As statistical classifiers become integrated into real-world applications, it is important to consider not only their accuracy but also their robustness to changes in the data distribution. Although identifying and controlling for confounding variables Z - correlated with both the input X of a classifier and its output Y - has been assiduously studied in empirical social science, it is often neglected in text classification. This can be understood by the fact that, if we assume that the impact of confounding variables does not change between the time we fit a model and the time we use it, then prediction accuracy should only be slightly affected. We show in this paper that this assumption often does not hold and that when the influence of a confounding variable changes from training time to prediction time (i.e. under confounding shift), the classifier accuracy can degrade rapidly. We use Pearl's back-door adjustment as a predictive framework to develop a model robust to confounding shift under the condition that Z is observed at training time. Our approach does not make any causal conclusions but by experimenting on 6 datasets, we show that our approach is able to outperform baselines 1) in controlled cases where confounding shift is manually injected between fitting time and prediction time 2) in natural experiments where confounding shift appears either abruptly or gradually 3) in cases where there is one or multiple confounders. Finally, we discuss multiple issues we encountered during this research such as the effect of noise in the observation of Z and the importance of only controlling for confounding variables.

Epilepsy is the most common neurological disorder and an accurate forecast of seizures would help to overcome the patient's uncertainty and helplessness. In this contribution, we present and discuss a novel methodology for the classification of intracranial electroencephalography (iEEG) for seizure prediction. Contrary to previous approaches, we categorically refrain from an extraction of hand-crafted features and use a convolutional neural network (CNN) topology instead for both the determination of suitable signal characteristics and the binary classification of preictal and interictal segments. Three different models have been evaluated on public datasets with long-term recordings from four dogs and three patients. Overall, our findings demonstrate the general applicability. In this work we discuss the strengths and limitations of our methodology.

Connectionist temporal classification (CTC) training criterion provides an alternative acoustic model (AM) training strategy for automatic speech recognition in an end-to-end fashion. Although CTC criterion benefits acoustic modeling without needs of time-aligned phonetics transcription, it remains in need of efforts of tweaking to convergence, especially in the resource-constrained scenario. In this paper, we proposed to improve CTC training by incorporating acoustic landmarks. We tailored a new set of acoustic landmarks to help CTC training converge more quickly while also reducing recognition error rates. We leveraged new target label sequences mixed with both phone and manner changes to guide CTC training. Experiments on TIMIT demonstrated that CTC based acoustic models converge faster and smoother significantly when they are augmented by acoustic landmarks. The models pretrained with mixed target labels can be finetuned furthermore, which reduced phone error rate by 8.72% on TIMIT. The consistent performance gain is also observed on reduced TIMIT and WSJ as well, in which case, we are the first to succeed in testing the effectiveness of acoustic landmark theory on mid-sized ASR tasks.

As advanced machine learning algorithms are gaining acceptance across many organizations and domains, machine learning interpretability is growing in importance to help extract insight and clarity regarding how these algorithms are performing and why one prediction is made over another. There are many methodologies to interpret machine learning results (i.e. However, some recent R packages that focus purely on ML interpretability agnostic to any specific ML algorithm are gaining popularity. One such package is DALEX and this post covers what this package does (and does not do) so that you can determine if it should become part of your preferred machine learning toolbox. We implement machine learning models using H2O, a high performance ML toolkit. Let's see how DALEX and H2O work together to get the best of both worlds with high performance and feature explainability!

This article in a continuation in my series of articles aimed at'Explainable Artificial Intelligence (XAI)'. If you haven't checked out the first article, I would definitely recommend you to take a quick glance at'Part I -- The Importance of Human Interpretable Machine Learning' which covers the what and why of human interpretable machine learning and the need and importance of model interpretation along with its scope and criteria. In this article, we will be picking up from where we left off and expand further into the criteria of machine learning model interpretation methods and explore techniques for interpretation based on scope. The aim of this article is to give you a good understanding of existing, traditional model interpretation methods, their limitations and challenges. We will also cover the classic model accuracy vs. model interpretability trade-off and finally take a look at the major strategies for model interpretation. Briefly, we will be covering the following aspects in this article. This should get us set and ready for the detailed hands-on guide to model interpretation coming in Part 3, so stay tuned! Model interpretation at heart, is to find out ways to understand model decision making policies better.

Predictive models such as decision trees and neural networks may produce discrimination in their predictions. This paper proposes a method to post-process the predictions of a predictive model to make the processed predictions non-discriminatory. The method considers multiple protected variables together. Multiple protected variables make the problem more challenging than a simple protected variable. The method uses a well-cited discrimination metric and adapts it to allow the specification of explanatory variables, such as position, profession, education, that describe the contexts of the applications. It models the post-processing of predictions problem as a nonlinear optimization problem to find best adjustments to the predictions so that the discrimination constraints of all protected variables are all met at the same time. The proposed method is independent of classification methods. It can handle the cases that existing methods cannot handle: satisfying multiple protected attributes at the same time, allowing multiple explanatory attributes, and being independent of classification model types. An evaluation using four real world data sets shows that the proposed method is as effectively as existing methods, in addition to its extra power.

Logit models are usually applied when studying individual travel behavior, i.e., to predict travel mode choice and to gain behavioral insights on traveler preferences. Recently, some studies have applied machine learning to model travel mode choice and reported higher out-of-sample prediction accuracy than conventional logit models (e.g., multinomial logit). However, there has not been a comprehensive comparison between logit models and machine learning that covers both prediction and behavioral analysis. This paper aims at addressing this gap by examining the key differences in model development, evaluation, and behavioral interpretation between logit and machine-learning models for travel-mode choice modeling. To complement the theoretical discussions, we also empirically evaluated the two approaches on stated-preference survey data for a new type of transit system integrating high-frequency fixed routes and micro-transit. The results show that machine learning can produce significantly higher predictive accuracy than logit models and are better at capturing the nonlinear relationships between trip attributes and mode-choice outcomes. On the other hand, compared to the multinomial logit model, the best-performing machine-learning model, the random forest model, produces less reasonable behavioral outputs (i.e. marginal effects and elasticities) when they were computed from a standard approach. By introducing some behavioral constraints into the computation of behavioral outputs from a random forest model, however, we obtained better results that are somewhat comparable with the multinomial logit model. We believe that there is great potential in merging ideas from machine learning and conventional statistical methods to develop refined models for travel-behavior research and suggest some possible research directions.

Personal electronic devices such as smartphones give access to a broad range of behavioral signals that can be used to learn about the characteristics and preferences of individuals. In this study we explore the connection between demographic and psychological attributes and digital records for a cohort of 7,633 people, closely representative of the US population with respect to gender, age, geographical distribution, education, and income. We collected self-reported assessments on validated psychometric questionnaires based on both the Moral Foundations and Basic Human Values theories, and combined this information with passively-collected multi-modal digital data from web browsing behavior, smartphone usage and demographic data. Then, we designed a machine learning framework to infer both the demographic and psychological attributes from the behavioral data. In a cross-validated setting, our model is found to predict demographic attributes with good accuracy (weighted AUC scores of 0.90 for gender, 0.71 for age, 0.74 for ethnicity). Our weighted AUC scores for Moral Foundation attributes (0.66) and Human Values attributes (0.60) suggest that accurate prediction of complex psychometric attributes is more challenging but feasible. This connection might prove useful for designing personalized services, communication strategies, and interventions, and can be used to sketch a portrait of people with similar worldviews.

Such information includes: the database in modern hospital systems, usually known as Electronic Health Records (EHR), which store the patients' diagnosis, medication, laboratory test results, medical image data, etc.; information on various health behaviors tracked and stored by wearable devices, ubiquitous sensors and mobile applications, such as the smoking status, alcoholism history, exercise level, sleeping conditions, etc.; information collected by census or various surveys regarding sociodemographic factors of the target cohort; and information on people's mental health inferred from their social media activities or social networks such as Twitter, Facebook, etc. These health-related data come from heterogeneous sources, describe assorted aspects of the individual's health conditions. Such data is rich in structure and information which has great research potentials for revealing unknown medical knowledge about genomic epidemiology, disease developments and correlations, drug discoveries, medical diagnosis, mental illness prevention, health behavior adaption, etc. In real-world problems, the number of features relating to a certain health condition could grow exponentially with the development of new information techniques for collecting and measuring data. To reveal the causal influence between various factors and a certain disease or to discover the correlations among diseases from data at such a tremendous scale, requires the assistance of advanced information technology such as data mining, machine learning, text mining, etc. Machine learning technology not only provides a way for learning qualitative relationships among features and patients, but also the quantitative parameters regarding the strength of such correlations.

Modern sensors generate large amounts of timestamped measurement data. These data sets are critical in a wide range of applications including traffic flow prediction, transportation management, GPS navigation, and city planning. Machine learning-based prediction algorithms typically adjust their parameters automatically based on the data, but also require users to set additional parameters, known as hyperparameters. For example, in a kernel-based regression model, the (ordinary) parameters are the regression weights, whereas the hyperparameters include the kernel scales and regularization constants. These hyperparameters have a strong influence on the prediction accuracy. Often, their values are set based on past experience or through time-consuming grid searches. In applications where the characteristics of the data change, such as unusual traffic pattern due to upcoming concert events, these hyperparameters have to be adjusted dynamically in order to maintain prediction quality. In this paper, we use the term hyperparameter learning, hyperparameter optimization, and hyperparameter selection/tuning interchangeably, referring to the process of configuring the model specification before model fitting.