Conventional out-of-distribution (OOD) detection schemes based on variational autoencoder or Random Network Distillation (RND) have been observed to assign lower uncertainty to the OOD than the target distribution. In this work, we discover that such conventional novelty detection schemes are also vulnerable to the blurred images. Based on the observation, we construct a novel RND-based OOD detector, SVD-RND, that utilizes blurred images during training. Our detector is simple, efficient at test time, and outperforms baseline OOD detectors in various domains. Further results show that SVD-RND learns better target distribution representation than the baseline RND algorithm. Finally, SVD-RND combined with geometric transform achieves near-perfect detection accuracy on the CelebA dataset.

We address the issue of estimating the topology and dynamics of sparse linear dynamic networks in a hyperparameter-free setting. We propose a method to estimate the network dynamics in a computationally efficient and parameter tuning-free iterative framework known as SPICE (Sparse Iterative Covariance Estimation). The estimated dynamics directly reveal the underlying topology. Our approach does not assume that the network is undirected and is applicable even with varying noise levels across the modules of the network. We also do not assume any explicit prior knowledge on the network dynamics. Numerical experiments with realistic dynamic networks illustrate the usefulness of our method.

If you're anything like my dad, you've worked in IT for decades but have only tangentially touched data science. Now, your new C-something-O wants you to fire up a data analytics team and work with new a set of buzzwords you've only vaguely heard about at conferences. Or perhaps you're a developer at a fast-moving startup and have spent weeks finalizing an algorithm, only to be stymied by issues with deploying the model onto your web application for real time use. For both cases, H2O.ai is definitely a solution worth looking into. H2O.ai positions itself as a software package that streamlines the machine learning process through its open source package H2O and AutoML.

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50% to 80%) is used for training and the rest for validation. In many problems, however, the data is highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesising feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesise data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesising data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, e.g. support vector machine, k-nearest neighbour, deep networks, rule-based classifiers, decision trees, etc. The results demonstrated that: i) a significantly more balanced (and fair) classification results can be achieved; ii) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.

Charge prediction which aims to determine appropriate charges for criminal cases based on textual fact descriptions, is an important technology in the field of AI&Law. Previous works focus on improving prediction accuracy, ignoring the interpretability, which limits the methods' applicability. In this work, we propose a deep neural framework to extract short but charge-decisive text snippets - rationales - from input fact description, as the interpretation of charge prediction. To solve the scarcity problem of rationale annotated corpus, rationales are extracted in a reinforcement style with the only supervision in the form of charge labels. We further propose a dynamic rationale attention mechanism to better utilize the information in extracted rationales and predict the charges. Experimental results show that besides providing charge prediction interpretation, our approach can also capture subtle details to help charge prediction.

This paper proposes a methodology for host-based anomaly detection using a semi-supervised algorithm namely one-class classifier combined with a PCA-based feature extraction technique called Eigentraces on system call trace data. The one-class classification is based on generating a set of artificial data using a reference distribution and combining the target class probability function with artificial class density function to estimate the target class density function through the Bayes formulation. The benchmark dataset, ADFA-LD, is employed for the simulation study. ADFA-LD dataset contains thousands of system call traces collected during various normal and attack processes for the Linux operating system environment. In order to pre-process and to extract features, windowing on the system call trace data followed by the principal component analysis which is named as Eigentraces is implemented. The target class probability function is modeled separately by Radial Basis Function neural network and Random Forest machine learners for performance comparison purposes. The simulation study showed that the proposed intrusion detection system offers high performance for detecting anomalies and normal activities with respect to a set of well-accepted metrics including detection rate, accuracy, and missed and false alarm rates.

Learning performance can show non-monotonic behavior. That is, more data does not necessarily lead to better models, even on average. We propose three algorithms that take a supervised learning model and make it perform more monotone. We prove consistency and monotonicity with high probability, and evaluate the algorithms on scenarios where non-monotone behaviour occurs. Our proposed algorithm $\text{MT}_{\text{HT}}$ makes less than $1\%$ non-monotone decisions on MNIST while staying competitive in terms of error rate compared to several baselines.

Principal component analysis (PCA) is one of the most widely used dimension reduction and multivariate statistical techniques. From a probabilistic perspective, PCA seeks a low-dimensional representation of data in the presence of independent identical Gaussian noise. Probabilistic PCA (PPCA) and its variants have been extensively studied for decades. Most of them assume the underlying noise follows a certain independent identical distribution. However, the noise in the real world is usually complicated and structured. To address this challenge, some non-linear variants of PPCA have been proposed. But those methods are generally difficult to interpret. To this end, we propose a powerful and intuitive PCA method (MN-PCA) through modeling the graphical noise by the matrix normal distribution, which enables us to explore the structure of noise in both the feature space and the sample space. MN-PCA obtains a low-rank representation of data and the structure of noise simultaneously. And it can be explained as approximating data over the generalized Mahalanobis distance. We develop two algorithms to solve this model: one maximizes the regularized likelihood, the other exploits the Wasserstein distance, which is more robust. Extensive experiments on various data demonstrate their effectiveness.

The number of shiny models out there can be overwhelming, which means a lot of times people fallback on a few they trust the most, and use them on all new problems. This can lead to sub-optimal results. Today we're going to learn how to quickly and efficiently narrow down the space of available models to find those that are most likely to perform best on your problem type. We'll also see how we can keep track of our models' performances using Weights and Biases and compare them. Unlike Lord of the Rings, in machine learning there is no one ring (model) to rule them all.

You are in a conference room, presenting your work on a classification problem. You demonstrate all the magic you performed with feature engineering, predictor selection, model selection, hyperparameter tuning, and ensembling. You conclude your presentation with the predicted probabilities and the ROC curve, and a fantastic AUC. You sit down confident in a job well done. And the manager says, "What am I supposed to do with all this probability and ROC stuff? I just want to know if I should do x or y."