Organ segmentation is an important pre-processing step in many computer assisted intervention and computer assisted diagnosis methods. In recent years, CNNs have dominated the state of the art in this task. Organ segmentation scenarios present a challenging environment for these methods due to high variability in shape, similarity with background, etc. This leads to the generation of false negative and false positive regions in the output segmentation. In this context, the uncertainty analysis of the model can provide us with useful information about potentially misclassified elements. In this work we propose a method based on uncertainty analysis and graph convolutional networks as a post-processing step for segmentation. For this, we employ the uncertainty levels of the CNN to formulate a semi-supervised graph learning problem that is solved by training a GCN on the low uncertainty elements. Finally, we evaluate the full graph on the trained GCN to get the refined segmentation. We compare our framework with CRF on a graph-like data representation as refinement strategy.

Centuries of development in natural sciences and mathematical modeling provide valuable domain expert knowledge that has yet to be explored for the development of machine learning models. When modeling complex physical systems, both domain knowledge and data contribute important information about the system. In this paper, we present a data-driven model that takes advantage of partial domain knowledge in order to improve generalization and interpretability. The presented model, which we call EVGP (Explicit Variational Gaussian Process), uses an explicit linear prior to incorporate partial domain knowledge while using data to fill in the gaps in knowledge. Variational inference was used to obtain a sparse approximation that scales well to large datasets. The advantages include: 1) using partial domain knowledge to improve inductive bias (assumptions of the model), 2) scalability to large datasets, 3) improved interpretability. We show how the EVGP model can be used to learn system dynamics using basic Newtonian mechanics as prior knowledge. We demonstrate that using simple priors from partially defined physics models considerably improves performance when compared to fully data-driven models.

A normalizing flow models a complex probability density as an invertible transformation of a simple density. The invertibility means that we can evaluate densities and generate samples from a flow. In practice, autoregressive flow-based models are slow to invert, making either density estimation or sample generation slow. Flows based on coupling transforms are fast for both tasks, but have previously performed less well at density estimation than autoregressive flows. We stack a new coupling transform, based on monotonic cubic splines, with LU-decomposed linear layers. The resulting cubic-spline flow retains an exact one-pass inverse, can be used to generate high-quality images, and closes the gap with autoregressive flows on a suite of density-estimation tasks.

Optimization of Binarized Neural Networks (BNNs) currently relies on real-valued latent weights to accumulate small update steps. In this paper, we argue that these latent weights cannot be treated analogously to weights in real-valued networks. Instead their main role is to provide inertia during training. We interpret current methods in terms of inertia and provide novel insights into the optimization of BNNs. We subsequently introduce the first optimizer specifically designed for BNNs, Binary Optimizer (Bop), and demonstrate its performance on CIFAR-10 and ImageNet. Together, the redefinition of latent weights as inertia and the introduction of Bop enable a better understanding of BNN optimization and open up the way for further improvements in training methodologies for BNNs.

The increasing access to brain signal data using electroencephalography creates new opportunities to study electrophysiological brain activity and perform ambulatory diagnoses of neuronal diseases. This work proposes a pairwise distance learning approach for Schizophrenia classification relying on the spectral properties of the signal. Given the limited number of observations (i.e. the case and/or control individuals) in clinical trials, we propose a Siamese neural network architecture to learn a discriminative feature space from pairwise combinations of observations per channel. In this way, the multivariate order of the signal is used as a form of data augmentation, further supporting the network generalization ability. Convolutional layers with parameters learned under a cosine contrastive loss are proposed to adequately explore spectral images derived from the brain signal. Results on a case-control population show that the features extracted using the proposed neural network lead to an improved Schizophrenia diagnosis (+10pp in accuracy and sensitivity) against spectral features, thus suggesting the existence of non-trivial, discriminative electrophysiological brain patterns.

Due to high complexity of many modern machine learning models such as deep convolutional networks, understanding the cause of model's prediction is critical. Many explainers have been designed to give us more insights on the decision of complex classifiers. However, there is no common ground on evaluating the quality of different classification methods. Motivated by the needs for comprehensive evaluation, we introduce the c-Eval metric and the corresponding framework to quantify the explainer's quality on feature-based explainers of machine learning image classifiers. Given a prediction and the corresponding explanation on that prediction, c-Eval is the minimum-power perturbation that successfully alters the prediction while keeping the explanation's features unchanged. We also provide theoretical analysis linking the proposed parameter with the portion of predicted object covered by the explanation. Using a heuristic approach, we introduce the c-Eval plot, which not only displays a strong connection between c-Eval and explainers' quality, but also serves as a low-complexity approach of assessing explainers. We finally conduct extensive experiments of explainers on three different datasets in order to support the adoption of c-Eval in evaluating explainers' performance.

In conventional prediction tasks, a machine learning algorithm outputs a single best model that globally optimizes its objective function, which typically is accuracy. Therefore, users cannot access the other models explicitly. In contrast to this, multiple model enumeration attracts increasing interests in non-standard machine learning applications where other criteria, e.g., interpretability or fairness, than accuracy are main concern and a user may want to access more than one non-optimal, but suitable models. In this paper, we propose a K-best model enumeration algorithm for Support Vector Machines (SVM) that given a dataset S and an integer K>0, enumerates the K-best models on S with distinct support vectors in the descending order of the objective function values in the dual SVM problem. Based on analysis of the lattice structure of support vectors, our algorithm efficiently finds the next best model with small latency. This is useful in supporting users's interactive examination of their requirements on enumerated models. By experiments on real datasets, we evaluated the efficiency and usefulness of our algorithm.

Covariance pooling is a feature pooling method with good classification accuracy. Because covariance features consist of second-order statistics, the scale of the feature elements are varied. Therefore, normalizing covariance features using a matrix square root affects the performance improvement. When pooling methods are applied to local features extracted from CNN models, the accuracy increases when the pooling function is back-propagatable and the feature-extraction model is learned in an end-to-end manner. Recently, the iterative polynomial approximation method for the matrix square root of a covariance feature was proposed, and resulted in a faster and more stable training than the methods based on singular-value decomposition. In this paper, we propose an extension of compact bilinear pooling, which is a compact approximation of the standard covariance feature, to the polynomials of the covariance feature. Subsequently, we apply the proposed approximation to the polynomial corresponding to the matrix square root to obtain a compact approximation for the square root of the covariance feature. Our method approximates a higher-dimensional polynomial of a covariance by the weighted sum of the approximate features corresponding to a pair of local features based on the similarity of the local features. We apply our method for standard fine-grained image recognition datasets and demonstrate that the proposed method shows comparable accuracy with fewer dimensions than the original feature.

We present a coupled Variational Auto-Encoder (VAE) method that improves the accuracy and robustness of the probabilistic inferences on represented data. The new method models the dependency between input feature vectors (images) and weighs the outliers with a higher penalty by generalizing the original loss function to the coupled entropy function, using the principles of nonlinear statistical coupling. We evaluate the performance of the coupled VAE model using the MNIST dataset. Compared with the traditional VAE algorithm, the output images generated by the coupled VAE method are clearer and less blurry. The visualization of the input images embedded in 2D latent variable space provides a deeper insight into the structure of new model with coupled loss function: the latent variable has a smaller deviation and the output values are generated by a more compact latent space. We analyze the histogram of the likelihoods of the input images using the generalized mean, which measures the model's accuracy as a function of the relative risk. The neutral accuracy, which is the geometric mean and is consistent with a measure of the Shannon cross-entropy, is improved. The robust accuracy, measured by the -2/3 generalized mean, is also improved. And the decisive accuracy, measured by the arithmetic mean, is unchanged.

Simplifying machine learning (ML) application development, including distributed computation, programming interface, resource management, model selection, etc, has attracted intensive interests recently. These research efforts have significantly improved the efficiency and the degree of automation of developing ML models. In this paper, we take a first step in an orthogonal direction towards automated quality management for human-in-the-loop ML application development. We build ease. ml/meter, a system that can automatically detect and measure the degree of overfitting during the whole lifecycle of ML application development. ease. ml/meter returns overfitting signals with strong probabilistic guarantees, based on which developers can take appropriate actions. In particular, ease. ml/meter provides principled guidelines to simple yet nontrivial questions regarding desired validation and test data sizes, which are among commonest questions raised by developers. The fact that ML application development is typically a continuous procedure further worsens the situation: The validation and test data sets can lose their statistical power quickly due to multiple accesses, especially in the presence of adaptive analysis. ease. ml/meter addresses these challenges by leveraging a collection of novel techniques and optimizations, resulting in practically tractable data sizes without compromising the probabilistic guarantees. We present the design and implementation details of ease. ml/meter, as well as detailed theoretical analysis and empirical evaluation of its effectiveness.