Supervised Learning is the crown jewel of Machine Learning. A couple years ago, Harvard Business Review released an article with the following title "Data Scientist: The Sexiest Job of the 21st Century." Ever since its release, Data Science or Statistics Departments become widely pursued by college students and, and Data Scientists (Nerds), for the first time, is referred to as being sexy. For some industries, Data Scientists have reshaped the corporation structure and reallocated a lot of decision-makings to the "front-line" workers. Being able to generate useful business insights from data has never been so easy.

Supervised Learning is the crown jewel of Machine Learning. A couple years ago, Harvard Business Review released an article with the following title "Data Scientist: The Sexiest Job of the 21st Century." Ever since its release, Data Science or Statistics Departments become widely pursued by college students and, and Data Scientists (Nerds), for the first time, is referred to as being sexy. For some industries, Data Scientists have reshaped the corporation structure and reallocated a lot of decision-makings to the "front-line" workers. Being able to generate useful business insights from data has never been so easy.

Uncertainty quantification for deep learning is a challenging open problem. Bayesian statistics offer a mathematically grounded framework to reason about uncertainties; however, approximate posteriors for modern neural networks still require prohibitive computational costs. We propose a family of algorithms which split the classification task into two stages: representation learning and uncertainty estimation. We compare four specific instances, where uncertainty estimation is performed via either an ensemble of Stochastic Gradient Descent or Stochastic Gradient Langevin Dynamics snapshots, an ensemble of bootstrapped logistic regressions, or via a number of Monte Carlo Dropout passes. We evaluate their performance in terms of \emph{selective} classification (risk-coverage), and their ability to detect out-of-distribution samples. Our experiments suggest there is limited value in adding multiple uncertainty layers to deep classifiers, and we observe that these simple methods strongly outperform a vanilla point-estimate SGD in some complex benchmarks like ImageNet.

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.

An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence (AI) algorithms in spheres ranging from healthcare, transportation, and education to college admissions, recruitment, provision of loans and many more realms. Since they now touch on many aspects of our lives, it is crucial to develop AI algorithms that are not only accurate but also objective and fair. Recent studies have shown that algorithmic decision-making may be inherently prone to unfairness, even when there is no intention for it. This paper presents an overview of the main concepts of identifying, measuring and improving algorithmic fairness when using AI algorithms. The paper begins by discussing the causes of algorithmic bias and unfairness and the common definitions and measures for fairness. Fairness-enhancing mechanisms are then reviewed and divided into pre-process, in-process and post-process mechanisms. A comprehensive comparison of the mechanisms is then conducted, towards a better understanding of which mechanisms should be used in different scenarios. The paper then describes the most commonly used fairness-related datasets in this field. Finally, the paper ends by reviewing several emerging research sub-fields of algorithmic fairness.

A validation dataset is a sample of data held back from training your model that is used to give an estimate of model skill while tuning the model's hyperparameters. The validation dataset is different from the test dataset that is also held back from the training of the model, but is instead used to give an unbiased estimate of the skill of the final tuned model when comparing or selecting between final models. There is much confusion in applied machine learning about what a validation dataset is exactly and how it differs from a test dataset. Validation techniques in machine learning are used to get the error rate of the ML model, which can be considered as close to the true error rate of the population. If the data volume is large enough to be representative of the population, you may not need the validation techniques.

How can we enable machines to make sense of the world, and become better at learning? To approach this goal, I believe viewing intelligence in terms of many integral aspects, and also a universal two-term tradeoff between task performance and complexity, provides two feasible perspectives. In this thesis, I address several key questions in some aspects of intelligence, and study the phase transitions in the two-term tradeoff, using strategies and tools from physics and information. Firstly, how can we make the learning models more flexible and efficient, so that agents can learn quickly with fewer examples? Inspired by how physicists model the world, we introduce a paradigm and an AI Physicist agent for simultaneously learning many small specialized models (theories) and the domain they are accurate, which can then be simplified, unified and stored, facilitating few-shot learning in a continual way. Secondly, for representation learning, when can we learn a good representation, and how does learning depend on the structure of the dataset? We approach this question by studying phase transitions when tuning the tradeoff hyperparameter. In the information bottleneck, we theoretically show that these phase transitions are predictable and reveal structure in the relationships between the data, the model, the learned representation and the loss landscape. Thirdly, how can agents discover causality from observations? We address part of this question by introducing an algorithm that combines prediction and minimizing information from the input, for exploratory causal discovery from observational time series. Fourthly, to make models more robust to label noise, we introduce Rank Pruning, a robust algorithm for classification with noisy labels. I believe that building on the work of my thesis we will be one step closer to enable more intelligent machines that can make sense of the world.

When creating text classification systems, one of the major bottlenecks is the annotation of training data. Active learning has been proposed to address this bottleneck using stopping methods to minimize the cost of data annotation. An important capability for improving the utility of stopping methods is to effectively forecast the performance of the text classification models. Forecasting can be done through the use of logarithmic models regressed on some portion of the data as learning is progressing. A critical unexplored question is what portion of the data is needed for accurate forecasting. There is a tension, where it is desirable to use less data so that the forecast can be made earlier, which is more useful, versus it being desirable to use more data, so that the forecast can be more accurate. We find that when using active learning it is even more important to generate forecasts earlier so as to make them more useful and not waste annotation effort. We investigate the difference in forecasting difficulty when using accuracy and F-measure as the text classification system performance metrics and we find that F-measure is more difficult to forecast. We conduct experiments on seven text classification datasets in different semantic domains with different characteristics and with three different base machine learning algorithms. We find that forecasting is easiest for decision tree learning, moderate for Support Vector Machines, and most difficult for neural networks.

The Information Bottleneck (IB) principle offers a unified approach to many learning and prediction problems. Although optimal in an information-theoretic sense, practical applications of IB are hampered by a lack of accurate high-dimensional estimators of mutual information, its main constituent. We propose to combine IB with invertible neural networks (INNs), which for the first time allows exact calculation of the required mutual information. Applied to classification, our proposed method results in a generative classifier we call IB-INN. It accurately models the class conditional likelihoods, generalizes well to unseen data and reliably recognizes out-of-distribution examples. In contrast to existing generative classifiers, these advantages incur only minor reductions in classification accuracy in comparison to corresponding discriminative methods such as feed-forward networks. Furthermore, we provide insight into why IB-INNs are superior to other generative architectures and training procedures and show experimentally that our method outperforms alternative models of comparable complexity.

Computer vision based melanoma diagnosis has been a side project of mine on and off for almost 2 years now, so I plan on making this the first of a short series of posts on the topic. This post is intended as a quick/informative read for those with basic machine learning experience looking for an introduction to the ISIC problem, and those just getting out of their first or second machine learning/data mining course who'd like a simple problem to get their hands dirty with. Tools for early diagnosis of different diseases are a major reason machine learning has a lot of people excited today. The process for these innovations is a long one: Labeled datasets need built, engineers and data scientists need trained, and each problem comes with its own set of edge cases that often make building robust classifiers very tricky (even for the experts). Here I'm going to focus on building a classifier.