These methods generally return either a weighting or subset of input features as an explanation of the classification of an instance. An alternative literature argues instead that counterfactual instances provide a more useable characterisation of a black box classifier's decisions. We present EMAP, a neural network based approach which returns as Explanation the Minimal Adversarial Perturbation to an instance required to cause the underlying black box model to missclassify. We show that this approach combines the two paradigms, recovering the output of feature-weighting methods in continuous feature spaces, whilst also indicating the direction in which the nearest counterfactuals can be found. Our method also provides an implicit confidence estimate in its own explanations, adding a clarity to model diagnostics other methods lack. Additionally, EMAP improves upon the speed of sampling-based methods such as LIME by an order of magnitude, allowing for model explanations in time-critical applications, or at the dataset level, where sampling-based methods are infeasible. We extend our approach to categorical features using a partitioned Gumbel layer, and demonstrate its efficacy on several standard datasets. Introduction Recent interest in explaining the output of complex machine learning models has been characterized by a wide range of approaches (Lipton 2016; Montavon, Samek, and M uller 2018). Many of these approaches are model specific; for example attempts to explain neural networks that rely on interpreting the flow of gradient information through the model (Shrikumar, Greenside, and Kundaje 2017; Olah, Mordv-intsev, and Schubert 2017; Karpathy, Johnson, and Fei-Fei 2015), or decision trees, which might be considered directly interpretable (Molnar 2019).

Large-scale non-convex sparsity-constrained problems have recently gained extensive attention. Most existing deterministic optimization methods (e.g., GraSP) are not suitable for large-scale and high-dimensional problems, and thus stochastic optimization methods with hard thresholding (e.g., SVRGHT) become more attractive. Inspired by GraSP, this paper proposes a new general relaxed gradient support pursuit (RGraSP) framework, in which the sub-algorithm only requires to satisfy a slack descent condition. We also design two specific semi-stochastic gradient hard thresholding algorithms. In particular, our algorithms have much less hard thresholding operations than SVRGHT, and their average per-iteration cost is much lower (i.e., O(d) vs. O(d log(d)) for SVRGHT), which leads to faster convergence. Our experimental results on both synthetic and real-world datasets show that our algorithms are superior to the state-of-the-art gradient hard thresholding methods.

Neural Ordinary Differential Equations (N-ODEs) are a powerful building block for learning systems, which extend residual networks to a continuous-time dynamical system. We propose a Bayesian version of N-ODEs that enables well-calibrated quantification of prediction uncertainty, while maintaining the expressive power of their deterministic counterpart. We assign Bayesian Neural Nets (BNNs) to both the drift and the diffusion terms of a Stochastic Differential Equation (SDE) that models the flow of the activation map in time. We infer the posterior on the BNN weights using a straightforward adaptation of Stochastic Gradient Langevin Dynamics (SGLD). We illustrate significantly improved stability on two synthetic time series prediction tasks and report better model fit on UCI regression benchmarks with our method when compared to its non-Bayesian counterpart.

Stochastic variational inference (SVI) plays a key role in Bayesian deep learning. Recently various divergences have been proposed to design the surrogate loss for variational inference. We present a simple upper bound of the evidence as the surrogate loss. This evidence upper bound (EUBO) equals to the log marginal likelihood plus the KL-divergence between the posterior and the proposal. We show that the proposed EUBO is tighter than previous upper bounds introduced by $\chi$-divergence or $\alpha$-divergence. To facilitate scalable inference, we present the numerical approximation of the gradient of the EUBO and apply the SGD algorithm to optimize the variational parameters iteratively. Simulation study with Bayesian logistic regression shows that the upper and lower bounds well sandwich the evidence and the proposed upper bound is favorably tight. For Bayesian neural network, the proposed EUBO-VI algorithm outperforms state-of-the-art results for various examples.

The problem of hyperparameter optimization exists widely in the real life and many common tasks can be transformed into it, such as neural architecture search and feature subset selection. Without considering various constraints, the existing hyperparameter tuning techniques can solve these problems effectively by traversing as many hyperparameter configurations as possible. However, because of the limited resources and budget, it is not feasible to evaluate so many kinds of configurations, which requires us to design effective algorithms to find a best possible hyperparameter configuration with a finite number of configuration evaluations. In this paper, we simulate human thinking processes and combine the merit of the existing techniques, and thus propose a new algorithm called ExperienceThinking, trying to solve this constrained hyperparameter optimization problem. In addition, we analyze the performances of 3 classical hyperparameter optimization algorithms with a finite number of configuration evaluations, and compare with that of ExperienceThinking. The experimental results show that our proposed algorithm provides superior results and has better performance.

We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of several active-learning and baseline methods, which successfully demonstrate a significant improvement on the benchmark CIFAR-10, CIFAR-100, and SVHN datasets (as much as 1.5% in absolute accuracy). We also provide an empirical analysis of the cost trade-off between incrementally gathering more labeled versus unlabeled data. This analysis can be used to measure the relative value of labeled/unlabeled data at different points of the learning curve, where we find that although the incremental value of labeled data can be as much as 20x that of unlabeled, it quickly diminishes to less than 3x once more than 2,000 labeled example are observed. Code can be found at https://github.com/google-research/mma.

Learning to automatically perceive smell is becoming increasingly important with applications in monitoring the quality of food and drinks for healthy living. In todays age of proliferation of internet of things devices, the deployment of electronic nose otherwise known as smell sensors is on the increase for a variety of olfaction applications with the aid of machine learning models. These models are trained to classify food and drink quality into several categories depending on the granularity of interest. However, models trained to smell in one domain rarely perform adequately when used in another domain. In this work, we consider a problem where only few samples are available in the target domain and we are faced with the task of leveraging knowledge from another domain with relatively abundant data to make reliable inference in the target domain. We propose a weakly supervised domain adaptation framework where we demonstrate that by building multiple models in a mixture of supervised and unsupervised framework, we can generalise effectively from one domain to another. We evaluate our approach on several datasets of beef cuts and quality collected across different conditions and environments. We empirically show via several experiments that our approach perform competitively compared to a variety of baselines.

Model selection is the process of selecting one final machine learning model from among a collection of candidate machine learning models for a training dataset. Model selection is a process that can be applied both across different types of models (e.g.

There's more and more research done on detecting all types of cancers in early stages and thus increasing probability of survival. Since I've been passionate about machine learning for a while, I decided to bring my own contribution to this research and learn to train my own neural network detection model. The twist was to build it using Tensorflow with JavaScript, not with Python. We're also using React to manage the state and display the data we get back from the model. For this tutorial, I chose to work with a breast cancer dataset.

Time series data are everywhere. This deliberately broad and multipurpose book can serve as either an introduction for the novice or a reference for someone looking to broaden a time series base. Unlike other texts specialized in time series analysis, this book includes many data munging and data sourcing tasks that are crucial to time series analysis. This book also takes a multidisciplinary approach in applying both statistical and machine learning methods to time series data. Finally, this book is multilingual and multi-topical in applying both R and Python to time series data across a wide variety of disciplines, from physics simulations to digital marking, and from blood glucose monitoring to open government data mining.