This course takes you from understanding the fundamentals of a machine learning project. Learners will understand and implement supervised learning techniques on real case studies to analyze business case scenarios where decision trees, k-nearest neighbours and support vector machines are optimally used. Learners will also gain skills to contrast the practical consequences of different data preparation steps and describe common production issues in applied ML. To be successful, you should have at least beginner-level background in Python programming (e.g., be able to read and code trace existing code, be comfortable with conditionals, loops, variables, lists, dictionaries and arrays). You should have a basic understanding of linear algebra (vector notation) and statistics (probability distributions and mean/median/mode).

Pre-trained Transformers currently dominate most NLP tasks. They impose, however, limits on the maximum input length (512 sub-words in BERT), which are too restrictive in the legal domain. Even sparse-attention models, such as Longformer and BigBird, which increase the maximum input length to 4,096 sub-words, severely truncate texts in three of the six datasets of LexGLUE. Simpler linear classifiers with TF-IDF features can handle texts of any length, require far less resources to train and deploy, but are usually outperformed by pre-trained Transformers. We explore two directions to cope with long legal texts: (i) modifying a Longformer warm-started from LegalBERT to handle even longer texts (up to 8,192 sub-words), and (ii) modifying LegalBERT to use TF-IDF representations. The first approach is the best in terms of performance, surpassing a hierarchical version of LegalBERT, which was the previous state of the art in LexGLUE. The second approach leads to computationally more efficient models at the expense of lower performance, but the resulting models still outperform overall a linear SVM with TF-IDF features in long legal document classification.

Where am I? This is one of the most critical questions that any intelligent system should answer to decide whether it navigates to a previously visited area. This problem has long been acknowledged for its challenging nature in simultaneous localization and mapping (SLAM), wherein the robot needs to correctly associate the incoming sensory data to the database allowing consistent map generation. The significant advances in computer vision achieved over the last 20 years, the increased computational power, and the growing demand for long-term exploration contributed to efficiently performing such a complex task with inexpensive perception sensors. In this article, visual loop closure detection, which formulates a solution based solely on appearance input data, is surveyed. We start by briefly introducing place recognition and SLAM concepts in robotics. Then, we describe a loop closure detection system's structure, covering an extensive collection of topics, including the feature extraction, the environment representation, the decision-making step, and the evaluation process. We conclude by discussing open and new research challenges, particularly concerning the robustness in dynamic environments, the computational complexity, and scalability in long-term operations. The article aims to serve as a tutorial and a position paper for newcomers to visual loop closure detection.

Get a solid understanding of Support Vector Machines (SVM) Understand the business scenarios where Support Vector Machines (SVM) is applicable Tune a machine learning model's hyperparameters and evaluate its performance. Tune a machine learning model's hyperparameters and evaluate its performance.

A new development in NLP is the construction of hyperbolic word embeddings. As opposed to their Euclidean counterparts, hyperbolic embeddings are represented not by vectors, but by points in hyperbolic space. This makes the most common basic scheme for constructing document representations, namely the averaging of word vectors, meaningless in the hyperbolic setting. We reinterpret the vector mean as the centroid of the points represented by the vectors, and investigate various hyperbolic centroid schemes and their effectiveness at text classification.

Volatile organic compounds (VOCs) are chemicals emitted by various groups, such as foods, bacteria, and plants. While there are specific pathways and biological features significantly related to such VOCs, detection of these is achieved mostly by human odor testing or high-end methods such as gas chromatography–mass spectrometry that can analyze the gaseous component. However, odor characterization can be quite helpful in the rapid classification of some samples in sufficient concentrations. Lower-cost metal-oxide gas sensors have the potential to allow the same type of detection with less training required. Here, we report a portable, battery-powered electronic nose system that utilizes multiple metal-oxide gas sensors and machine learning algorithms to detect and classify VOCs. An in-house circuit was designed with ten metal-oxide sensors and voltage dividers; an STM32 microcontroller was used for data acquisition with 12-bit analog-to-digital conversion. For classification of target samples, a supervised machine learning algorithm such as support vector machine (SVM) was applied to classify the VOCs based on the measurement results. The coefficient of variation (standard deviation divided by mean) of 8 of the 10 sensors stayed below 10%, indicating the excellent repeatability of these sensors. As a proof of concept, four different types of wine samples and three different oil samples were classified, and the training model reported 100% and 98% accuracy based on the confusion matrix analysis, respectively. When the trained model was challenged against new sets of data, sensitivity and specificity of 98.5% and 98.6% were achieved for the wine test and 96.3% and 93.3% for the oil test, respectively, when the SVM classifier was used. These results suggest that the metal-oxide sensors are suitable for usage in food authentication applications.

The emergence of pre-trained language models (PLMs) has shown great success in many Natural Language Processing (NLP) tasks including text classification. Due to the minimal to no feature engineering required when using these models, PLMs are becoming the de facto choice for any NLP task. However, for domain-specific corpora (e.g., financial, legal, and industrial), fine-tuning a pre-trained model for a specific task has shown to provide a performance improvement. In this paper, we compare the performance of four different PLMs on three public domain-free datasets and a real-world dataset containing domain-specific words, against a simple SVM linear classifier with TFIDF vectorized text. The experimental results on the four datasets show that using PLMs, even fine-tuned, do not provide significant gain over the linear SVM classifier. Hence, we recommend that for text classification tasks, traditional SVM along with careful feature engineering can pro-vide a cheaper and superior performance than PLMs.

Distributing machine learning predictors enables the collection of large-scale datasets while leaving sensitive raw data at trustworthy sites. We show that locally training support vector machines (SVMs) and computing their averages leads to a learning technique that is scalable to a large number of users, satisfies differential privacy, and is applicable to non-trivial tasks, such as CIFAR-10. For a large number of participants, communication cost is one of the main challenges. We achieve a low communication cost by requiring only a single invocation of an efficient secure multiparty summation protocol. By relying on state-of-the-art feature extractors (SimCLR), we are able to utilize differentially private convex learners for non-trivial tasks such as CIFAR-10. Our experimental results illustrate that for $1{,}000$ users with $50$ data points each, our scheme outperforms state-of-the-art scalable distributed learning methods (differentially private federated learning, short DP-FL) while requiring around $500$ times fewer communication costs: For CIFAR-10, we achieve a classification accuracy of $79.7\,\%$ for an $\varepsilon = 0.59$ while DP-FL achieves $57.6\,\%$. More generally, we prove learnability properties for the average of such locally trained models: convergence and uniform stability. By only requiring strongly convex, smooth, and Lipschitz-continuous objective functions, locally trained via stochastic gradient descent (SGD), we achieve a strong utility-privacy tradeoff.

A three-phase pulse-width modulation (PWM) rectifier can usually maintain operation when open-circuit faults occur in insulated-gate bipolar transistors (IGBTs), which will lead the system to be unstable and unsafe. Aiming at this problem, based on random forests with transient synthetic features, a data-driven online fault diagnosis method is proposed to locate the open-circuit faults of IGBTs timely and effectively in this study. Firstly, by analysing the open-circuit fault features of IGBTs in the three-phase PWM rectifier, it is found that the occurrence of the fault features is related to the fault location and time, and the fault features do not always appear immediately with the occurrence of the fault. Secondly, different data-driven fault diagnosis methods are compared and evaluated, the performance of random forests algorithm is better than that of support vector machine or artificial neural networks. Meanwhile, the accuracy of fault diagnosis classifier trained by transient synthetic features is higher than that trained by original features. Also, the random forests fault diagnosis classifier trained by multiplicative features is the best with fault diagnosis accuracy can reach 98.32%. Finally, the online fault diagnosis experiments are carried out and the results demonstrate the effectiveness of the proposed method, which can accurately locate the open-circuit faults in IGBTs while ensuring system safety.

Background: Mild cognitive impairment (MCI) is often considered a precursor to Alzheimer's disease (AD) due to the high rate of progression from MCI to AD. Sensitive neural biomarkers may provide a tool for an accurate MCI diagnosis, enabling earlier and perhaps more effective treatment. Despite the availability of numerous neuroscience techniques, electroencephalography (EEG) is the most popular and frequently used tool among researchers due to its low cost and superior temporal resolution. Objective: We conducted a scoping review of EEG and MCI between 2012 and 2022 to track the progression of research in this field. Methods: In contrast to previous scoping reviews, the data charting was aided by co-occurrence analysis using VOSviewer, while data reporting adopted a Patterns, Advances, Gaps, Evidence of Practice, and Research Recommendations (PAGER) framework to increase the quality of the results. Results: Event-related potentials (ERPs) and EEG, epilepsy, quantitative EEG (QEEG), and EEG-based machine learning were the research themes addressed by 2310 peer-reviewed articles on EEG and MCI. Conclusion: Our review identified the main research themes in EEG and MCI with high-accuracy detection of seizure and MCI performed using ERP/EEG, QEEG and EEG-based machine learning frameworks.