Ex-Nervana Systems engineers made the jump from a hardware-centric approach to efficient training to pushing better insight into optimization of models and systems. Nervana Systems was one of the first AI chip startups to generate big buzz, culminating in an acquisition by Intel in summer, 2016. The startup's co-founder and CEO, Naveen Rao, moved into the VP role for the AI products group while fellow Nervana engineers, including Hanlin Tang (who led development for the Neon software stack for Nervana's devices) also stuck around Intel focusing on practical AI algorithms and federal programs. Rao and Tang, among others, are together again with a new startup, MosaicML, which came out of stealth today with $37 million in funding from a wide range of VC partners, including Lux Capital, Future Ventures, E14, and others. The target is machine learning training and as the world quickly learned, optimized deep learning has far less to do with efficient, high performance hardware than the VCs believed in the 2014-2021 frame.

Artificial intelligence (AI) is a broad field of computer science that focuses on creating intelligent machines that can accomplish activities that would normally need human intelligence. Machines may learn from their experiences, adapt to new inputs, and execute human-like jobs thanks to artificial intelligence (AI). Most AI examples you hear about today rely largely on deep learning and natural language processing, from chess-playing computers to self-driving cars. Computers can be trained to perform certain jobs by processing massive volumes of data and recognizing patterns in the data using these methods. Artificial Intelligence refers to the intelligence displayed by machines. In today's world, Artificial Intelligence has become highly popular. It is the simulation of human intelligence in computers that have been programmed to learn and mimic human actions.

In the moon-like landscape of northern Sudan, informal gold miners toil with spades and pickaxes to extract their prize from shallow pits that pockmark the terrain. Mining ore in the sweltering heat of the Nubian desert is the first stage of an illicit network that has exploded in the past 18 months following a pandemic-induced spike in the gold price. African governments desperate to recoup lost revenue are looking to Dubai to help stop the trade. Interviews with government officials across Africa reveal smuggling operations that span at least nine countries and involve tons of gold spirited over borders. That's a cause for international concern because the funds from contraband minerals dealing in Africa fuel conflict, finance criminal and terrorist networks, undermine democracy and facilitate money laundering, according to the Organisation for Economic Cooperation and Development. While it's impossible to say precisely how much is lost to smugglers each year, United Nations trade data for 2020 show a discrepancy of at least $4 billion between the United Arab Emirates' declared gold imports from Africa and what African countries say they exported to the UAE.

A swarm intelligence-based optimization algorithm, named Duck Swarm Algorithm (DSA), is proposed in this paper. This algorithm is inspired by the searching for food sources and foraging behaviors of the duck swarm. The performance of DSA is verified by using eighteen benchmark functions, where it is statistical (best, mean, standard deviation, and average running time) results are compared with seven well-known algorithms like Particle swarm optimization (PSO), Firefly algorithm (FA), Chicken swarm optimization (CSO), Grey wolf optimizer (GWO), Sine cosine algorithm (SCA), and Marine-predators algorithm (MPA), and Archimedes optimization algorithm (AOA). Moreover, the Wilcoxon rank-sum test, Friedman test, and convergence curves of the comparison results are used to prove the superiority of the DSA against other algorithms. The results demonstrate that DSA is a high-performance optimization method in terms of convergence speed and exploration-exploitation balance for solving high-dimension optimization functions. Also, DSA is applied for the optimal design of two constrained engineering problems (the Three-bar truss problem, and the Sawmill operation problem). Additionally, four engineering constraint problems have also been used to analyze the performance of the proposed DSA. Overall, the comparison results revealed that the DSA is a promising and very competitive algorithm for solving different optimization problems.

Road maintenance planning is an integral part of road asset management. One of the main challenges in Maintenance and Rehabilitation (M&R) practices is to determine maintenance type and timing. This research proposes a framework using Reinforcement Learning (RL) based on the Long Term Pavement Performance (LTPP) database to determine the type and timing of M&R practices. A predictive DNN model is first developed in the proposed algorithm, which serves as the Environment for the RL algorithm. For the Policy estimation of the RL model, both DQN and PPO models are developed. However, PPO has been selected in the end due to better convergence and higher sample efficiency. Indicators used in this study are International Roughness Index (IRI) and Rutting Depth (RD). Initially, we considered Cracking Metric (CM) as the third indicator, but it was then excluded due to the much fewer data compared to other indicators, which resulted in lower accuracy of the results. Furthermore, in cost-effectiveness calculation (reward), we considered both the economic and environmental impacts of M&R treatments. Costs and environmental impacts have been evaluated with paLATE 2.0 software. Our method is tested on a hypothetical case study of a six-lane highway with 23 kilometers length located in Texas, which has a warm and wet climate. The results propose a 20-year M&R plan in which road condition remains in an excellent condition range. Because the early state of the road is at a good level of service, there is no need for heavy maintenance practices in the first years. Later, after heavy M&R actions, there are several 1-2 years of no need for treatments. All of these show that the proposed plan has a logical result. Decision-makers and transportation agencies can use this scheme to conduct better maintenance practices that can prevent budget waste and, at the same time, minimize the environmental impacts.

There are two types of people aboard the research vessel Rachel Carson: There's me, quite sick and spending a good amount of time on the deck trying to keep an eye on the bobbing horizon, and there are the scientists minding the remotely operated vehicle dangling below us. Sitting in a chair with a joystick on the armrest, surrounded by glowing monitors in an otherwise darkened room, a pilot guides the SUV-sized robot through a galaxy of life--little fishes, free-swimming crustaceans, jellyfish, and other gelatinous critters that dart out of the way--stopping every so often to cross something off a species shopping list. Scientists with the Monterey Bay Aquarium, and its associated Monterey Bay Aquarium Research Institute, are on a methodical hunt for specimens for a new exhibit, Into the Deep, opening in the spring. It'll be loaded with exceedingly fragile, rarely seen animals kept healthy in life-support systems that aquarists have taken years to perfect. "Some of them we call'wet tissue paper,'" says Wyatt Patry, a senior aquarist, speaking of the species they're seeking.

The applicant must hold a doctoral degree in Artificial Intelligence/Data Mining/Machine Learning/Information Technology or related fields. The applicant needs to demonstrate a strong research profile in the fields related to topics of interest for CAISR research environment, including recent activities with high impact.

Modern neural language models widely used in tasks across NLP risk memorizing sensitive information from their training data. As models continue to scale up in parameters, training data, and compute, understanding memorization in language models is both important from a learning-theoretical point of view, and is practically crucial in real world applications. An open question in previous studies of memorization in language models is how to filter out "common" memorization. In fact, most memorization criteria strongly correlate with the number of occurrences in the training set, capturing "common" memorization such as familiar phrases, public knowledge or templated texts. In this paper, we provide a principled perspective inspired by a taxonomy of human memory in Psychology. From this perspective, we formulate a notion of counterfactual memorization, which characterizes how a model's predictions change if a particular document is omitted during training. We identify and study counterfactually-memorized training examples in standard text datasets. We further estimate the influence of each training example on the validation set and on generated texts, and show that this can provide direct evidence of the source of memorization at test time.

Engineers are developing software for lighter-than-air spacecraft that might be able to explore the clouds of Venus, an environment that could harbour alien life. These hybrid machines use buoyancy and aerodynamic lift to control their altitude – with the substantial benefit that during the day they can collect energy from the Sun in order to move while conserving power by floating during the night. It is hoped that the aerobots would be able to cruise for several months to one year. This buoyancy of the vehicle also means that it would be prevented from descending more than 50 kilometres from the surface of Venus. The temperature of the planet can reach approximately 475 degrees Celsius, and has melted numerous probes sent to it already.

Micro-sized robots could have countless valuable applications, for instance, assisting humans during search-and-rescue missions, conducting precise surgical procedures, and agricultural interventions. Researchers at Massachusetts Institute of Technology (MIT) have recently created a tiny, flying robot based on a class of artificial muscles known as dielectric elastomer actuators (DEAs). This new robot, presented in a paper published in Wiley's Advanced Materials journal, significantly outperformed many DEA-based micro-systems developed in the past. Most notably, the robot can operate at low voltages and has high endurance despite its miniature size. "Our group has a long-term vision of creating a swarm of insect-like robots that can perform complex tasks such as assisted pollination and collective search-and-rescue," Kevin Chen, one of the researchers who carried out the study, told Tech Xplore.