Attention mechanisms in biological perception are thought to select subsets of perceptual information for more sophisticated processing which would be prohibitive to perform on all sensory inputs. In computer vision, however, there has been relatively little exploration of hard attention, where some information is selectively ignored, in spite of the success of soft attention, where information is re-weighted and aggregated, but never filtered out. Here, we introduce a new approach for hard attention and find it achieves very competitive performance on a recently-released visual question answering datasets, equalling and in some cases surpassing similar soft attention architectures while entirely ignoring some features. Even though the hard attention mechanism is thought to be non-differentiable, we found that the feature magnitudes correlate with semantic relevance, and provide a useful signal for our mechanism's attentional selection criterion. Because hard attention selects important features of the input information, it can also be more efficient than analogous soft attention mechanisms. This is especially important for recent approaches that use non-local pairwise operations, whereby computational and memory costs are quadratic in the size of the set of features.

Predictive analytics attempts to predict a future outcome based on historical data, and the most common method is referred to as Supervised Learning.

In our previous post, we discussed what is feature selection and why we need feature selection. In this post, we're going to look at the different methods used in feature selection. There are three main classification of feature selection methods – Filter Methods, Wrapper Methods, and Embedded Methods. We'll look at all of them individually. Filter methods are learning-algorithm-agnostic, which means they can be employed no matter which learning algorithm you're using.

At IBM Research, we are exploring new solutions for a range of health care challenges. One such challenge is emergency room (ER) overcrowding, which can lead to long wait times for treatment. Patients who use the ER for non-emergency situations are more likely to return to the ER multiple times (Poole et al. 2016), further contributing to overcrowding. Identifying those patients who are likely to return to the ER may enable hospitals to intervene to ensure access to necessary care outside the ER and potentially alleviate overcrowding. My team at IBM Research-China took on this challenge.

It's a timeless manufacturing goal: to produce high quality products at a minimum cost. Factory 4.0 is already demonstrating its value by enabling manufacturers to reach this goal more successfully than ever, and one of the core technologies driving this new wave of ultra-automation is Industrial AI and Machine Learning. Data has become a valuable resource, and it's cheaper than ever to capture and store. Through the use of artificial intelligence, specifically Machine Learning, manufacturers can use data to significantly impact their bottom line by greatly improving efficiency, employee safety, and product quality. Maintenance represents a significant part of any manufacturing operation's expenses.

Stochastic gradient descent (SGD), which dates back to the 1950s, is one of the most popular and effective approaches for performing stochastic optimization. Research on SGD resurged recently in machine learning for optimizing convex loss functions as well as training nonconvex deep neural networks. The theory assumes that one can easily compute an unbiased gradient estimator, which is usually the case due to the sample average nature of empirical risk minimization. There exist, however, many scenarios (e.g., graph learning) where an unbiased estimator may be as expensive to compute as the full gradient, because training examples are interconnected. In a recent work, Chen et al. (2018) proposed using a consistent gradient estimator as an economic alternative. Encouraged by empirical success, we show, in a general setting, that consistent estimators result in the same convergence behavior as do unbiased ones. Our analysis covers strongly convex, convex, and nonconvex objectives. This work opens several new research directions, including the development of more efficient SGD updates with consistent estimators and the design of efficient training algorithms for large-scale graphs.

The edge structure of the graph defining an undirected graphical model describes precisely the structure of dependence between the variables in the graph. In many applications, the dependence structure is unknown and it is desirable to learn it from data, often because it is a preliminary step to be able to ascertain causal effects. This problem, known as structure learning, is hard in general, but for Gaussian graphical models it is slightly easier because the structure of the graph is given by the sparsity pattern of the precision matrix of the joint distribution, and because independence coincides with decorrelation. A major difficulty too often ignored in structure learning is the fact that if some variables are not observed, the marginal dependence graph over the observed variables will possibly be significantly more complex and no longer reflect the direct dependencies that are potentially associated with causal effects. In this work, we consider a family of latent variable Gaussian graphical models in which the graph of the joint distribution between observed and unobserved variables is sparse, and the unobserved variables are conditionally independent given the others. Prior work was able to recover the connectivity between observed variables, but could only identify the subspace spanned by unobserved variables, whereas we propose a convex optimization formulation based on structured matrix sparsity to estimate the complete connectivity of the complete graph including unobserved variables, given the knowledge of the number of missing variables, and a priori knowledge of their level of connectivity. Our formulation is supported by a theoretical result of identifiability of the latent dependence structure for sparse graphs in the infinite data limit. We propose an algorithm leveraging recent active set methods, which performs well in the experiments on synthetic data.

Abstract--Modern datasets and models are notoriously difficult to explore and analyze due to their inherent high dimensionality and massive numbers of samples. Existing visualization methods which employ dimensionality reduction to two or three dimensions are often inefficient and/or ineffective for these datasets. This paper introduces t-SNE-CUDA, a GPU-accelerated implementation of t-distributed Symmetric Neighbour Embedding (t-SNE) for visualizing datasets and models. These speedups enable, for the first time, visualization of the neural network activations on the entire ImageNet dataset - a feat that was previously computationally intractable. We also demonstrate visualization performance in the NLP domain by visualizing the GloV e embedding vectors. From these visualizations, we can draw interesting conclusions about using the L2 metric in these embedding spaces. The recent emergence of large-scale, high-dimensional datasets has been a major factor contributing to advances in the areas of Machine Learning and Artificial Intelligence. While researchers have developed numerous methods for visualizing medium-sized data-sets, such visualizations are often inefficient or ineffective for high-dimensional or large-scale data.

Industry is evolving towards Industry 4.0, which holds the promise of increased flexibility in manufacturing, better quality and improved productivity. A core actor of this growth is using sensors, which must capture data that can used in unforeseen ways to achieve a performance not achievable without them. However, the complexity of this improved setting is much greater than what is currently used in practice. Hence, it is imperative that the management cannot only be performed by human labor force, but part of that will be done by automated algorithms instead. A natural way to represent the data generated by this large amount of sensors, which are not acting measuring independent variables, and the interaction of the different devices is by using a graph data model. Then, machine learning could be used to aid the Industry 4.0 system to, for example, perform predictive maintenance. However, machine learning directly on graphs, needs feature engineering and has scalability issues. In this paper we discuss methods to convert (embed) the graph in a vector space, such that it becomes feasible to use traditional machine learning methods for Industry 4.0 settings.

An econometric or statistical model may undergo a marginal gain when a new variable is admitted, and a marginal loss if an existing variable is removed. The value of a variable to the model is quantified by its expected marginal gain and marginal loss. Assuming the equality of opportunity, we derive a few formulas which evaluate the overall performance in potential modeling scenarios. However, the value is not symmetric to marginal gain and marginal loss; thus, we introduce an unbiased solution. Simulation studies show that our new approaches significantly outperform a few practice-used variable selection methods.