply stunning, it seems like we are on the cusp of general artificial intelligence. In reality, my view is that we are much less advanced than what these news making innovations seem to suggest, and for the typical company that I work with, many of the machine learning and deep learning (ML/DL) models are still living mostly in prototypes and experimental setups. For companies to be successful in their digital transformation, it is not sufficient to use more software and collect more data. We also need to use this capability to collect data for more than traditional data analytics.

Some company managers or stakeholders are pessimistic about machine learning model predictions. Therefore, it is data scientists' reasonability to convince them that the model prediction is credible and also understandable to humans. Therefore, we need to focus not only on creating powerful machine learning/deep learning models, but also make the models interpretable by humans. Interpretability helps in many ways, such as helping us to understand how a model makes a decision, it justifies model prediction and gaining insights, building trust in the model, and it helps us improve the model. There are two types of ML model interpretation -- global and local. Good Examples of inherently explainable models are linear regression and decision trees.

In conclusion to the series where I deployed containers for our ML/DL models for free on Heroku, I will now deploy a web app with 6 Deep Learning models. The Web-App that would be containerized and deployed is Dr. Detect. In the latter half, I will discuss some take-away points related to my experience. The procedure to deploy the web app is the same as discussed in the previous article. There is no difference in the Dockerfile and Requirements.txt

It is hard to agree on the best tools to serve models in production because each problem is unique, and their solutions have different constraints. Therefore, I wanted to choose a solution or a set of tools that would benefit as many people as possible. The solution should be simple enough so that it takes only a few minutes to whip up a working prototype and serve it online and, if needed, can scale to larger-scale problems. The core component of this solution is the BentoML package. It is one of the latest promising players in the MLOps landscape and has already amassed half a million downloads on GitHub.

Practical experience with image/video classification, object detection, speech recognition, machine translation, and similar problems.

The following article will look at various data types and focus on Categorical data and answer as to Why and How to reduce categories and end with hands-on example in Python. The article will also look at a different method which can be used for missing value imputation and reducing categories. Data preprocessing enhances the quality of data to promote the extraction of meaningful insights. In Machine Learning, it refers to the transformation of raw data to make it viable for Machine learning Models. Data can be Continuous or Discrete.

The use of artificial intelligence (AI) technologies has spread across the insurance value chain. In product development, it enables insurers to create more profitable and effective products based on insights from past claims and product uptake in the market. In underwriting, it creates a better understanding of risk for new and underserved markets. Even so, the potential of AI has yet to be fully realized. For now, AI's role in the industry is largely limited to optimizing existing business processes rather than developing new and disruptive business models.

Recent years have witnessed widespread adoption of machine learning (ML)/deep learning (DL) techniques due to their superior performance for a variety of healthcare applications ranging from the prediction of cardiac arrest from one-dimensional heart signals to computer-aided diagnosis (CADx) using multi-dimensional medical images. Notwithstanding the impressive performance of ML/DL, there are still lingering doubts regarding the robustness of ML/DL in healthcare settings (which is traditionally considered quite challenging due to the myriad security and privacy issues involved), especially in light of recent results that have shown that ML/DL are vulnerable to adversarial attacks. In this paper, we present an overview of various application areas in healthcare that leverage such techniques from security and privacy point of view and present associated challenges. In addition, we present potential methods to ensure secure and privacy-preserving ML for healthcare applications. Finally, we provide insight into the current research challenges and promising directions for future research.

Deploying machine-, and in particular deep-learning, (ML/DL) solutions in industry-strength, production quality contexts proves to challenging. This requires a structured engineering approach to constructing and evolving systems that contain ML/DL components. In this paper, we provide a conceptualization of the typical evolution patterns that companies experience when employing ML/DL well as a framework for integrating ML/DL components in systems consisting of multiple types of components. In addition, we provide an overview of the engineering challenges surrounding AI/ML/DL solutions and, based on that, we provide a research agenda and overview of open items that need to be addressed by the research community at large.