A group of scientists in Canada have announced a new initiative to use drones to plant new trees cheaply and quickly in part of an effort to fight against the negative effects of climate change and deforestation. Called Flash Forest, the team began testing its drone delivery systems in August, with a test flight that saw them successfully plant 100 trees with a drone. Those results were so encouraging they've expanded their goals to use their specially designed drone systems to plant a billion new trees by 2028. 'Every year the planet loses 13 billion trees and regains less than half of that,' the team's Bryce Jones said in a fundraising video announcing the project. 'We started Flash Forest with the goal of healing the planet's lungs and taking that job seriously.

Honda's exhibit at CES 2020 will feature global debuts of concepts that integrate connected, autonomous, shared and electric (CASE) technologies in new mobility products and services. Some of the eye-catching technology concepts and prototypes include the augmented driving concept, the energy management solutions and'Safe Swarm' and'Smart Intersection' prototypes. This augmented driving concept features a seamless transition from autonomous to semi-autonomous driving operation. This system is constantly on standby, ready to intervene and control the vehicle when needed. Various sensors in the vehicle continuously read the user's intention to smoothly shift between these modes, creating an instinctive driving experience.

Circular fashion is part of the circular economy, an economic system that at its core is embedded with an ideology of reuse, recycle and refurbish in order to eliminate waste, stop items from going into landfills, and extend the lifecycle of products by keeping them in use and in circulation. The fashion industry is notorious for its wasteful and environmentally damaging practices accounting for over 10% of global carbon emissions a percentage which is slated to increase to 24% of the global carbon budget by the year 2050 at current demand. Much of this is due to the synthetic fibers and fabrics primarily used in fast fashion, 70 million barrels of oil are used to produce polyester every year and wasteful practices exacerbate the impact, it turns out that the equivalent of one garbage truck of textiles is landfilled or incinerated every second! Fresh on the heels of a $175 million raise, thredUP is poised to capitalize on the growing $24 billion second-hand market through its use of artificial intelligence to bring efficiencies and scale to every area of its operations, while fueling the circular fashion trend among traditional retail brands with the launch of its "resale as a service" offering. The company's mission is to inspire a new generation of shoppers to think second hand first, keeping clothing out of landfills so that people can look great without being part of the problem.

Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot learn at all. Similarly, if the agent receives also rewards that create suboptimal modes of the objective function, it will likely prematurely stop exploring. More recent methods add auxiliary intrinsic rewards to encourage exploration. However, auxiliary rewards lead to a non-stationary target for the Q-function. In this paper, we present a novel approach that (1) plans exploration actions far into the future by using a long-term visitation count, and (2) decouples exploration and exploitation by learning a separate function assessing the exploration value of the actions. Contrary to existing methods which use models of reward and dynamics, our approach is off-policy and model-free. We further propose new tabular environments for benchmarking exploration in reinforcement learning. Empirical results on classic and novel benchmarks show that the proposed approach outperforms existing methods in environments with sparse rewards, especially in the presence of rewards that create suboptimal modes of the objective function. Results also suggest that our approach scales gracefully with the size of the environment. Source code is available at https://github.com/sparisi/visit-value-explore

Smart grid is an emerging and promising technology. It uses the power of information technologies to deliver intelligently the electrical power to customers, and it allows the integration of the green technology to meet the environmental requirements. Unfortunately, information technologies have its inherent vulnerabilities and weaknesses that expose the smart grid to a wide variety of security risks. The Intrusion detection system (IDS) plays an important role in securing smart grid networks and detecting malicious activity, yet it suffers from several limitations. Many research papers have been published to address these issues using several algorithms and techniques. Therefore, a detailed comparison between these algorithms is needed. This paper presents an overview of four data mining algorithms used by IDS in Smart Grid. An evaluation of performance of these algorithms is conducted based on several metrics including the probability of detection, probability of false alarm, probability of miss detection, efficiency, and processing time. Results show that Random Forest outperforms the other three algorithms in detecting attacks with higher probability of detection, lower probability of false alarm, lower probability of miss detection, and higher accuracy.

Researchers at the University of Central Florida think artificial intelligence could help move that process forward faster. The team's work so impressed …

LONDON – Helicopter cash, climate crises, smart cities and the space economy -- investors have all those possibilities ahead as they enter the third decade of the 21st century. They go into the new decade with a spring in their step after watching world stocks add over $25 trillion in value in the past 10 years and a bond rally put $13 trillion worth of bond yields below zero. They also saw internet-based firms transform the way humans work, shop and relax. Now investors are positioning for the tech revolution's next 10 years. Could we see a repeat of the Roaring '20, as the 1920s were known -- years of prosperity, technological innovation and such social developments as women winning the right to vote?

A fully-convolutional neural-network model is used to predict the streamwise velocity fields at several wall-normal locations by taking as input the streamwise and spanwise wall-shear-stress planes in a turbulent open channel flow. The training data are generated by performing a direct numerical simulation (DNS) at a friction Reynolds number of $Re_{\tau}=180$. Various networks are trained for predictions at three inner-scaled locations ($y^+ = 15,~30,~50$) and for different time steps between input samples $\Delta t^{+}_{s}$. The inherent non-linearity of the neural-network model enables a better prediction capability than linear methods, with a lower error in both the instantaneous flow fields and turbulent statistics. Using a dataset with higher $\Delta t^+_{s}$ improves the generalization at all the considered wall-normal locations, as long as the network capacity is sufficient to generalize over the dataset. The use of a multiple-output network, with parallel dedicated branches for two wall-normal locations, does not provide any improvement over two separated single-output networks, other than a moderate saving in training time. Training time can be effectively reduced, by a factor of 4, via a transfer learning method that initializes the network parameters using the optimized parameters of a previously-trained network.

A BSTRACT A fundamental goal in deep learning is the characterization of trainability and generalization of neural networks as a function of their architecture and hyper-parameters. In this paper, we discuss these challenging issues in the context of wide neural networks at large depths where we will see that the situation simplifies considerably. To do this, we leverage recent advances that have separately shown: (1) that in the wide network limit, random networks before training are Gaussian Processes governed by a kernel known as the Neural Network Gaussian Process (NNGP) kernel, (2) that at large depths the spectrum of the NNGP kernel simplifies considerably and becomes "weakly data-dependent", and (3) that gradient descent training of wide neural networks is described by a kernel called the Neural Tangent Kernel (NTK) that is related to the NNGP . Here we show that in the large depth limit the spectrum of the NTK simplifies in much the same way as that of the NNGP kernel. By analyzing this spectrum, we arrive at a precise characterization of trainability and a necessary condition for generalization across a range of architectures including Fully Connected Networks (FCNs) and Con-volutional Neural Networks (CNNs). In particular, we find that there are large regions of hyperparameter space where networks can only memorize the training set in the sense they reach perfect training accuracy but completely fail to generalize outside the training set, in contrast with several recent results. By comparing CNNs with-and without-global average pooling, we show that CNNs without average pooling have very nearly identical learning dynamics to FCNs while CNNs with pooling contain a correction that alters its generalization performance. We perform a thorough empirical investigation of these theoretical results and finding excellent agreement on real datasets. Historically, the rampant success of deep learning models has lacked a sturdy theoretical foundation; architectures, hyperparameters, and learning algorithms are often selected by brute force search (Bergstra & Bengio, 2012) and heuristics (Glorot & Bengio, 2010). Recently, significant theoretical progress has been made on several fronts that have shown promise in making neural network design more systematic. In particular, in the infinite width (or channel) limit, the distribution of functions induced by neural networks with random weights and biases has been precisely characterized before, during, and after training. The study of infinite networks dates back to seminal work by Neal (1994) who showed that the distribution of functions given by single hidden-layer networks with random weights and biases in the infinite-width limit are Gaussian Processes (GPs). Recently, there has been renewed interest in studying random, infinite, networks starting with concurrent work on "conjugate kernels" (Daniely et al., 2016; Daniely, 2017) and "mean-field theory" (Poole et al., 2016; Schoenholz et al., 2017).

Given an overcomplete dictionary $A$ and a signal $b = Ac^*$ for some sparse vector $c^*$ whose nonzero entries correspond to linearly independent columns of $A$, classical sparse signal recovery theory considers the problem of whether $c^*$ can be recovered as the unique sparsest solution to $b = A c$. It is now well-understood that such recovery is possible by practical algorithms when the dictionary $A$ is incoherent or restricted isometric. In this paper, we consider the more general case where $b$ lies in a subspace $\mathcal{S}_0$ spanned by a subset of linearly dependent columns of $A$, and the remaining columns are outside of the subspace. In this case, the sparsest representation may not be unique, and the dictionary may not be incoherent or restricted isometric. The goal is to have the representation $c$ correctly identify the subspace, i.e. the nonzero entries of $c$ should correspond to columns of $A$ that are in the subspace $\mathcal{S}_0$. Such a representation $c$ is called subspace-preserving, a key concept that has found important applications for learning low-dimensional structures in high-dimensional data. We present various geometric conditions that guarantee subspace-preserving recovery. Among them, the major results are characterized by the covering radius and the angular distance, which capture the distribution of points in the subspace and the similarity between points in the subspace and points outside the subspace, respectively. Importantly, these conditions do not require the dictionary to be incoherent or restricted isometric. By establishing that the subspace-preserving recovery problem and the classical sparse signal recovery problem are equivalent under common assumptions on the latter, we show that several of our proposed conditions are generalizations of some well-known conditions in the sparse signal recovery literature.