We study fast algorithms for statistical regression problems under the strong contamination model, where the goal is to approximately optimize a generalized linear model (GLM) given adversarially corrupted samples. Prior works in this line of research were based on the robust gradient descent framework of Prasad et. al., a first-order method using biased gradient queries, or the Sever framework of Diakonikolas et. al., an iterative outlier-removal method calling a stationary point finder. We present nearly-linear time algorithms for robust regression problems with improved runtime or estimation guarantees compared to the state-of-the-art. For the general case of smooth GLMs (e.g. logistic regression), we show that the robust gradient descent framework of Prasad et. al. can be accelerated, and show our algorithm extends to optimizing the Moreau envelopes of Lipschitz GLMs (e.g. support vector machines), answering several open questions in the literature. For the well-studied case of robust linear regression, we present an alternative approach obtaining improved estimation rates over prior nearly-linear time algorithms. Interestingly, our method starts with an identifiability proof introduced in the context of the sum-of-squares algorithm of Bakshi and Prasad, which achieved optimal error rates while requiring large polynomial runtime and sample complexity. We reinterpret their proof within the Sever framework and obtain a dramatically faster and more sample-efficient algorithm under fewer distributional assumptions.

Inspired by evidence that pretrained language models (LMs) encode commonsense knowledge, recent work has applied LMs to automatically populate commonsense knowledge graphs (CKGs). However, there is a lack of understanding on their generalization to multiple CKGs, unseen relations, and novel entities. This paper analyzes the ability of LMs to perform generalizable commonsense inference, in terms of knowledge capacity, transferability, and induction. Our experiments with these three aspects show that: (1) LMs can adapt to different schemas defined by multiple CKGs but fail to reuse the knowledge to generalize to new relations. (2) Adapted LMs generalize well to unseen subjects, but less so on novel objects. Future work should investigate how to improve the transferability and induction of commonsense mining from LMs.

Over the past two decades, recommender systems have attracted a lot of interest due to the explosion in the amount of data in online applications. A particular attention has been paid to collaborative filtering, which is the most widely used in applications that involve information recommendations. Collaborative filtering (CF) uses the known preference of a group of users to make predictions and recommendations about the unknown preferences of other users (recommendations are made based on the past behavior of users). First introduced in the 1990s, a wide variety of increasingly successful models have been proposed. Due to the success of machine learning techniques in many areas, there has been a growing emphasis on the application of such algorithms in recommendation systems. In this article, we present an overview of the CF approaches for recommender systems, their two main categories, and their evaluation metrics. We focus on the application of classical Machine Learning algorithms to CF recommender systems by presenting their evolution from their first use-cases to advanced Machine Learning models. We attempt to provide a comprehensive and comparative overview of CF systems (with python implementations) that can serve as a guideline for research and practice in this area.

Human interactions with the physical environment are often mediated through information services, and sometimes depend on them. These human interactions with their environment relate to a range of scales,28 in the scenario here from the "west of the city" to the "back of the store," or beyond the scenario to "the cat is under the sofa." These interactions go far beyond references to places that are recorded in geographic gazetteers,37 both in scale (the place where the cat is) and conceptualization (the place that forms the west of the city29), or that fit to the classical coordinate-based representations of digital maps. And yet, these kinds of services have to use such digital representations of environments, such as digital maps, building information models, knowledge bases, or just text/documents. Also, their abilities to interact are limited to either fusing with the environment,44 or using media such as maps, photos, augmented reality, or voice. These interactions also happen in a vast range of real-world contexts, or in situ, in which conversation partners typically adapt their conversational strategies to their interlocutor, based on mutual information, activities, and the shared situation.2 Verbal information sharing and conversations about places may also be more suitable when visual communication through maps or imagery is inaccessible, distracting, or irrelevant, such as when navigating in a familiar shopping mall.

Scientists in Hong Kong have developed artificial skin that bruises like the real thing. The material, called I-skin, could be used on artificial limbs to alert users they have damaged their prosthetics. It's embedded with a gel that turns from yellow to welt-like purple when subjected to physical stress. Volunteers wearing strips of I-skin on their fingers, hands and knees repeatedly banged the appendage against a wall, proving the'bruise' would appear if enough force was used. Scientists in Hong Kong have developed an artificial skin that will mimic the discoloration of a bruise if hit hard enough.

Data Bridge Market Research published a new report, titled, "Artificial intelligence in medical imaging Market". The report offers an extensive analysis of key growth strategies, drivers, opportunities, key segments, and competitive landscape. This study is a helpful source of information for market players, investors, VPs, stakeholders, and new entrants to gain a thorough understanding of the industry and determine steps to be taken to gain a competitive advantage. Businesses can bring about an absolute knowhow of general market conditions and tendencies with the information and data covered in the large scale Artificial intelligence in medical imaging market survey report. To get knowledge of all the above things, this market report is made transparent, wide-ranging and supreme in quality.

Fighting climate change is both an urgent global imperative and a massive business opportunity. Climate change is the most pressing threat that the human species faces today. Artificial intelligence is the most powerful tool that humanity has at its disposal in the twenty-first century. Can we deploy the second to combat the first? A group of promising startups has emerged to do just that. Both climate change and artificial intelligence are sprawling, cross-disciplinary fields. Both will transform literally every sector of the economy in the years ahead. There is therefore no single "silver bullet" application of AI to climate change. Instead, a wide range of machine learning use cases can help in the race to decarbonize our world. Nearly every major activity that humanity engages in today contributes to our carbon footprint to some extent: building things, moving things, powering things, eating things, computing things.

Welcome back to our "Life in 2050" series! In previous installments, we looked at how accelerating change and environmental issues will affect the future of warfare, economy, education, everyday living, and space exploration (in two installments). Today, we look at how people will get from A to B by mid-century, whether it's across town, from one city to the next, or one continent to the next. Transportation is another sector that is expected to undergo a major revolution in the coming decades. In several respects, this revolution is already underway thanks to the introduction of autonomous vehicles, the wide-scale adoption of electric vehicles, the growth of renewable energy, and the advent of commercial spaceflight. Between now and 2050, these technologies and trends will accelerate and lead to the creation of new transportation infrastructure, radically different from what we know today. Of course, the infrastructure of tomorrow will be built on existing transportation networks.

UCLA Researchers have developed a method to change the apparent race of faces in datasets that are used to train medical machine learning systems, in an attempt to redress the racial bias that many common datasets suffer from. The new technique is capable of producing photorealistic and physiologically accurate synthetic video at an average rate of 0.005 seconds per frame, and is hoped to aid the development of new diagnostics systems for remote healthcare diagnosis and monitoring – a field that has expanded greatly under COVID restrictions. The system is intended to improve the applicability of remote photoplethysmography (rPPG), a computer vision technique that evaluates facial video content to detect volumetric changes in blood supply in a non-invasive manner. Though the work, which utilizes convolutional neural networks (CNNs), incorporates previous research code published by the UK's Durham University in 2020, the new application is intended to preserve pulsatile signals in the original test data, rather than just visually changing the apparent race of the data, as the 2020 research does. The first part of the encoder-decoder system uses the Durham race transfer model, pre-trained on VGGFace2, to generate proxy target frames with the prior Caucasian-to-African component of the Durham research.

Every day across Australia, truckies are driving thousands of kilometres to get fresh produce from farms to markets. But what if the truck could do this job, without a driver? The NASDAQ-listed company TuSimple is celebrating a milestone, after transporting watermelons from Arizona to Oklahoma City using an autonomous truck. There were two humans in the truck during the trial -- and they did take control of the vehicle at the front and back end of the journey -- but for more than 1,500 kilometres, the truck was driving itself. "Our business case is to take the human driver out," TuSimple's Jim Mullen said.