An image pattern can be represented by a probability distribution whose density is concentrated on different low-dimensional subspaces in the high-dimensional image space. Such probability densities have an astronomical number of local modes corresponding to typical pattern appearances. Related groups of modes can join to form macroscopic image basins that represent pattern concepts. Recent works use neural networks that capture high-order image statistics to learn Gibbs models capable of synthesizing realistic images of many patterns. However, characterizing a learned probability density to uncover the Hopfield memories of the model, encoded by the structure of the local modes, remains an open challenge. In this work, we present novel computational experiments that map and visualize the local mode structure of Gibbs densities. Efficient mapping requires identifying the global basins without enumerating the countless modes. Inspired by Grenander's jump-diffusion method, we propose a new MCMC tool called Attraction-Diffusion (AD) that can capture the macroscopic structure of highly non-convex densities by measuring metastability of local modes. AD involves altering the target density with a magnetization potential penalizing distance from a known mode and running an MCMC sample of the altered density to measure the stability of the initial chain state. Using a low-dimensional generator network to facilitate exploration, we map image spaces with up to 12,288 dimensions (64 $\times$ 64 pixels in RGB). Our work shows: (1) AD can efficiently map highly non-convex probability densities, (2) metastable regions of pattern probability densities contain coherent groups of images, and (3) the perceptibility of differences between training images influences the metastability of image basins.

Imagine you wanted to determine how much solar energy could be generated from adding solar cells to a particular house. This is what Google's Project Sunroof does with Deep Learning. Enter an address and Google uses a Deep Learning framework to estimate how much money you could save in energy costs with solar cells over 20 years (see Figure 1). But let's assume there "might" be an even better way to estimate solar energy savings. For example, you want to use Deep Learning to estimate how much solar energy we could generate with solar panels on the Golden Gate Bridge (that probably wouldn't be a very popular decision in San Francisco).

IoT data control is a key way that companies can maximize the value of their Internet of Things deployments. It allows companies to mine the data that IoT devices generate and monetize the information.

Optimal Transport (OT) is a mathematical gem at the interface between probability, analysis and optimization. The goal of that theory is to define geometric tools that are useful to compare probability distributions. Earlier contributions originated from Monge's work in the 18th century, to be later rediscovered under a different formalism by Tolstoi in the 1920's, Kantorovich, Hitchcock and Koopmans in the 1940's. The problem was solved numerically by Dantzig in 1949 and others in the 1950's within the framework of linear programming, paving the way for major industrial applications in the second half of the 20th century. OT was later rediscovered under a different light by analysts in the 90's, following important work by Brenier and others, as well as in the computer vision/graphics fields under the name of earth mover's distances. Recent years have witnessed yet another revolution in the spread of OT, thanks to the emergence of approximate solvers that can scale to sizes and dimensions that are relevant to data sciences. Thanks to this newfound scalability, OT is being increasingly used to unlock various problems in imaging sciences (such as color or texture processing), computer vision and graphics (for shape manipulation) or machine learning (for regression,classification and density fitting). This short book reviews OT with a bias toward numerical methods and their applications in data sciences, and sheds lights on the theoretical properties of OT that make it particularly useful for some of these applications.

In recent years, correntropy and its applications in machine learning have been drawing continuous attention owing to its merits in dealing with non-Gaussian noise and outliers. However, theoretical understanding of correntropy, especially in the statistical learning context, is still limited. In this study, within the statistical learning framework, we investigate correntropy based regression in the presence of non-Gaussian noise or outliers. To this purpose, we first introduce mixture of symmetric stable noise, which include Gaussian noise, Cauchy noise, and the mixture of Gaussian noise as special cases, to model non-Gaussian noise and outliers. We demonstrate that under the mixture of symmetric stable noise assumption, correntropy based regression can learn the conditional mean function or the conditional median function well without requiring the finite variance assumption of the noise. In particular, we establish learning rates for correntropy based regression estimators that are asymptotically of type $\mathcal{O}(n^{-1})$. We believe that the present study completes our understanding towards correntropy based regression from a statistical learning viewpoint, and may also shed some light on robust statistical learning for regression.

The oil and gas industry, auto manufacturers and more can maximize the value of IoT deployments with IoT data control. A Cisco exec explains how to manage data control and why it's necessary.

These eye-opening designs propose a future of flight that is both supersonic and eco-friendly. The hypersonic plane would cut travel times between New York and London to just three hours, more than halving the duration of current flights. What's more, the amazing aircraft will produce zero carbon emissions, thanks to the compact fusion reactor that will power it. According to designer Oscar Vinals, the craft, which he hopes will revolutionise the aeronautic industry, will run primarily on a compact fusion reactor (CFR). This reactor, the plans say, would provide the Magavem with an incredible amount of electrical energy - all at no cost to the environment.

The design of gaits for robot locomotion can be a daunting process which requires significant expert knowledge and engineering. This process is even more challenging for robots that do not have an accurate physical model, such as compliant or micro-scale robots. Data-driven gait optimization provides an automated alternative to analytical gait design. In this paper, we propose a novel approach to efficiently learn a wide range of locomotion tasks with walking robots. This approach formalizes locomotion as a contextual policy search task to collect data, and subsequently uses that data to learn multi-objective locomotion primitives that can be used for planning. As a proof-of-concept we consider a simulated hexapod modeled after a recently developed microrobot, and we thoroughly evaluate the performance of this microrobot on different tasks and gaits. Our results validate the proposed controller and learning scheme on single and multi-objective locomotion tasks. Moreover, the experimental simulations show that without any prior knowledge about the robot used (e.g., dynamics model), our approach is capable of learning locomotion primitives within 250 trials and subsequently using them to successfully navigate through a maze.

Skynet, V.I.K.I, and H.A.L. 9000 are a few examples of AIs imbued with the power of machine learning. They were created to solve problems that had become too complex for humans and were given control of everything through a neural network to increase efficiency, safety, and success. Granted, movies need an antagonist, so these AI marvels were given an unfavorable dark side – but such complex machine learning is real and has been successfully implemented. Data centers have exploded into existence since the 2000's. Originating from small servers in local offices, they have grown into hyperscale facilities in order to maintain our IoT and all of the associated data.

Computers can beat chess champions, simulate star explosions, and forecast global climate. We are even teaching them to be infallible problem-solvers and fast learners. And now, physicists at the Department of Energy's Lawrence Berkeley National Laboratory (Berkeley Lab) and their collaborators have demonstrated that computers are ready to tackle the universe's greatest mysteries. The team fed thousands of images from simulated high-energy particle collisions to train computer networks to identify important features. The researchers programmed powerful arrays known as neural networks to serve as a sort of hivelike digital brain in analyzing and interpreting the images of the simulated particle debris left over from the collisions.