Inspired by dynamic programming, we propose Stochastic Virtual Gradient Descent (SVGD) algorithm where the Virtual Gradient is defined by computational graph and automatic differentiation. The method is computationally efficient and has little memory requirements. We also analyze the theoretical convergence properties and implementation of the algorithm. Experimental results on multiple datasets and network models show that SVGD has advantages over other stochastic optimization methods.

Modern longitudinal studies feature data collected at many timepoints, often of the same order of sample size. Such studies are typically affected by dropout and positivity violations. We tackle these problems by generalizing effects of recent incremental interventions (which shift propensity scores rather than set treatment values deterministically) to accommodate multiple outcomes and subject dropout. We give an identifying expression for incremental effects when dropout is conditionally ignorable (without requiring treatment positivity), and derive the nonparametric efficiency bound for estimating such effects. Then we present efficient nonparametric estimators, showing that they converge at fast parametric rates and yield uniform inferential guarantees, even when nuisance functions are estimated flexibly at slower rates. We also study the efficiency of incremental effects relative to more conventional deterministic effects in a novel infinite time horizon setting, where the number of timepoints grows with sample size, and show that incremental effects yield near-exponential gains in this setup. Finally we conclude with simulations and apply our methods in a study of the effect of low-dose aspirin on pregnancy outcomes.

Deep Neural Networks (DNNs) have begun to thrive in the field of automation systems, owing to the recent advancements in standardising various aspects such as architecture, optimization techniques, and regularization. In this paper, we take a step towards a better understanding of Spectral Normalization (SN) and its potential for standardizing regularization of a wider range of Deep Learning models, following an empirical approach. We conduct several experiments to study their training dynamics, in comparison with the ubiquitous Batch Normalization (BN) and show that SN increases the gradient sparsity and controls the gradient variance. Furthermore, we show that SN suffers from a phenomenon, we call the mean-drift effect, which mitigates its performance. We, then, propose a weight reparameterization called as the Mean Spectral Normalization (MSN) to resolve the mean drift, thereby significantly improving the network's performance. Our model performs ~16% faster as compared to BN in practice, and has fewer trainable parameters. We also show the performance of our MSN for small, medium, and large CNNs - 3-layer CNN, VGG7 and DenseNet-BC, respectively - and unsupervised image generation tasks using Generative Adversarial Networks (GANs) to evaluate its applicability for a broad range of embedded automation tasks.

Sparse Principal Component Analysis (sPCA) is a popular matrix factorization approach based on Principal Component Analysis (PCA) that combines variance maximization and sparsity with the ultimate goal of improving data interpretation. When moving from PCA to sPCA, there are a number of implications that the practitioner needs to be aware of. A relevant one is that scores and loadings in sPCA may not be orthogonal. For this reason, the traditional way of computing scores, residuals and variance explained that is used in the classical PCA cannot directly be applied to sPCA models. This also affects how sPCA components should be visualized. In this paper we illustrate this problem both theoretically and numerically using simulations for several state-of-the-art sPCA algorithms, and provide proper computation of the different elements mentioned. We show that sPCA approaches present disparate and limited performance when modeling noise-free, sparse data. In a follow-up paper, we discuss the theoretical properties that lead to this problem.

Deep Learning Accelerators are prone to faults which manifest in the form of errors in Neural Networks. Fault Tolerance in Neural Networks is crucial in real-time safety critical applications requiring computation for long durations. Neural Networks with high regularisation exhibit superior fault tolerance, however, at the cost of classification accuracy. In the view of difference in functionality, a Neural Network is modelled as two separate networks, i.e, the Feature Extractor with unsupervised learning objective and the Classifier with a supervised learning objective. Traditional approaches of training the entire network using a single supervised learning objective is insufficient to achieve the objectives of the individual components optimally. In this work, a novel multi-criteria objective function, combining unsupervised training of the Feature Extractor followed by supervised tuning with Classifier Network is proposed. The unsupervised training solves two games simultaneously in the presence of adversary neural networks with conflicting objectives to the Feature Extractor. The first game minimises the loss in reconstructing the input image for indistinguishability given the features from the Extractor, in the presence of a generative decoder. The second game solves a minimax constraint optimisation for distributional smoothening of feature space to match a prior distribution, in the presence of a Discriminator network. The resultant strongly regularised Feature Extractor is combined with the Classifier Network for supervised fine-tuning. The proposed Adversarial Fault Tolerant Neural Network Training is scalable to large networks and is independent of the architecture. The evaluation on benchmarking datasets: FashionMNIST and CIFAR10, indicates that the resultant networks have high accuracy with superior tolerance to stuck at "0" faults compared to widely used regularisers.

Translation-based embedding models have gained significant attention in link prediction tasks for knowledge graphs. TransE is the primary model among translation-based embeddings and is well-known for its low complexity and high efficiency. Therefore, most of the earlier works have modified the score function of the TransE approach in order to improve the performance of link prediction tasks. Nevertheless, proven theoretically and experimentally, the performance of TransE strongly depends on the loss function. Margin Ranking Loss (MRL) has been one of the earlier loss functions which is widely used for training TransE. However, the scores of positive triples are not necessarily enforced to be sufficiently small to fulfill the translation from head to tail by using relation vector (original assumption of TransE). To tackle this problem, several loss functions have been proposed recently by adding upper bounds and lower bounds to the scores of positive and negative samples. Although highly effective, previously developed models suffer from an expansion in search space for a selection of the hyperparameters (in particular the upper and lower bounds of scores) on which the performance of the translation-based models is highly dependent. In this paper, we propose a new loss function dubbed Adaptive Margin Loss (AML) for training translation-based embedding models. The formulation of the proposed loss function enables an adaptive and automated adjustment of the margin during the learning process. Therefore, instead of obtaining two values (upper bound and lower bound), only the center of a margin needs to be determined. During learning, the margin is expanded automatically until it converges. In our experiments on a set of standard benchmark datasets including Freebase and WordNet, the effectiveness of AML is confirmed for training TransE on link prediction tasks.

Artificial Intelligence models are becoming increasingly more powerful and accurate, supporting or even replacing humans' decision making. But with increased power and accuracy also comes higher complexity, making it hard for users to understand how the model works and what the reasons behind its predictions are. Humans must explain and justify their decisions, and so do the AI models supporting them in this process, making semantic interpretability an emerging field of study. In this work, we look at interpretability from a broader point of view, going beyond the machine learning scope and covering different AI fields such as distributional semantics and fuzzy logic, among others. We examine and classify the models according to their nature and also based on how they introduce interpretability features, analyzing how each approach affects the final users and pointing to gaps that still need to be addressed to provide more human-centered interpretability solutions.

We propose, therefore, procedural content 1984) in the 1980s, certain genres of digital games have generation through quality-diversity (PCG-QD) as a subset relied on algorithmic processes to generate content such as of search-based procedural content generation [4] which is levels, weapons, personalities, quests, etc. Throughout its long perfectly suited for generating content autonomously (as it can history, procedural content generation (PCG) has aimed to produce a large set of diverse and high-quality artifacts in one provide content that is playable, of a high quality, and yet run, even in search spaces which are not well-defined) or with different from other content that came before or after. On the a human designer (as it can explain and express its artifacts' one hand, most game content need to satisfy certain minimal desirable properties). This paper presents the components of criteria on playability (such as the exit in a dungeon being quality-diversity algorithms, identifies the strengths of PCG-reachable by the player) while they also need to be entertaining QD over popular alternatives, surveys recent work in this vein and challenging (which are softer and often subjective quality and attempts to map out the road ahead.

At the core of our uniquely human cognitive abilities is the capacity to see things from different perspectives, or to place them in a new context. We propose that this was made possible by two cognitive transitions. First, the large brain of Homo erectus facilitated the onset of recursive recall: the ability to string thoughts together into a stream of potentially abstract or imaginative thought. This hypothesis is supported by a set of computational models where an artificial society of agents evolved to generate more diverse and valuable cultural outputs under conditions of recursive recall. We propose that the capacity to see things in context arose much later, following the appearance of anatomically modern humans. This second transition was brought on by the onset of contextual focus: the capacity to shift between a minimally contextual analytic mode of thought, and a highly contextual associative mode of thought, conducive to combining concepts in new ways and ‗breaking out of a rut'. When contextual focus is implemented in an art-generating computer program, the resulting artworks are seen as more creative and appealing. We summarize how both transitions can be modeled using a theory of concepts which highlights the manner in which different contexts can lead to modern humans attributing very different meanings to the interpretation of one concept.

A model of the mechanisms underlying exploratory behaviour, based on empirical research and refined using a computer simulation, is presented. The behaviour of killifish from two lakes, one with killifish predators and one without, was compared in the laboratory. Plotting average activity in a novel environment versus time resulted in an inverted-U-shaped curve for both groups; however, the curve for killifish from the lake without predators was (1) steeper, (2) reached a peak value earlier, (S) reached a higher peak value, and (4) subsumed less area than the curve for killifish from the lake with predators. We hypothesize that the shape of the exploration curve reflects a competition between motivational subsystems that excite and inhibit exploratory behaviour in a way that is tuned to match the affordance probabilities of the animal's environment. A computer implementation of this model produced curves which differed along the same four dimensions as differentiate the two killifish curves. All four differences were reproduced in the model by tuning a single parameter: the time-dependent component of the decay-rate of the exploration-inhibiting subsystem.