The visual systems of many mammals, including humans, is able to integrate the geometric information of visual stimuli and to perform cognitive tasks already at the first stages of the cortical processing. This is thought to be the result of a combination of mechanisms, which include feature extraction at single cell level and geometric processing by means of cells connectivity. We present a geometric model of such connectivities in the space of detected features associated to spatio-temporal visual stimuli, and show how they can be used to obtain low-level object segmentation. The main idea is that of defining a spectral clustering procedure with anisotropic affinities over datasets consisting of embeddings of the visual stimuli into higher dimensional spaces. Neural plausibility of the proposed arguments will be discussed.

In many statistical learning problems, the target functions to be optimized are highly non-convex in various model spaces and thus are difficult to analyze. In this paper, we compute Energy Landscape Maps (ELMs) which characterize and visualize an energy function with a tree structure, in which each leaf node represents a local minimum and each non-leaf node represents the barrier between adjacent energy basins. The ELM also associates each node with the estimated probability mass and volume for the corresponding energy basin. We construct ELMs by adopting the generalized Wang-Landau algorithm and multidomain sampler that simulates a Markov chain traversing the model space by dynamically reweighting the energy function. We construct ELMs in the model space for two classic statistical learning problems: i) clustering with Gaussian mixture models or Bernoulli templates; and ii) bi-clustering. We propose a way to measure the difficulties (or complexity) of these learning problems and study how various conditions affect the landscape complexity, such as separability of the clusters, the number of examples, and the level of supervision; and we also visualize the behaviors of different algorithms, such as K-mean, EM, two-step EM and Swendsen-Wang cuts, in the energy landscapes. Key words and phrases: Non-convex Optimization, Visualization, Clustering, Bi-clustering, Markov chain Monte Carlo. 1. INTRODUCTION In many statistical learning problems, the energy functions to be optimized are highly non-convex.

Classifiers based on sparse representations have recently been shown to provide excellent results in many visual recognition and classification tasks. However, the high cost of computing sparse representations at test time is a major obstacle that limits the applicability of these methods in large-scale problems, or in scenarios where computational power is restricted. We consider in this paper a simple yet efficient alternative to sparse coding for feature extraction. We study a classification scheme that applies the soft-thresholding nonlinear mapping in a dictionary, followed by a linear classifier. A novel supervised dictionary learning algorithm tailored for this low complexity classification architecture is proposed. The dictionary learning problem, which jointly learns the dictionary and linear classifier, is cast as a difference of convex (DC) program and solved efficiently with an iterative DC solver. We conduct experiments on several datasets, and show that our learning algorithm that leverages the structure of the classification problem outperforms generic learning procedures. Our simple classifier based on soft-thresholding also competes with the recent sparse coding classifiers, when the dictionary is learned appropriately. The adopted classification scheme further requires less computational time at the testing stage, compared to other classifiers. The proposed scheme shows the potential of the adequately trained soft-thresholding mapping for classification and paves the way towards the development of very efficient classification methods for vision problems.

Artificial intelligence, or AI, is transforming the medical device industry today. As medical devices continue to incorporate artificial intelligence to perform or support medical applications, new regulations require AI-driven medical devices to comply with state-of-the-art requirements and provide objective evidence for repeatability and reliability. AI has the potential to improve patient outcomes as well as the productivity and efficiency of healthcare delivery. It can also improve the day-to-day lives of healthcare providers by allowing them to spend more time caring for patients, hence improving staff morale and retention. It may even accelerate the development of life-saving therapies.

An increasing number of medical devices incorporate artificial intelligence (AI) capabilities to support therapeutic and diagnostic applications. In spite of the risks connected with this innovative technology, the applicable regulatory framework does not specify any requirements for this class of medical devices. To make matters even more complicated for manufacturers, there are no standards, guidance documents or common specifications for medical devices on how to demonstrate conformity with the essential requirements. The term artificial intelligence (AI) describes the capability of algorithms to take over tasks and decisions by mimicking human intelligence.1 Many experts believe that machine learning, a subset of artificial intelligence, will play a significant role in the medtech sector.2,3 "Machine learning" is the term used to describe algorithms capable of learning directly from a large volume of "training data". The algorithm builds a model based on training data and applies the experience, it has gained from the training to make predictions and decisions on new, unknown data. Artificial neural networks are a subset of machine learning methods, which have evolved from the idea of simulating the human brain.22 Neural networks are information-processing systems used for machine learning and comprise multiple layers of neurons. Between the input layer, which receives information, and the output layer, there are numerous hidden layers of neurons. In simple terms, neural networks comprise neurons – also known as nodes – which receive external information or information from other connected nodes, modify this information, and pass it on, either to the next neuron layer or to the output layer as the final result.5 Deep learning is a variation of artificial neural networks, which consist of multiple hidden neural network layers between the input and output layers. The inner layers are designed to extract higher-level features from the raw external data.

Since 2019 the FDA's crosscutting work has implemented artificial intelligence (AI) as part of the its New Era of Smarter Food Safety initiative. This new application of available data sources can strengthen the agency's public health mission with the goal using AI to improve capabilities to quickly and efficiently identify products that may pose a threat to public health by impeding their entry into the U.S. market. On February 8 the FDA reported the initiation of their succeeding phase for AI activity with the Imported Seafood Pilot program. Running from February 1 through July 31, 2021, the pilot will allow FDA to study and evaluate the utility of AI in support of import targeting, ultimately assisting with the implementation of an AI model to target high-risk seafood products--a critical strategy, as the United States imports nearly 94% of its seafood, according to the FDA. Where in the past, reliance on human intervention and/or trend analysis drove scrutiny of seafood shipments such as field exams, label exams or laboratory analysis of samples, with the use of AI technologies, FDA surveillance and regulatory efforts might be improved.

The use of artificial intelligence (AI) in life sciences, or "Life Tech", has increased at a rapid pace. According to World Intellectual Property Organization (WIPO), there has been "a shift from theoretical research to the use of AI technologies in commercial products and services," as reflected in the change in ratio of scientific papers to patent applications over the past decade.1 Indeed, while research into AI began in earnest in the 1950s, more than 1.6 million scientific papers have been published on AI, with more than half of identified AI inventions in the last six years alone.2,3 A review article in Nature Medicine reported last year that despite few peer-reviewed publications on use of machine learning technologies in medical devices, FDA approvals of AI as medical devices have been accelerating.4 Many of these FDA approvals relate to image analysis for diagnostic purposes, such as QuantX, the first AI platform to evaluate breast abnormalities; Aidoc, which detects acute intracranial hemorrhages in head CT scans, assisting radiologists to prioritize patient injuries; and IDx-DR, which analyzes retinal images to detect diabetic retinopathy.

We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching computers to recognize objects in images. We want the computers to be able to learn faster at the expense of providing extra information during training time. As additional information about the image data, we look at several scenarios that have been studied in computer vision before: attributes, bounding boxes and image tags. The information is privileged as it is available at training time but not at test time. We explore two maximum-margin techniques that are able to make use of this additional source of information, for binary and multiclass object classification. We interpret these methods as learning easiness and hardness of the objects in the privileged space and then transferring this knowledge to train a better classifier in the original space. We provide a thorough analysis and comparison of information transfer from privileged to the original data spaces for both LUPI methods. Our experiments show that incorporating privileged information can improve the classification accuracy. Finally, we conduct user studies to understand which samples are easy and which are hard for human learning, and explore how this information is related to easy and hard samples when learning a classifier.

We present an integer programming framework to build accurate and interpretable discrete linear classification models. Unlike existing approaches, our framework is designed to provide practitioners with the control and flexibility they need to tailor accurate and interpretable models for a domain of choice. To this end, our framework can produce models that are fully optimized for accuracy, by minimizing the 0--1 classification loss, and that address multiple aspects of interpretability, by incorporating a range of discrete constraints and penalty functions. We use our framework to produce models that are difficult to create with existing methods, such as scoring systems and M-of-N rule tables. In addition, we propose specially designed optimization methods to improve the scalability of our framework through decomposition and data reduction. We show that discrete linear classifiers can attain the training accuracy of any other linear classifier, and provide an Occam's Razor type argument as to why the use of small discrete coefficients can provide better generalization. We demonstrate the performance and flexibility of our framework through numerical experiments and a case study in which we construct a highly tailored clinical tool for sleep apnea diagnosis.

Unsupervised Bump Hunting Using Principal Components Daniel A D ıaz-Pach on Jean-Eudes Dazard † J. Sunil Rao‡ March 14, 2018 Abstract Principal Components Analysis is a widely used technique for dimension reduction and characterization of variability in multivariate populations. Our interest lies in studying when and why the rotation to principal components can be used effectively within a response-predictor set relationship in the context of mode hunting. Specifically focusing on the Patient Rule Induction Method (PRIM), we first develop a fast version of this algorithm (fastPRIM) under normality which facilitates the theoretical studies to follow. Using basic geometrical arguments, we then demonstrate how the PC rotation of the predictor space alone can in fact generate improved mode estimators. Simulation results are used to illustrate our findings. Key words: Algorithms, Bump hunting, Computationally intensive methods, Mode hunting, Principal components. 1 Introduction The PRIM algorithm for bump hunting was first developed by Friedman and Fisher (1999). It is an intuitively useful computational algorithm for the detection of local maxima (or minima) on target functions. Roughly speaking, PRIM peels the (conditional) distribution of a response from the outside in, leaving at the end rectangular boxes which are supposed to contain a bump (see the formal description in Algorithm 1) at page 5. However, some shortcomings against this procedure have also appeared in the literature when several dimensions are under consideration. For instance, as Polonik and Wang (2010) explained it, the method could fail when there are two or more modes in high-dimensional settings.