Have you ever wondered if it's possible to learn all there is to know about machine learning and deep learning from a book? Machine Learning--A Journey to Deep Learning, with Exercises and Answers is designed to give the self-taught student a solid foundation in machine learning with step-by-step solutions to the formative exercises and many concrete examples. By going through this text, readers should become able to apply and understand machine learning algorithms as well as create new ones. The statistical approach leads to the definition of regularization out of the example of regression. Building on regression, we develop the theory of perceptrons and logistic regression.

We consider the symmetric binary perceptron model, a simple model of neural networks that has gathered significant attention in the statistical physics, information theory and probability theory communities, with recent connections made to the performance of learning algorithms in Baldassi et al. '15. We establish that the partition function of this model, normalized by its expected value, converges to a lognormal distribution. As a consequence, this allows us to establish several conjectures for this model: (i) it proves the contiguity conjecture of Aubin et al. '19 between the planted and unplanted models in the satisfiable regime; (ii) it establishes the sharp threshold conjecture; (iii) it proves the frozen 1-RSB conjecture in the symmetric case, conjectured first by Krauth-M\'ezard '89 in the asymmetric case. In a recent concurrent work of Perkins-Xu [PX21], the last two conjectures were also established by proving that the partition function concentrates on an exponential scale. This left open the contiguity conjecture and the lognormal limit characterization, which are established here. In particular, our proof technique relies on a dense counter-part of the small graph conditioning method, which was developed for sparse models in the celebrated work of Robinson and Wormald.

This paper deals with the identification of machines in a smart city environment. The concept of machine biometrics is proposed in this work for the first time, as a way to authenticate machine identities interacting with humans in everyday life. This definition is imposed in modern years where autonomous vehicles, social robots, etc. are considered active members of contemporary societies. In this context, the case of car identification from the engine behavioral biometrics is examined. For this purpose, 22 sound features were extracted and their discrimination capabilities were tested in combination with 9 different machine learning classifiers, towards identifying 5 car manufacturers. The experimental results revealed the ability of the proposed biometrics to identify cars with high accuracy up to 98% for the case of the Multilayer Perceptron (MLP) neural network model.

Determining the dynamics of the expectation values for operators acting on a quantum many-body (QMB) system is a challenging task. Matrix product states (MPS) have traditionally been the "go-to" models for these systems because calculating expectation values in this representation can be done with relative simplicity and high accuracy. However, such calculations can become computationally costly when extended to long times. Here, we present a solution for efficiently extending the computation of expectation values to long time intervals. We utilize a multi-layer perceptron (MLP) model as a tool for regression on MPS expectation values calculated within the regime of short time intervals. With this model, the computational cost of generating long-time dynamics is significantly reduced, while maintaining a high accuracy. These results are demonstrated with operators relevant to quantum spin models in one spatial dimension.

Embedding methods for mixed-curvature spaces are powerful techniques for low-distortion and low-dimensional representation of complex data structures. Nevertheless, little is known regarding downstream learning and optimization in the embedding space. Here, we address for the first time the problem of linear classification in a product space form -- a mix of Euclidean, spherical, and hyperbolic spaces with different dimensions. First, we revisit the definition of a linear classifier on a Riemannian manifold by using geodesics and Riemannian metrics which generalize the notions of straight lines and inner products in vector spaces, respectively. Second, we prove that linear classifiers in $d$-dimensional constant curvature spaces can shatter exactly $d+1$ points: Hence, Euclidean, hyperbolic and spherical classifiers have the same expressive power. Third, we formalize linear classifiers in product space forms, describe a novel perceptron classification algorithm, and establish rigorous convergence results. We support our theoretical findings with simulation results on several datasets, including synthetic data, MNIST and Omniglot. Our results reveal that learning methods applied to small-dimensional embeddings in product space forms significantly outperform their algorithmic counterparts in Euclidean spaces.

Classification algorithms have recently found applications in computational physics for the selection of numerical methods or models adapted to the environment and the state of the physical system. For such classification tasks, labeled training data come from numerical simulations and generally correspond to physical fields discretized on a mesh. Three challenging difficulties arise: the lack of training data, their high dimensionality, and the non-applicability of common data augmentation techniques to physics data. This article introduces two algorithms to address these issues, one for dimensionality reduction via feature selection, and one for data augmentation. These algorithms are combined with a wide variety of classifiers for their evaluation. When combined with a stacking ensemble made of six multilayer perceptrons and a ridge logistic regression, they enable reaching an accuracy of 90% on our classification problem for nonlinear structural mechanics.

Transfer learning seeks to improve the generalization performance of a target task by exploiting the knowledge learned from a related source task. Central questions include deciding what information one should transfer and when transfer can be beneficial. The latter question is related to the so-called negative transfer phenomenon, where the transferred source information actually reduces the generalization performance of the target task. This happens when the two tasks are sufficiently dissimilar. In this paper, we present a theoretical analysis of transfer learning by studying a pair of related perceptron learning tasks. Despite the simplicity of our model, it reproduces several key phenomena observed in practice. Specifically, our asymptotic analysis reveals a phase transition from negative transfer to positive transfer as the similarity of the two tasks moves past a well-defined threshold. Transfer learning [1]-[5] is a promising approach to improving the performance of machine learning tasks. It does so by exploiting the knowledge gained from a previously-learned model, referred to as the source task, to improve the generalization performance of a related learning problem, referred to as the target task.

Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-trained feature extractors for few-shot image classification. We show experimentally that a library of pre-trained feature extractors combined with a simple feed-forward network learned with an L2-regularizer can be an excellent option for solving cross-domain few-shot image classification. Our experimental results suggest that this simpler sample-efficient approach far outperforms several well-established meta-learning algorithms on a variety of few-shot tasks.

Solar flares are caused by magnetic eruptions in active regions (ARs) on the surface of the sun. These events can have significant impacts on human activity, many of which can be mitigated with enough advance warning from good forecasts. To date, machine learning-based flare-prediction methods have employed physics-based attributes of the AR images as features; more recently, there has been some work that uses features deduced automatically by deep learning methods (such as convolutional neural networks). We describe a suite of novel shape-based features extracted from magnetogram images of the Sun using the tools of computational topology and computational geometry. We evaluate these features in the context of a multi-layer perceptron (MLP) neural network and compare their performance against the traditional physics-based attributes. We show that these abstract shape-based features outperform the features chosen by the human experts, and that a combination of the two feature sets improves the forecasting capability even further.

In this paper we investigate the relationships between a multipreferential semantics for defeasible reasoning in knowledge representation and a deep neural network model. Weighted knowledge bases for description logics are considered under a "concept-wise" multipreference semantics. The semantics is further extended to fuzzy interpretations and exploited to provide a preferential interpretation of Multilayer Perceptrons.