Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on multimodal unsupervised learning (as infants) and active learning (as children). With this motivation, we present a learning framework for sound representation and recognition that combines (i) a self-supervised objective based on a general notion of unimodal and cross-modal coincidence, (ii) a clustering objective that reflects our need to impose categorical structure on our experiences, and (iii) a cluster-based active learning procedure that solicits targeted weak supervision to consolidate categories into relevant semantic classes. By training a combined sound embedding/clustering/classification network according to these criteria, we achieve a new state-of-the-art unsupervised audio representation and demonstrate up to a 20-fold reduction in the number of labels required to reach a desired classification performance.

We consider a model for logistic regression where only a subset of features of size $p$ is used for training a linear classifier over $n$ training samples. The classifier is obtained by running gradient-descent (GD) on the logistic-loss. For this model, we investigate the dependence of the generalization error on the overparameterization ratio $\kappa=p/n$. First, building on known deterministic results on convergence properties of the GD, we uncover a phase-transition phenomenon for the case of Gaussian regressors: the generalization error of GD is the same as that of the maximum-likelihood (ML) solution when $\kappa<\kappa_\star$, and that of the max-margin (SVM) solution when $\kappa>\kappa_\star$. Next, using the convex Gaussian min-max theorem (CGMT), we sharply characterize the performance of both the ML and SVM solutions. Combining these results, we obtain curves that explicitly characterize the generalization error of GD for varying values of $\kappa$. The numerical results validate the theoretical predictions and unveil double-descent phenomena that complement similar recent observations in linear regression settings.

This paper is organized as follows: Section 2 briefly introduces some studies related to the formalization of theoretical frameworks in the context of the Data Clustering (DC) problem; Section 3 introduces a general formulation for the DC and HC problems; Section 4 discusses the Coarse-Refinement Dilemma considering the homology group H 0; Section 5 shows that homology groups of degree greater than zero are affected by overrefined and over-coarsed topologies; Section 6 compares our proposed generalization bounds to Carlsson and M emoli [12]'s consistency; finally, conclusions and future directions are provided in Section 8. 2. Related work Data Clustering (DC) faces many challenges in defining and guaranteeing generalization from datasets, as it does not rely on labels and, consequently, it cannot take advantage of computing any evident error measurement such as risk [7]. While studying this issue, Kleinberg [8] considered that a clustering model is an application of a mapping f on top of a distance function d: I I R, given I contains indices of data points in some fixed-size set S, disregarding its ambient space though [25]. From this initial setup, Kleinberg [8] defined three properties to be respected in order to assess clustering algorithms and models: - Scale-invariance: Given a distance and a clustering function, d and f, and a scalar α, the following must hold f (d) f (αd). Thus, the similarity representation over S must be consistent with the units of measurement; - Consistency: Let Γ be a partition of S and d,d null two distance functions. Function d null is referred to as a Γ transformation of d if: (i) for all i,j S belonging to the same cluster, d null (i,j) d( i,j); and (ii) for all i,j S belonging to different clusters, d null (i,j) d( i,j). Consistency holds if f (d null) f ( d) whenever d null is a Σ transformation of d.

The ubiquity of smartphone usage in many people's lives make it a rich source of information about a person's mental and cognitive state. In this work we analyze 12 weeks of phone usage data from 113 older adults, 31 with diagnosed cognitive impairment and 82 without. We develop structured models of users' smartphone interactions to reveal differences in phone usage patterns between people with and without cognitive impairment. In particular, we focus on inferring specific types of phone usage sessions that are predictive of cognitive impairment. Our model achieves an AUROC of 0.79 when discriminating between healthy and symptomatic subjects, and its interpretability enables novel insights into which aspects of phone usage strongly relate with cognitive health in our dataset.

Motivation: MiRNAs are a kind of small non - coding RNAs that are not translated into proteins, and aberrant expression of miRNAs is associated with human diseases. Since miRNAs have different roles in diseases, the miRNA - disease associations are categorized into multiple types according to their roles. Predicting miRNA - disease associations and types is critical to understand the underlying patho genesis of human diseases from the molecular level . Results: In this paper, we formulate the problem as a link prediction in knowledge graphs. We use biomedical knowledge bases to build a knowledge graph of entities representing miRNAs and disease and mult i - relations, and we propose a tensor decomposition - based model named TDRC to predict miRNA - disease associations and their types from the knowledge graph. We have experimentally evaluated our method and compared it to several baseline methods. The results d emonstrate that the proposed method h as high - accuracy and high - efficiency performances.

Multimodal language analysis often considers relationships between features based on text and those based on acoustical and visual properties. Text features typically outperform non-text features in sentiment analysis or emotion recognition tasks in part because the text features are derived from advanced language models or word embeddings trained on massive data sources while audio and video features are human-engineered and comparatively underdeveloped. Given that the text, audio, and video are describing the same utterance in different ways, we hypothesize that the multimodal sentiment analysis and emotion recognition can be improved by learning (hidden) correlations between features extracted from the outer product of text and audio (we call this text-based audio) and analogous text-based video . This paper proposes a novel model, the Interaction Canonical Correlation Network (ICCN), to learn such multimodal embeddings. ICCN learns correlations between all three modes via deep canonical correlation analysis (DCCA) and the proposed embeddings are then tested on several benchmark datasets and against other state-of-the-art multimodal embedding algorithms. Empirical results and ablation studies confirm the effectiveness of ICCN in capturing useful information from all three views.

Asynchronous event sequences are the basis of many applications throughout different industries. In this work, we tackle the task of predicting the next event (given a history), and how this prediction changes with the passage of time. Since at some time points (e.g. predictions far into the future) we might not be able to predict anything with confidence, capturing uncertainty in the predictions is crucial. We present two new architectures, WGP-LN and FD-Dir, modelling the evolution of the distribution on the probability simplex with time-dependent logistic normal and Dirichlet distributions. In both cases, the combination of RNNs with either Gaussian process or function decomposition allows to express rich temporal evolution of the distribution parameters, and naturally captures uncertainty. Experiments on class prediction, time prediction and anomaly detection demonstrate the high performances of our models on various datasets compared to other approaches.

In this paper, the extension of the framework of Learning from Constraints (LfC) to a distributed setting where multiple parties, connected over the network, contribute to the learning process is studied. LfC relies on the generic notion of "constraint" to inject knowledge into the learning problem and, due to its generality, it deals with possibly nonconvex constraints, enforced either in a hard or soft way. Motivated by recent progresses in the field of distributed and constrained nonconvex optimization, we apply the (distributed) Asynchronous Method of Multipliers (ASYMM) to LfC. The study shows that such a method allows us to support scenarios where selected constraints (i.e., knowledge), data, and outcomes of the learning process can be locally stored in each computational node without being shared with the rest of the network, opening the road to further investigations into privacy-preserving LfC. Constraints act as a bridge between what is shared over the net and what is private to each node and no central authority is required. We demonstrate the applicability of these ideas in two distributed real-world settings in the context of digit recognition and document classification.

The Statistical Learning Theory (SLT) provides the theoretical background to ensure that a supervised algorithm generalizes the mapping $f: \mathcal{X} \to \mathcal{Y}$ given $f$ is selected from its search space bias $\mathcal{F}$. This formal result depends on the Shattering coefficient function $\mathcal{N}(\mathcal{F},2n)$ to upper bound the empirical risk minimization principle, from which one can estimate the necessary training sample size to ensure the probabilistic learning convergence and, most importantly, the characterization of the capacity of $\mathcal{F}$, including its under and overfitting abilities while addressing specific target problems. In this context, we propose a new approach to estimate the maximal number of hyperplanes required to shatter a given sample, i.e., to separate every pair of points from one another, based on the recent contributions by Har-Peled and Jones in the dataset partitioning scenario, and use such foundation to analytically compute the Shattering coefficient function for both binary and multi-class problems. As main contributions, one can use our approach to study the complexity of the search space bias $\mathcal{F}$, estimate training sample sizes, and parametrize the number of hyperplanes a learning algorithm needs to address some supervised task, what is specially appealing to deep neural networks. Experiments were performed to illustrate the advantages of our approach while studying the search space $\mathcal{F}$ on synthetic and one toy datasets and on two widely-used deep learning benchmarks (MNIST and CIFAR-10). In order to permit reproducibility and the use of our approach, our source code is made available at~\url{https://bitbucket.org/rodrigo_mello/shattering-rcode}.

The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains. Self-supervised learning, a paradigm which exploits the structure of unlabeled data to create learning problems that can be solved with standard supervised approaches, has shown great promise as a pretraining or feature learning approach in fields like computer vision and time series processing. In this work, we present self-supervision strategies that can be used to learn informative representations from multivariate time series. One successful approach relies on predicting whether time windows are sampled from the same temporal context or not. As demonstrated on a clinically relevant task (sleep scoring) and with two electroencephalography datasets, our approach outperforms a purely supervised approach in low data regimes, while capturing important physiological information without any access to labels.