In model serving, having one fixed model during the entire often life-long inference process is usually detrimental to model performance, as data distribution evolves over time, resulting in lack of reliability of the model trained on historical data. It is important to detect changes and retrain the model in time. The existing methods generally have three weaknesses: 1) using only classification error rate as signal, 2) assuming ground truth labels are immediately available after features from samples are received and 3) unable to decide what data to use to retrain the model when change occurs. We address the first problem by utilizing six different signals to capture a wide range of characteristics of data, and we address the second problem by allowing lag of labels, where labels of corresponding features are received after a lag in time. For the third problem, our proposed method automatically decides what data to use to retrain based on the signals. Extensive experiments on structured and unstructured data for different type of data changes establish that our method consistently outperforms the state-of-the-art methods by a large margin.

Supervised learning models are one of the most fundamental classes of models. Viewing supervised learning from a probabilistic perspective, the set of training data to which the model is fitted is usually assumed to follow a stationary distribution. However, this stationarity assumption is often violated in a phenomenon called concept drift, which refers to changes over time in the predictive relationship between covariates $\mathbf{X}$ and a response variable $Y$ and can render trained models suboptimal or obsolete. We develop a comprehensive and computationally efficient framework for detecting, monitoring, and diagnosing concept drift. Specifically, we monitor the Fisher score vector, defined as the gradient of the log-likelihood for the fitted model, using a form of multivariate exponentially weighted moving average, which monitors for general changes in the mean of a random vector. In spite of the substantial performance advantages that we demonstrate over popular error-based methods, a score-based approach has not been previously considered for concept drift monitoring. Advantages of the proposed score-based framework include applicability to any parametric model, more powerful detection of changes as shown in theory and experiments, and inherent diagnostic capabilities for helping to identify the nature of the changes.

Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical applications. In this paper, we introduce a novel target criterion for model confidence, namely the true class probability (TCP). We show that TCP offers better properties for confidence estimation than standard maximum class probability (MCP). Since the true class is by essence unknown at test time, we propose to learn TCP criterion from data with an auxiliary model, introducing a specific learning scheme adapted to this context. We evaluate our approach on the task of failure prediction and of self-training with pseudo-labels for domain adaptation, which both necessitate effective confidence estimates. Extensive experiments are conducted for validating the relevance of the proposed approach in each task. We study various network architectures and experiment with small and large datasets for image classification and semantic segmentation. In every tested benchmark, our approach outperforms strong baselines.

Fraudsters are getting smarter and have more access to information than ever before. Old methods of authentication -- such as passwords, PINs or even bank account numbers -- can easily be obtained by fraudsters on the dark web. To outsmart bad actors and keep customers' information safe, financial organizations should consider how tools like AI can minimize opportunities for fraud and add an extra layer of protection into their security systems. Fighting fraud has always been a key challenge in the finance industry -- especially as fraudsters get more advanced in their approaches. A 2019 survey revealed that more than 60% of banks and other financial institutions saw the volume of fraudulent activity increase from the year before.

The field of machine learning can broadly be categorised into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning uses previous examples with known outputs to determine an appropriate mathematical function to solve a classification or a regression problem. This post focusses on ROC (Receiver Operating Characteristics) curve that is widely used in the machine learning community to assess the performance of a classification algorithm. This post will help you intuitively understand what an ROC curve is and help you implement it in both R and Python. This article is divided into four parts, each dealing with an objective stated above.

Objective: Causality mining is an active research area, which requires the application of state-of-the-art natural language processing techniques. In the healthcare domain, medical experts create clinical text to overcome the limitation of well-defined and schema driven information systems. The objective of this research work is to create a framework, which can convert clinical text into causal knowledge. Methods: A practical approach based on term expansion, phrase generation, BERT based phrase embedding and semantic matching, semantic enrichment, expert verification, and model evolution has been used to construct a comprehensive causality mining framework. This active transfer learning based framework along with its supplementary services, is able to extract and enrich, causal relationships and their corresponding entities from clinical text. Results: The multi-model transfer learning technique when applied over multiple iterations, gains performance improvements in terms of its accuracy and recall while keeping the precision constant. We also present a comparative analysis of the presented techniques with their common alternatives, which demonstrate the correctness of our approach and its ability to capture most causal relationships. Conclusion: The presented framework has provided cutting-edge results in the healthcare domain. However, the framework can be tweaked to provide causality detection in other domains, as well. Significance: The presented framework is generic enough to be utilized in any domain, healthcare services can gain massive benefits due to the voluminous and various nature of its data. This causal knowledge extraction framework can be used to summarize clinical text, create personas, discover medical knowledge, and provide evidence to clinical decision making.

Nowadays, heart disease is the leading cause of death worldwide. Predicting heart disease is a complex task since it requires experience along with advanced knowledge. Internet of Things (IoT) technology has lately been adopted in healthcare systems to collect sensor values for heart disease diagnosis and prediction. Many researchers have focused on the diagnosis of heart disease, yet the accuracy of the diagnosis results is low. To address this issue, an IoT framework is proposed to evaluate heart disease more accurately using a Modified Deep Convolutional Neural Network (MDCNN). The smartwatch and heart monitor device that is attached to the patient monitors the blood pressure and electrocardiogram (ECG). The MDCNN is utilized for classifying the received sensor data into normal and abnormal. The performance of the system is analyzed by comparing the proposed MDCNN with existing deep learning neural networks and logistic regression. The results demonstrate that the proposed MDCNN based heart disease prediction system performs better than other methods. The proposed method shows that for the maximum number of records, the MDCNN achieves an accuracy of 98.2 which is better than existing classifiers.

Prediction and quantification of future volatility and returns play an important role in financial modelling, both in portfolio optimization and risk management. Natural language processing today allows to process news and social media comments to detect signals of investors' confidence. We have explored the relationship between sentiment extracted from financial news and tweets and FTSE100 movements. We investigated the strength of the correlation between sentiment measures on a given day and market volatility and returns observed the next day. The findings suggest that there is evidence of correlation between sentiment and stock market movements: the sentiment captured from news headlines could be used as a signal to predict market returns; the same does not apply for volatility. Also, in a surprising finding, for the sentiment found in Twitter comments we obtained a correlation coefficient of -0.7, and p-value below 0.05, which indicates a strong negative correlation between positive sentiment captured from the tweets on a given day and the volatility observed the next day. We developed an accurate classifier for the prediction of market volatility in response to the arrival of new information by deploying topic modelling, based on Latent Dirichlet Allocation, to extract feature vectors from a collection of tweets and financial news. The obtained features were used as additional input to the classifier. Thanks to the combination of sentiment and topic modelling our classifier achieved a directional prediction accuracy for volatility of 63%.

Anomalous change detection (ACD) is an important problem in remote sensing image processing. Detecting not only pervasive but also anomalous or extreme changes has many applications for which methodologies are available. This paper introduces a nonlinear extension of a full family of anomalous change detectors. In particular, we focus on algorithms that utilize Gaussian and elliptically contoured (EC) distribution and extend them to their nonlinear counterparts based on the theory of reproducing kernels' Hilbert space. We illustrate the performance of the kernel methods introduced in both pervasive and ACD problems with real and simulated changes in multispectral and hyperspectral imagery with different resolutions (AVIRIS, Sentinel-2, WorldView-2, and Quickbird). A wide range of situations is studied in real examples, including droughts, wildfires, and urbanization. Excellent performance in terms of detection accuracy compared to linear formulations is achieved, resulting in improved detection accuracy and reduced false-alarm rates. Results also reveal that the EC assumption may be still valid in Hilbert spaces. We provide an implementation of the algorithms as well as a database of natural anomalous changes in real scenarios http://isp.uv.es/kacd.html.

Convolutional neural networks (CNNs) are a promising technique for automated glaucoma diagnosis from images of the fundus, and these images are routinely acquired as part of an ophthalmic exam. Nevertheless, CNNs typically require a large amount of well-labeled data for training, which may not be available in many biomedical image classification applications, especially when diseases are rare and where labeling by experts is costly. This paper makes two contributions to address this issue: (1) It introduces a new network architecture and training method for low-shot learning when labeled data are limited and imbalanced, and (2) it introduces a new semi-supervised learning strategy that uses additional unlabeled training data to achieve great accuracy. Our multi-task twin neural network (MTTNN) can use any backbone CNN, and we demonstrate with ResNet-50 and MobileNet-v2 that its accuracy with limited training data approaches the accuracy of a finetuned backbone trained with a dataset that is 50 times larger. We also introduce One-Vote Veto (OVV) self-training, a semi-supervised learning strategy, that is designed specifically for MTTNNs. By taking both self-predictions and contrastive-predictions of the unlabeled training data into account, OVV self-training provides additional pseudo labels for finetuning a pretrained MTTNN. Using a large dataset with more than 50,000 fundus images acquired over 25 years, extensive experimental results demonstrate the effectiveness of low-shot learning with MTTNN and semi-supervised learning with OVV. Three additional, smaller clinical datasets of fundus images acquired under different conditions (cameras, instruments, locations, populations), are used to demonstrate generalizability of the methods. Source code and pretrained models will be publicly available upon publication.