We seek to align agent behavior with a user's objectives in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. The user knows the rewards and unsafe states, but querying the user is expensive. To address this challenge, we propose an algorithm that safely and interactively learns a model of the user's reward function. We start with a generative model of initial states and a forward dynamics model trained on off-policy data. Our method uses these models to synthesize hypothetical behaviors, asks the user to label the behaviors with rewards, and trains a neural network to predict the rewards. The key idea is to actively synthesize the hypothetical behaviors from scratch by maximizing tractable proxies for the value of information, without interacting with the environment. We call this method reward query synthesis via trajectory optimization (ReQueST). We evaluate ReQueST with simulated users on a state-based 2D navigation task and the image-based Car Racing video game. The results show that ReQueST significantly outperforms prior methods in learning reward models that transfer to new environments with different initial state distributions. Moreover, ReQueST safely trains the reward model to detect unsafe states, and corrects reward hacking before deploying the agent.

Deep neural networks are known to achieve superior results i n classification tasks. However, it has been recently shown that they are incapable t o detect examples that are generated by a distribution which is different than the one they have been trained on since they are making overconfident prediction fo r Out-Of-Distribution (OOD) examples. OOD detection has attracted a lot of attenti on recently. In this paper, we review some of the most seminal recent algorit hms in the OOD detection field, we divide those methods into training and po st-training and we experimentally show how the combination of the former with t he latter can achieve state-of-the-art results in the OOD detection task. Since the seminal work of Krizhevsky et al. (2012), Deep Neur al Networks (DNNs) have demonstrated great success in several applications, e.g.

Deep metric learning employs deep neural networks to embed instances into a metric space such that distances between instances of the same class are small and distances between instances from different classes are large. In most existing deep metric learning techniques, the embedding of an instance is given by a feature vector produced by a deep neural network and Euclidean distance or cosine similarity defines distances between these vectors. In this paper, we study deep distributional embeddings of sequences, where the embedding of a sequence is given by the distribution of learned deep features across the sequence. This has the advantage of capturing statistical information about the distribution of patterns within the sequence in the embedding. When embeddings are distributions rather than vectors, measuring distances between embeddings involves comparing their respective distributions. We propose a distance metric based on Wasserstein distances between the distributions and a corresponding loss function for metric learning, which leads to a novel end-to-end trainable embedding model. We empirically observe that distributional embeddings outperform standard vector embeddings and that training with the proposed Wasserstein metric outperforms training with other distance functions.

Support Vector Data Description is a popular method for outlier detection. However, its usefulness largely depends on selecting good hyperparameter values -- a difficult problem that has received significant attention in literature. Existing methods to estimate hyperparameter values are purely heuristic, and the conditions under which they work well are unclear. In this article, we propose LAMA (Local Active Min-Max Alignment), the first principled approach to estimate SVDD hyperparameter values by active learning. The core idea bases on kernel alignment, which we adapt to active learning with small sample sizes. In contrast to many existing approaches, LAMA provides estimates for both SVDD hyperparameters. These estimates are evidence-based, i.e., rely on actual class labels, and come with a quality score. This eliminates the need for manual validation, an issue with current heuristics. LAMA outperforms state-of-the-art competitors in extensive experiments on real-world data. In several cases, LAMA even yields results close to the empirical upper bound.

We study the interpretability of predictive systems that use high-dimensonal behavioral and textual data. Examples include predicting product interest based on online browsing data and detecting spam emails or objectionable web content. Recently, counterfactual explanations have been proposed for generating insight into model predictions, which focus on what is relevant to a particular instance. Conducting a complete search to compute counterfactuals is very time-consuming because of the huge dimensionality. To our knowledge, for behavioral and text data, only one model-agnostic heuristic algorithm (SEDC) for finding counterfactual explanations has been proposed in the literature. However, there may be better algorithms for finding counterfactuals quickly. This study aligns the recently proposed Linear Interpretable Model-agnostic Explainer (LIME) and Shapley Additive Explanations (SHAP) with the notion of counterfactual explanations, and empirically benchmarks their effectiveness and efficiency against SEDC using a collection of 13 data sets. Results show that LIME-Counterfactual (LIME-C) and SHAP-Counterfactual (SHAP-C) have low and stable computation times, but mostly, they are less efficient than SEDC. However, for certain instances on certain data sets, SEDC's run time is comparably large. With regard to effectiveness, LIME-C and SHAP-C find reasonable, if not always optimal, counterfactual explanations. SHAP-C, however, seems to have difficulties with highly unbalanced data. Because of its good overall performance, LIME-C seems to be a favorable alternative to SEDC, which failed for some nonlinear models to find counterfactuals because of the particular heuristic search algorithm it uses. A main upshot of this paper is that there is a good deal of room for further research. For example, we propose algorithmic adjustments that are direct upshots of the paper's findings.

The Pima Indians of Arizona and Mexico have the highest reported prevalence of diabetes of any population in the world. A small study has been conducted to analyse their medical records to assess if it is possible to predict the onset of diabetes based on diagnostic measures. The dataset is downloaded from Kaggle, where all patients included are females at least 21 years old of Pima Indian heritage. The objective of this project is to build a predictive machine learning model to predict based on diagnostic measurements whether a patient has diabetes. This is a binary (2-class) classification project with supervised learning. Jupyter Notebook (Python) could be used to follow the process below.

--Scientists have used many different classification methods to solve the problem of music classification. But the efficiency of each classification is different. In this paper, we propose two compared methods on the task of music style classification. More specifically, feature extraction for representing timbral texture, rhythmic content and pitch content are proposed. Comparative evaluations on performances of two classifiers were conducted for music classification with different composers' styles.

Cross-Validation is an essential tool in the Data Scientist toolbox. It allows us to utilize our data better. Before I present you my five reasons to use cross-validation, I want to briefly go over what cross-validation is and show some common strategies. The training set is used to train the model, and the validation/test set is used to validate it on data it has never seen before. The classic approach is to do a simple 80%-20% split, sometimes with different values like 70%-30% or 90%-10%.

Ensemble methods based on bootstrapping have improved the predictive accuracy of base learners, but fail to provide a framework in which formal statistical inference can be conducted. Recent theoretical developments suggest taking subsamples without replacement and analyze the resulting estimator in the context of a U-statistic, thus demonstrating asymptotic normality properties. However, we observe that current methods for variance estimation exhibit severe bias when the number of base learners is not large enough, compromising the validity of the resulting confidence intervals or hypothesis tests. This paper shows that similar asymptotics can be achieved by means of V-statistics, corresponding to taking subsamples with replacement. Further, we develop a bias correction algorithm for estimating variance in the limiting distribution, which yields satisfactory results with moderate size of base learners.

We present a novel algorithm that predicts the probability that time derivative of the horizontal component of the ground magnetic field $dB/dt$ exceeds a specified threshold at a given location. This quantity provides important information that is physically relevant to Geomagnetically Induced Currents (GIC), which are electric currents induced by sudden changes of the Earth's magnetic field due to Space Weather events. The model follows a 'gray-box' approach by combining the output of a physics-based model with a machine learning approach. Specifically, we use the University of Michigan's Geospace model, that is operational at the NOAA Space Weather Prediction Center, with a boosted ensemble of classification trees. We discuss in detail the issue of combining a large dataset of ground-based measurements ($\sim$ 20 years) with a limited set of simulation runs ($\sim$ 2 years) by developing a surrogate model for the years in which simulation runs are not available. We also discuss the problem of re-calibrating the output of the decision tree to obtain reliable probabilities. The performance of the model is assessed by typical metrics for probabilistic forecasts: Probability of Detection and False Detection, True Skill Score, Heidke Skill Score, and Receiver Operating Characteristic curve.