Online conversations are ubiquitous in modern life, spanning industries from video games to telecommunications. This has led to an exponential growth in the amount of online conversation data, which has helped in the development of state-of-the-art natural language processing (NLP) systems like chatbots and natural language generation (NLG) models. Over time, various NLP techniques for text analysis have also evolved. This necessitates the requirement for a fully managed service that can be integrated into applications using API calls without the need for extensive machine learning (ML) expertise. AWS offers pre-trained AWS AI services like Amazon Comprehend, which can effectively handle NLP use cases involving classification, text summarization, entity recognition, and more to gather insights from text.

It is therefore critical that we question vague conceptions of the field as value-neutral or universally beneficial, and investigate what specific values the field is advancing. In this paper, we present a rigorous examination of the values of the field by quantitatively and qualitatively analyzing 100 highly cited ML papers published at premier ML conferences, ICML and NeurIPS. We annotate key features of papers which reveal their values: how they justify their choice of project, which aspects they uplift, their consideration of potential negative consequences, and their institutional affiliations and funding sources. We find that societal needs are typically very loosely connected to the choice of project, if mentioned at all, and that consideration of negative consequences is extremely rare. We identify 67 values that are uplifted in machine learning research, and, of these, we find that papers most frequently justify and assess themselves based on performance, generalization, efficiency, researcher understanding, novelty, and building on previous work. We present extensive textual evidence and analysis of how these values are operationalized. Notably, we find that each of these top values is currently being defined and applied with assumptions and implications generally supporting the centralization of power. Finally, we find increasingly close ties between these highly cited papers and tech companies and elite universities.

Having the skills and the knowledge to attack every aspect of point cloud processing opens up many ideas and development doors. It is like a toolbox for 3D research creativity and development agility. And at the core, there is this incredible Artificial Intelligence space that targets 3D scene understanding. It is particularly relevant due to its importance for many applications, such as self-driving cars, autonomous robots, 3D mapping, virtual reality, and the Metaverse. And if you are an automation geek like me, it is hard to resist the temptation to have new paths to answer these challenges! This tutorial aims to give you what I consider the essential footing to do just that: the knowledge and code skills for developing 3D Point Cloud Semantic Segmentation systems. But actually, how can we apply semantic segmentation? And how challenging is 3D Machine Learning? Let me present a clear, in-depth 201 hands-on course focused on 3D Machine Learning.

Machine learning is rapidly becoming as ubiquitous as data itself. Quite literally wherever there is an abundance of data, machine learning is somehow intertwined. After all, what utility would data have if we were not able to use it to predict something about the future? Luckily there is a plethora of toolkits and frameworks that have made it rather simple to deploy ML in Python. Specifically, Sklearn has done a terrifically effective job at making ML accessible to developers.

Kernel ridge regression (KRR) has recently attracted renewed interest due to its potential for explaining the transient effects, such as double descent, that emerge during neural network training. In this work, we study how the alignment between the target function and the kernel affects the performance of the KRR. We focus on the truncated KRR (TKRR) which utilizes an additional parameter that controls the spectral truncation of the kernel matrix. We show that for polynomial alignment, there is an \emph{over-aligned} regime, in which TKRR can achieve a faster rate than what is achievable by full KRR. The rate of TKRR can improve all the way to the parametric rate, while that of full KRR is capped at a sub-optimal value. This shows that target alignemnt can be better leveraged by utilizing spectral truncation in kernel methods. We also consider the bandlimited alignment setting and show that the regularization surface of TKRR can exhibit transient effects including multiple descent and non-monotonic behavior. Our results show that there is a strong and quantifable relation between the shape of the \emph{alignment spectrum} and the generalization performance of kernel methods, both in terms of rates and in finite samples.

In Machine Learning (ML), model evaluation is the most challenging step. The confusion matrix is one of the globally utilized performance metrics to evaluate the model for classification tasks. It is also a visualization tool that many ML courses and researchers have used. Moreover, it is a table with two dimensions, i.e., actual class label and predicted class label. The actual class label is represented by a row, while a column in the confusion matrix represents the predicted class label.

In recent years, specific evaluation metrics for time series anomaly detection algorithms have been developed to handle the limitations of the classical precision and recall. However, such metrics are heuristically built as an aggregate of multiple desirable aspects, introduce parameters and wipe out the interpretability of the output. In this article, we first highlight the limitations of the classical precision/recall, as well as the main issues of the recent event-based metrics -- for instance, we show that an adversary algorithm can reach high precision and recall on almost any dataset under weak assumption. To cope with the above problems, we propose a theoretically grounded, robust, parameter-free and interpretable extension to precision/recall metrics, based on the concept of ``affiliation'' between the ground truth and the prediction sets. Our metrics leverage measures of duration between ground truth and predictions, and have thus an intuitive interpretation. By further comparison against random sampling, we obtain a normalized precision/recall, quantifying how much a given set of results is better than a random baseline prediction. By construction, our approach keeps the evaluation local regarding ground truth events, enabling fine-grained visualization and interpretation of algorithmic results. We compare our proposal against various public time series anomaly detection datasets, algorithms and metrics. We further derive theoretical properties of the affiliation metrics that give explicit expectations about their behavior and ensure robustness against adversary strategies.

Autonomous underwater vehicles (AUV) are commonly used in many underwater applications. Recently, the usage of multi-rotor unmanned autonomous vehicles (UAV) for marine applications is receiving more attention in the literature. Usually, both platforms employ an inertial navigation system (INS), and aiding sensors for an accurate navigation solution. In AUV navigation, Doppler velocity log (DVL) is mainly used to aid the INS, while for UAVs, it is common to use global navigation satellite systems (GNSS) receivers. The fusion between the aiding sensor and the INS requires a definition of step size parameter in the estimation process. It is responsible for the solution frequency update and, eventually, its accuracy. The choice of the step size poses a tradeoff between computational load and navigation performance. Generally, the aiding sensors update frequency is considered much slower compared to the INS operating frequency (hundreds Hertz). Such high rate is unnecessary for most platforms, specifically for low dynamics AUVs. In this work, a supervised machine learning based adaptive tuning scheme to select the proper INS step size is proposed. To that end, a velocity error bound is defined, allowing the INS/DVL or the INS/GNSS to act in a sub-optimal working conditions, and yet minimize the computational load. Results from simulations and field experiment show the benefits of using the proposed approach. In addition, the proposed framework can be applied to any other fusion scenarios between any type of sensors or platforms.

Research on Fairness and Bias Mitigation in Machine Learning often uses a set of reference datasets for the design and evaluation of novel approaches or definitions. While these datasets are well structured and useful for the comparison of various approaches, they do not reflect that datasets commonly used in real-world applications can have missing values. When such missing values are encountered, the use of imputation strategies is commonplace. However, as imputation strategies potentially alter the distribution of data they can also affect the performance, and potentially the fairness, of the resulting predictions, a topic not yet well understood in the fairness literature. In this article, we investigate the impact of different imputation strategies on classical performance and fairness in classification settings. We find that the selected imputation strategy, along with other factors including the type of classification algorithm, can significantly affect performance and fairness outcomes. The results of our experiments indicate that the choice of imputation strategy is an important factor when considering fairness in Machine Learning. We also provide some insights and guidance for researchers to help navigate imputation approaches for fairness.

Survival analysis encompasses a collection of statistical methods for describing time to event data. It originates from clinical studies, where physicians are mostly interested in assessing the effect of a new therapy on survival against a control group, or how certain features represent a risk of an adverse event in time. This post introduces the challenges related to survival analysis (censoring) and explains popular metrics to evaluate survival models, sharing practical Python examples along the way. Let us imagine to be clinical researchers. As we want to assess that the new treatment has a significant effect in preventing an adverse event (such as death), we monitor the patients of both groups for a certain period of time. This condition goes under the name of right censoring, and it is a common trait of survival analysis studies.