Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity. Indeed, neural networks often have many more parameters than there are data points, yet still provide good generalization performance. Moreover, when we measure generalization as a function of parameters, we see double descent behaviour, where the test error decreases, increases, and then again decreases. We show that many of these properties become understandable when viewed through the lens of effective dimensionality, which measures the dimensionality of the parameter space determined by the data. We relate effective dimensionality to posterior contraction in Bayesian deep learning, model selection, double descent, and functional diversity in loss surfaces, leading to a richer understanding of the interplay between parameters and functions in deep models.

Recent studies have shown that modern deep neural network classifiers are easy to fool, assuming that an adversary is able to slightly modify their inputs. Many papers have proposed adversarial attacks, defenses and methods to measure robustness to such adversarial perturbations. However, most commonly considered adversarial examples are based on $\ell_p$-bounded perturbations in the input space of the neural network, which are unlikely to arise naturally. Recently, especially in computer vision, researchers discovered "natural" or "semantic" perturbations, such as rotations, changes of brightness, or more high-level changes, but these perturbations have not yet been systematically utilized to measure the performance of classifiers. In this paper, we propose several metrics to measure robustness of classifiers to natural adversarial examples, and methods to evaluate them. These metrics, called latent space performance metrics, are based on the ability of generative models to capture probability distributions, and are defined in their latent spaces. On three image classification case studies, we evaluate the proposed metrics for several classifiers, including ones trained in conventional and robust ways. We find that the latent counterparts of adversarial robustness are associated with the accuracy of the classifier rather than its conventional adversarial robustness, but the latter is still reflected on the properties of found latent perturbations. In addition, our novel method of finding latent adversarial perturbations demonstrates that these perturbations are often perceptually small.

Classification is one of the core problems in statistical learning and has been intensively studied in statistical and machine learning literature. Nevertheless, while the theory for binary classification is well developed (see, Devroy, Gyöfri and Lugosi, 1996; Vapnik, 2000; Boucheron, Bousquet and Lugosi, 2005 and references therein for a comprehensive review), its multiclass extensions are much less complete. Consider a general L-class classification with a (high-dimensional) vector of features X X R d and the outcome class label Y {1,..., L}. We can model it as Y (X x) Mult(p 1 (x),..., p L (x)), where p l (x) P (Y l X x), l 1,..., L. A classifier is a measurable function η: X {1,..., L}. The accuracy of a classifier η is defined by a misclassification error R(η) P (Y η(x)). The optimal classifier that minimizes this error is the Bayes classifier η (x) arg max 1 l L p l (x) with R(η) 1 E X max 1 l L p l (x). The probabilities p l (x)'s are, however, unknown and one should derive a classifier η(x) from the available data D: a random sample of n independent observations (X 1, Y 1),..., (X n, Y n) from the joint distribution of (X, Y). The corresponding (conditional) misclassification error of η is R( η) P (Y η(x) D) and the goodness of η w.r.t.

Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring flexibility and adaptability of the algorithm. We develop a context-aware mixture of deep models termed the {\alpha}-\b{eta} network coupled with uncertainty quantification (UQ) based upon maximum entropy to enhance human activity recognition performance. We improve accuracy and F score by 10% by identifying high-level contexts in a data-driven way to guide model development. In order to ensure training stability, we have used a clustering-based pre-training in both public and in-house datasets, demonstrating improved accuracy through unknown context discovery.

Federated learning is proposed as a machine learning setting to enable distributed edge devices, such as mobile phones, to collaboratively learn a shared prediction model while keeping all the training data on device, which can not only take full advantage of data distributed across millions of nodes to train a good model but also protect data privacy. However, learning in scenario above poses new challenges. In fact, data across a massive number of unreliable devices is likely to be non-IID (identically and independently distributed), which may make the performance of models trained by federated learning unstable. In this paper, we introduce a framework designed for large-scale federated learning which consists of approaches to generating dataset and modular evaluation framework. Firstly, we construct a suite of open-source non-IID datasets by providing three respects including covariate shift, prior probability shift, and concept shift, which are grounded in real-world assumptions. In addition, we design several rigorous evaluation metrics including the number of network nodes, the size of datasets, the number of communication rounds and communication resources etc. Finally, we present an open-source benchmark for large-scale federated learning research.

Deep neural networks are nowadays among the most successful and most widely used methods in machine learning, see, e.g., Schmidhuber (2015), Rawat and Wang (2017), and the literature cited therein. In many applications the most successful networks are deep convolutional networks, see, e.g., Krizhevsky, Sutskever and Hinton (2012) and Kim (2014) concerning applications in image classification or language recognition, resp. These networks can be considered as a special case of deep feedforward neural networks, where symmetry constraints are imposed on the weights of the networks. For general deep feedforward neural networks it was recently shown that under suitable compository assumptions on the structure of the regression function these networks are able to achieve dimension reduction in estimation of high-dimensional regression functions (cf., Kohler

Energy-efficient navigation constitutes an important challenge in electric vehicles, due to their limited battery capacity. We employ a Bayesian approach to model energy consumption at road-segments for efficient navigation. In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound. We then extend our online learning framework to multi-agent setting, where multiple vehicles adaptively navigate and learn the parameters of the energy model. We analyze Thompson Sampling and establish rigorous regret bounds on its performance. Finally, we demonstrate the performance of our methods via several real-world experiments on Luxembourg SUMO Traffic dataset.

Current deep reinforcement learning approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. We incorporate a few object-based priors that humans are known to use: "Infants divide perceptual arrays into units that move as connected wholes, that move separately from one another, that tend to maintain their size and shape over motion, and that tend to act upon each other only on contact" [Spelke]. We propose a probabilistic object-based model of environments and use human object priors to develop an efficient self-supervised algorithm for maximum likelihood estimation of the model parameters from observations and for inferring objects directly from the perceptual stream. We then use object features and incorporate object-contact priors to improve the sample efficiency our object-based RL agent.We evaluate our approach on a subset of the Atari benchmarks, and learn up to four orders of magnitude faster than the standard deep Q-learning network, rendering rapid desktop experiments in this domain feasible. To our knowledge, our system is the first to learn any Atari task in fewer environment interactions than humans.

Pattern recognition is the automated recognition of patterns and regularities in data. Pattern recognition is closely related to artificial intelligence and machine learning,[1] together with applications such as data mining and knowledge discovery in databases (KDD), and is often used interchangeably with these terms. However, these are distinguished: machine learning is one approach to pattern recognition, while other approaches include hand-crafted (not learned) rules or heuristics; and pattern recognition is one approach to artificial intelligence, while other approaches include symbolic artificial intelligence.[2] The field of pattern recognition is concerned with the automatic discovery of regularities in data through the use of computer algorithms and with the use of these regularities to take actions such as classifying the data into different categories.[3] This article focuses on machine learning approaches to pattern recognition.

Even though model predictive control (MPC) is currently the main algorithm for insulin control in the artificial pancreas (AP), it usually requires complex online optimizations, which are infeasible for resource-constrained medical devices. MPC also typically relies on state estimation, an error-prone process. In this paper, we introduce a novel approach to AP control that uses Imitation Learning to synthesize neural-network insulin policies from MPC-computed demonstrations. Such policies are computationally efficient and, by instrumenting MPC at training time with full state information, they can directly map measurements into optimal therapy decisions, thus bypassing state estimation. We apply Bayesian inference via Monte Carlo Dropout to learn policies, which allows us to quantify prediction uncertainty and thereby derive safer therapy decisions. We show that our control policies trained under a specific patient model readily generalize (in terms of model parameters and disturbance distributions) to patient cohorts, consistently outperforming traditional MPC with state estimation.