The local authority, Council of Agriculture (COA), guided seeds manufacturers to improve F1 hybrid seed collecting techniques that resulted in superior harvest performance of cruciferous vegetables, watermelons and cherry tomatoes. The featured exhibitors invited to showcase at the pavilion of Taiwan Seed Varieties this year include Besgrow Seed, Ching Long Seed, Agronew Trading, Taiwan Banana Research Institute, Known-You Seed and Sing-Flow Seed Trading. One of the exhibitors - CH Biotech, developed'Weather Mend,' a product to regulate plant gene expression system with non-genetically modified active components, which is seen as a crucial solutions for crops in facing extreme climate change. This product aims to increase plant survival rate and helps steady food supply. Not only will it initiate plants' defence mechanism in advance, but also reduce losses caused by severe weather.

The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference. Conventional approximate computing focuses on balancing the efficiency-accuracy trade-off for existing pre-trained networks, which can lead to suboptimal solutions. In this paper, we propose AxTrain, a hardware-oriented training framework to facilitate approximate computing for NN inference. Specifically, AxTrain leverages the synergy between two orthogonal methods---one actively searches for a network parameters distribution with high error tolerance, and the other passively learns resilient weights by numerically incorporating the noise distributions of the approximate hardware in the forward pass during the training phase. Experimental results from various datasets with near-threshold computing and approximation multiplication strategies demonstrate AxTrain's ability to obtain resilient neural network parameters and system energy efficiency improvement.

We consider the problem of predicting power outages in an electrical power grid due to hazards produced by convective storms. These storms produce extreme weather phenomena such as intense wind, tornadoes and lightning over a small area. In this paper, we discuss the application of state-of-the-art machine learning techniques, such as random forest classifiers and deep neural networks, to predict the amount of damage caused by storms. We cast this application as a classification problem where the goal is to classify storm cells into a finite number of classes, each corresponding to a certain amount of expected damage. The classification method use as input features estimates for storm cell location and movement which has to be extracted from the raw data. A main challenge of this application is that the training data is heavily imbalanced as the occurrence of extreme weather events is rare. In order to address this issue, we applied SMOTE technique.

The great success of deep learning shows that its technology contains profound truth, and understanding its internal mechanism not only has important implications for the development of its technology and effective application in various fields, but also provides meaningful insights into the understanding of human brain mechanism. At present, most of the theoretical research on deep learning is based on mathematics. This dissertation proposes that the neural network of deep learning is a physical system, examines deep learning from three different perspectives: microscopic, macroscopic, and physical world views, answers multiple theoretical puzzles in deep learning by using physics principles. For example, from the perspective of quantum mechanics and statistical physics, this dissertation presents the calculation methods for convolution calculation, pooling, normalization, and Restricted Boltzmann Machine, as well as the selection of cost functions, explains why deep learning must be deep, what characteristics are learned in deep learning, why Convolutional Neural Networks do not have to be trained layer by layer, and the limitations of deep learning, etc., and proposes the theoretical direction and basis for the further development of deep learning now and in the future. The brilliance of physics flashes in deep learning, we try to establish the deep learning technology based on the scientific theory of physics.

Insect-sized flying robots could help with time-consuming tasks like surveying crop growth on large farms or sniffing out gas leaks. These robots soar by fluttering tiny wings because they are too small to use propellers, like those seen on their larger drone cousins. Small size is advantageous: These robots are cheap to make and can easily slip into tight places that are inaccessible to big drones. But current flying robo-insects are still tethered to the ground. The electronics they need to power and control their wings are too heavy for these miniature robots to carry.

Bike sharing provides an environment-friendly way for traveling and is booming worldwide. Yet, due to the high similarity of user travel patterns, the bike imbalance problem constantly occurs, especially for dockless bike sharing systems, causing significant impact on service quality and company revenue. Thus, it has become a critical task for bike sharing systems to resolve such imbalance efficiently. In this paper, we propose a novel deep reinforcement learning framework for incentivizing users to rebalance such sys- tems. We model this problem as a Markov decision process and take both spatial and temporal features into consideration. We develop a novel deep reinforcement learning algorithm called Hierarchical Reinforcement Pricing (HRP), which builds upon the Deep Deterministic Policy Gradient algorithm. Different from existing methods that often ignore spatial information and rely heavily on accurate prediction, HRP can capture both spatial and temporal dependencies using a divide-and-conquer structure with an embedded localized module. We conduct extensive experiments to evaluate HRP, based on a dataset from Mobike, a major Chinese dockless bike sharing company. Results show that HRP performs close to the 24-timeslot look-ahead optimization, and outperforms state-of-the-art methods in both service level and bike distribution. It also transfers well when applied to unseen areas.

We have obtained an integral representation of the shallow neural network that attains the global minimum of its backpropagation (BP) training problem. According to our unpublished numerical simulations conducted several years prior to this study, we had noticed that such an integral representation may exist, but it was not proven until today. First, we introduced a Hilbert space of coefficient functions, and a reproducing kernel Hilbert space (RKHS) of hypotheses, associated with the integral representation. The RKHS reflects the approximation ability of neural networks. Second, we established the ridgelet analysis on RKHS. The analytic property of the integral representation is remarkably clear. Third, we reformulated the BP training as the optimization problem in the space of coefficient functions, and obtained a formal expression of the unique global minimizer, according to the Tikhonov regularization theory. Finally, we demonstrated that the global minimizer is the shrink ridgelet transform. Since the relation between an integral representation and an ordinary finite network is not clear, and BP is convex in the integral representation, we cannot immediately answer the question such as "Is a local minimum a global minimum?" However, the obtained integral representation provides an explicit expression of the global minimizer, without linearity-like assumptions, such as partial linearity and monotonicity. Furthermore, it indicates that the ordinary ridgelet transform provides the minimum norm solution to the original training equation.

Scientists have taken the tiny house trend to a whole new level. Using a new nanorobotic system, French scientists built a'microhouse' on top of an optical fiber that's as thin as human hair, which is 75 microns thick. It measures just 20 micrometers across but has several stunningly accurate details, including a front door, windows and even a tiled roof. A team of French scientists from the Femto-ST Institute built a 20-micrometer wide'microhouse' (pictured) on top of an optical fiber to demonstrate a new nanorobotic system A team of French scientists from the Femto-ST Institute detailed the process of creating the microhouse in new study published Friday in the Journal of Vacuum Science & Technology A. The new nanorobotic system, called μRobotex, uses a combination of technologies, including a tiny maneuverable robot, a focused ion beam and a gas injection device. To construct the microhouse, the scientists used a mix of origami and nanometer-precise robotics.

But current flying robo-insects are still tethered to the ground. The electronics they need to power and control their wings are too heavy for these miniature robots to carry. Now, engineers at the University of Washington have for the first time cut the cord and added a brain, allowing their RoboFly to take its first independent flaps. This might be one small flap for a robot, but it's one giant leap for robot-kind. The team will present its findings May 23 at the International Conference on Robotics and Automation in Brisbane, Australia.

UAVs are tackling everything from disease control to vacuuming up ocean waste to delivering pizza, and more. Drone technology has been used by defense organizations and tech-savvy consumers for quite some time. However, the benefits of this technology extends well beyond just these sectors. With the rising accessibility of drones, many of the most dangerous and high-paying jobs within the commercial sector are ripe for displacement by drone technology. The use cases for safe, cost-effective solutions range from data collection to delivery. And as autonomy and collision-avoidance technologies improve, so too will drones' ability to perform increasingly complex tasks. According to forecasts, the emerging global market for business services using drones is valued at over $127B. As more companies look to capitalize on these commercial opportunities, investment into the drone space continues to grow. A drone or a UAV (unmanned aerial vehicle) typically refers to a pilotless aircraft that operates through a combination of technologies, including computer vision, artificial intelligence, object avoidance tech, and others. But drones can also be ground or sea vehicles that operate autonomously.