Explore the vast range of titles available.

The past decade has evinced a boom of computer-based approaches to aid movement assessment in early infancy. Increasing interests have been dedicated to develop AI driven approaches to complement the classic Prechtl general movements assessment (GMA). This study proposes a novel machine learning algorithm to detect an age-specific movement pattern, the fidgety movements (FMs), in a prospectively collected sample of typically developing infants. Participants were recorded using a passive, single camera RGB video stream. The dataset of 2800 five-second snippets was annotated by two well-trained and experienced GMA assessors, with excellent inter- and intra-rater reliabilities. Using OpenPose, the infant full pose was recovered from the video stream in the form of a 25-points skeleton. This skeleton was used as input vector for a shallow multilayer neural network (SMNN). An ablation study was performed to justify the network’s architecture and hyperparameters. We show for the first time that the SMNN is sufficient to discriminate fidgety from non-fidgety movements in a sample of age-specific typical movements with a classification accuracy of 88%. The computer-based solutions will complement original GMA to consistently perform accurate and efficient screening and diagnosis that may become universally accessible in daily clinical practice in the future.

There is an urgent need to assess neurodevelopment in Zika virus (ZIKV)-exposed infants. To perform general movement assessment (GMA) at 9 to 20 weeks' postterm age and to evaluate whether the findings are associated with neurodevelopmental outcomes at age 12 months in infants prenatally exposed to acute maternal illness with rash in Brazil during the ZIKV outbreak and in age-matched controls. In this cohort study, infants prenatally exposed to acute maternal illness with rash were recruited at medical institutions in Rio de Janeiro and Belo Horizonte, Brazil, from February 1, 2016, to April 30, 2017, while infants without any exposure to maternal illness originated from the Graz University Audiovisual Research Database for the Interdisciplinary Analysis of Neurodevelopment. Participants were 444 infants, including 76 infants without congenital microcephaly, 35 infants with microcephaly, and 333 neurotypical children matched for sex, gestational age at birth, and age at GMA. General movement assessment performed at 9 to 20 weeks' postterm age, with negative predictive value, positive predictive value, sensitivity, and specificity generated, as well as clinical, neurologic, and developmental status (Bayley Scales of Infant and Toddler Development, Third Edition [Bayley-III] scores) at age 12 months. Motor Optimality Scores were generated based on the overall quality of the motor repertoire. Adverse outcomes were defined as a Bayley-III score less than 2 SD in at least 1 domain, a score less than 1 SD in at least 2 domains, and/or atypical neurologic findings. A total of 444 infants were enrolled, including 111 children prenatally exposed to a maternal illness with rash and 333 children without any prenatal exposure to maternal illness (57.7% male and mean [SD] age, 14 [2] weeks for both groups); 82.1% (46 of 56) of ZIKV-exposed infants without congenital microcephaly were healthy at age 12 months. Forty-four of 46 infants were correctly identified by GMA at 3 months, with a negative predictive value of 94% (95% CI, 85%-97%). Seven of 10 ZIKV-exposed children without microcephaly with adverse neurodevelopmental outcomes were identified by GMA. The GMA positive predictive value was 78% (95% CI, 46%-94%), sensitivity was 70% (95% CI, 35%-93%), specificity was 96% (95% CI, 85%-99%), and accuracy was 91% (95% CI, 80%-97%). Children with microcephaly had bilateral spastic cerebral palsy; none had normal movements. The Motor Optimality Score differentiated outcomes: the median Motor Optimality Score was 23 (interquartile range [IQR], 21-26) in children with normal development, 12 (IQR, 8-19) in children with adverse outcomes, and 5 (IQR, 5-6) in children with microcephaly, a significant difference (P = .001). This study suggests that although a large proportion of ZIKV-exposed infants without microcephaly develop normally, many do not. The GMA should be incorporated into routine infant assessments to enable early entry into targeted treatment programs.

Optimization-based techniques for federated learning (FL) often come with prohibitive communication cost, as high dimensional model parameters need to be communicated repeatedly between server and clients. In this paper, we follow a Bayesian approach allowing to perform FL with one-shot communication, by solving the global inference problem as a product of local client posteriors. For models with multi-modal likelihoods, such as neural networks, a naive application of this scheme is hampered, since clients will capture different posterior modes, causing a destructive collapse of the posterior on the server side. Consequently, we explore approximate inference in the function-space representation of client posteriors, hence suffering less or not at all from multi-modality. We show that distributed function-space inference is tightly related to learning Bayesian pseudocoresets and develop a tractable Bayesian FL algorithm on this insight. We show that this approach achieves prediction performance competitive to state-of-the-art while showing a striking reduction in communication cost of up to two orders of magnitude. Moreover, due to its Bayesian nature, our method also delivers well-calibrated uncertainty estimates.

Probabilistic circuits (PCs) are a prominent representation of probability distributions with tractable inference. While parameter learning in PCs is rigorously studied, structure learning is often more based on heuristics than on principled objectives. In this paper, we develop Bayesian structure scores for deterministic PCs, i.e., the structure likelihood with parameters marginalized out, which are well known as rigorous objectives for structure learning in probabilistic graphical models. When used within a greedy cutset algorithm, our scores effectively protect against overfitting and yield a fast and almost hyper-parameter-free structure learner, distinguishing it from previous approaches. In experiments, we achieve good trade-offs between training time and model fit in terms of log-likelihood. Moreover, the principled nature of Bayesian scores unlocks PCs for accommodating frameworks such as structural expectation-maximization.

Probabilistic models based on continuous latent spaces, such as variational autoencoders, can be understood as uncountable mixture models where components depend continuously on the latent code. They have proven to be expressive tools for generative and probabilistic modelling, but are at odds with tractable probabilistic inference, that is, computing marginals and conditionals of the represented probability distribution. Meanwhile, tractable probabilistic models such as probabilistic circuits (PCs) can be understood as hierarchical discrete mixture models, and thus are capable of performing exact inference efficiently but often show subpar performance in comparison to continuous latent-space models. In this paper, we investigate a hybrid approach, namely continuous mixtures of tractable models with a small latent dimension. While these models are analytically intractable, they are well amenable to numerical integration schemes based on a finite set of integration points. With a large enough number of integration points the approximation becomes de-facto exact. Moreover, for a finite set of integration points, the integration method effectively compiles the continuous mixture into a standard PC. In experiments, we show that this simple scheme proves remarkably effective, as PCs learnt this way set new state of the art for tractable models on many standard density estimation benchmarks.

Bayesian causal inference (BCI) naturally incorporates epistemic uncertainty about the true causal model into down-stream causal reasoning tasks by posterior averaging over causal models. However, this poses a tremendously hard computational problem due to the intractable number of causal structures to marginalise over. In this work, we decompose the structure learning problem into inferring (i) a causal order and (ii) a parent set for each variable given a causal order. By limiting the number of parents per variable, we can exactly marginalise over the parent sets in polynomial time, which leaves only the causal order to be marginalised. To this end, we propose a novel autoregressive model over causal orders (ARCO) learnable with gradient-based methods. Our method yields state-of-the-art in structure learning on simulated non-linear additive noise benchmarks with scale-free and Erdos-Renyi graph structures, and competitive results on real-world data. Moreover, we illustrate that our method accurately infers interventional distributions, which allows us to estimate posterior average causal effects and many other causal quantities of interest.

Some of the most successful knowledge graph embedding (KGE) models for link prediction -- CP, RESCAL, TuckER, ComplEx -- can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical constraints. This work re-interprets the score functions of these KGEs as circuits -- constrained computational graphs allowing efficient marginalisation. Then, we design two recipes to obtain efficient generative circuit models by either restricting their activations to be non-negative or squaring their outputs. Our interpretation comes with little or no loss of performance for link prediction, while the circuits framework unlocks exact learning by MLE, efficient sampling of new triples, and guarantee that logical constraints are satisfied by design. Furthermore, our models scale more gracefully than the original KGEs on graphs with millions of entities.

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology from a scientific environment with virtually unlimited computing resources into everyday's applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. In particular, we focus on resource-efficient inference based on deep neural networks (DNNs), the predominant machine learning models of the past decade. We give a comprehensive overview of the vast literature that can be mainly split into three non-mutually exclusive categories: (i) quantized neural networks, (ii) network pruning, and (iii) structural efficiency. These techniques can be applied during training or as post-processing, and they are widely used to reduce the computational demands in terms of memory footprint, inference speed, and energy efficiency. We also briefly discuss different concepts of embedded hardware for DNNs and their compatibility with machine learning techniques as well as potential for energy and latency reduction. We substantiate our discussion with experiments on well-known benchmark data sets using compression techniques (quantization, pruning) for a set of resource-constrained embedded systems, such as CPUs, GPUs and FPGAs. The obtained results highlight the difficulty of finding good trade-offs between resource efficiency and prediction quality.

Continuous latent variables (LVs) are a key ingredient of many generative models, as they allow modelling expressive mixtures with an uncountable number of components. In contrast, probabilistic circuits (PCs) are hierarchical discrete mixtures represented as computational graphs composed of input, sum and product units. Unlike continuous LV models, PCs provide tractable inference but are limited to discrete LVs with categorical (i.e. unordered) states. We bridge these model classes by introducing probabilistic integral circuits (PICs), a new language of computational graphs that extends PCs with integral units representing continuous LVs. In the first place, PICs are symbolic computational graphs and are fully tractable in simple cases where analytical integration is possible. In practice, we parameterise PICs with light-weight neural nets delivering an intractable hierarchical continuous mixture that can be approximated arbitrarily well with large PCs using numerical quadrature. On several distribution estimation benchmarks, we show that such PIC-approximating PCs systematically outperform PCs commonly learned via expectation-maximization or SGD.

This paper establishes a rigorous connection between circuit representations and tensor factorizations, two seemingly distinct yet fundamentally related areas. By connecting these fields, we highlight a series of opportunities that can benefit both communities. Our work generalizes popular tensor factorizations within the circuit language, and unifies various circuit learning algorithms under a single, generalized hierarchical factorization framework. Specifically, we introduce a modular \"Lego block\" approach to build tensorized circuit architectures. This, in turn, allows us to systematically construct and explore various circuit and tensor factorization models while maintaining tractability. This connection not only clarifies similarities and differences in existing models, but also enables the development of a comprehensive pipeline for building and optimizing new circuit/tensor factorization architectures. We show the effectiveness of our framework through extensive empirical evaluations, and highlight new research opportunities for tensor factorizations in probabilistic modeling.