Modeling how individuals evolve over time is a fundamental problem in the natural and social sciences. However, existing datasets are often cross-sectional with each individual only observed at a single timepoint, making inference of temporal dynamics hard. Motivated by the study of human aging, we present a model that can learn temporal dynamics from cross-sectional data. Our model represents each individual with a low-dimensional latent state that consists of 1) a dynamic vector $rt$ that evolves linearly with time $t$, where $r$ is an individual-specific "rate of aging" vector, and 2) a static vector $b$ that captures time-independent variation. Observed features are a non-linear function of $rt$ and $b$. We prove that constraining the mapping between $rt$ and a subset of the observed features to be order-isomorphic yields a model class that is identifiable if the distribution of time-independent variation is known. Our model correctly recovers the latent rate vector $r$ in realistic synthetic data. Applied to the UK Biobank human health dataset, our model accurately reconstructs the observed data while learning interpretable rates of aging $r$ that are positively associated with diseases, mortality, and aging risk factors.

His research interests are in the area of large scale and online machine learning algorithms. He develops infinitely scalable machine learning algorithms for Amazon SageMaker. Amir Sadoughi is a Senior Software Development Engineer on the AWS AI SageMaker Algorithms team. He is passionate about technologies at the intersection of distributed systems and machine learning.

The terms artificial intelligence and machine learning have gained a lot of hype in the news lately, and a lot of articles seem to use both terms interchangeably, even though they are different. The aim of this article is to make more sense of all the technical jargon out there. The term artificial intelligence (AI) is derived from the phrase, "man-made ability to learn and understand." This means AI is a broad brand association name which covers all things man-made with respect to the human ability to understand and disseminate information. Data, which is unprocessed information, is the foundation to which all man-made systems learn, hence the rise of the term, "big data."

Markov Chain Monte Carlo (MCMC) is a widely popular technique in Bayesian statistics. It is used for posteriori distribution sampling since the analytical form is very often non-trackable. In this post, however, we are going to use it to generate animations from static images/logos. Incidentally, it might serve as an introduction to MCMC and Rejection sampling. The idea is based on a great open source package imcmc that is built upon PyMC3.

We introduce a methodology for nonlinear inverse problems using a variational Bayesian approach where the unknown quantity is a spatial field. A structured Bayesian Gaussian process latent variable model is used both to construct a low-dimensional generative model of the sample-based stochastic prior as well as a surrogate for the forward evaluation. Its Bayesian formulation captures epistemic uncertainty introduced by the limited number of input and output examples, automatically selects an appropriate dimensionality for the learned latent representation of the data, and rigorously propagates the uncertainty of the data-driven dimensionality reduction of the stochastic space through the forward model surrogate. The structured Gaussian process model explicitly leverages spatial information for an informative generative prior to improve sample efficiency while achieving computational tractability through Kronecker product decompositions of the relevant kernel matrices. Importantly, the Bayesian inversion is carried out by solving a variational optimization problem, replacing traditional computationally-expensive Monte Carlo sampling. The methodology is demonstrated on an elliptic PDE and is shown to return well-calibrated posteriors and is tractable with latent spaces with over 100 dimensions.

Collision avoidance is a critical task in many applications, such as ADAS (advanced driver-assistance systems), industrial automation and robotics. In an industrial automation setting, certain areas should be off limits to an automated vehicle for protection of people and high-valued assets. These areas can be quarantined by mapping (e.g., GPS) or via beacons that delineate a no-entry area. We propose a delineation method where the industrial vehicle utilizes a LiDAR {(Light Detection and Ranging)} and a single color camera to detect passive beacons and model-predictive control to stop the vehicle from entering a restricted space. The beacons are standard orange traffic cones with a highly reflective vertical pole attached. The LiDAR can readily detect these beacons, but suffers from false positives due to other reflective surfaces such as worker safety vests. Herein, we put forth a method for reducing false positive detection from the LiDAR by projecting the beacons in the camera imagery via a deep learning method and validating the detection using a neural network-learned projection from the camera to the LiDAR space. Experimental data collected at Mississippi State University's Center for Advanced Vehicular Systems (CAVS) shows the effectiveness of the proposed system in keeping the true detection while mitigating false positives.

Sparse learning has been shown to be effective in solving many real-world problems. Finding sparse representations is a fundamentally important topic in many fields of science including signal processing, computer vision, genome study and medical imaging. One important issue in applying sparse representation is to find the basis to represent the data,especially in computer vision and medical imaging where the data is not necessary incoherent. In medical imaging, clinicians often grade the severity or measure the risk score of a disease based on images. This process is referred to as medical image grading. Manual grading of the disease severity or risk score is often used. However, it is tedious, subjective and expensive. Sparse learning has been used for automatic grading of medical images for different diseases. In the grading, we usually begin with one step to find a sparse representation of the testing image using a set of reference images or atoms from the dictionary. Then in the second step, the selected atoms are used as references to compute the grades of the testing images. Since the two steps are conducted sequentially, the objective function in the first step is not necessarily optimized for the second step. In this paper, we propose a novel sparse range-constrained learning(SRCL)algorithm for medical image grading.Different from most of existing sparse learning algorithms, SRCL integrates the objective of finding a sparse representation and that of grading the image into one function. It aims to find a sparse representation of the testing image based on atoms that are most similar in both the data or feature representation and the medical grading scores. We apply the new proposed SRCL to CDR computation and cataract grading. Experimental results show that the proposed method is able to improve the accuracy in cup-to-disc ratio computation and cataract grading.

Raven's Progressive Matrices are one of the widely used tests in evaluating the human test taker's fluid intelligence. Analogously, this paper introduces geometric generalization based zero-shot learning tests to measure the rapid learning ability and the internal consistency of deep generative models. Our empirical research analysis on state-of-the-art generative models discern their ability to generalize concepts across classes. In the process, we introduce Infinite World, an evaluable, scalable, multi-modal, light-weight dataset and Zero-Shot Intelligence Metric ZSI. The proposed tests condenses human-level spatial and numerical reasoning tasks to its simplistic geometric forms. The dataset is scalable to a theoretical limit of infinity, in numerical features of the generated geometric figures, image size and in quantity. We systematically analyze state-of-the-art model's internal consistency, identify their bottlenecks and propose a pro-active optimization method for few-shot and zero-shot learning.

To predict the employee attrition beforehand and to enable management to take individualized preventive action. Using Ensemble classification modeling techniques and Linear Regression. Model could predict over 91% accurate employee prediction, lead-time in separation and individual reasons causing attrition. Prior intimation of employee attrition enables manager to take preventive actions to retain employee or to manage the business consequences of attrition. Once deployed this will model can help in downtrend Employee Attrition, will help manager to manage team more effectively. Model does not cover the natural calamities, and unforeseen events occurring at an individual level like accident, death etc.

In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning. We develop a formal correspondence between this work and thermodynamics and discuss its implications.