Collaborating Authors


Intel Lab Transforms Your Phone into a Robot for $50


Have you ever dreamed of owning a personal robot? Boston Dynamic's doglike Spot would be a great choice were it not for the hefty US$74,500 price tag. But don't worry -- a couple of Intel Labs researchers have proposed a novel method for building a robot called "OpenBot" on just a US$50 budget. Complete design and implementation information has been open-sourced, all you need to supply is the brain and sensory system -- your smartphone. Inspired by projects such as Google Cardboard that plug standard smartphones into cheap physical enclosures, the researchers developed and validated a design for a mobile robot that leverages a smartphone for sensory and computational abilities, communication channels and access to a software ecosystem. The robot is capable of mobile navigation with real-time onboard sensing and computation, and can perform tasks such as person-following and real-time autonomous navigation in unstructured environments.

Implement Artificial Intelligence using Artificial Intelligence – IAM Network


Transforming a business into one controlled by Artificial Intelligence (AI) requires everybody's interest and commitment. Despite the fact that transformation requires significant investment, various strategies can start democratizing AI immediately. It has often been said that crises uncover real character, both in people and in companies. Crises force companies to reevaluate how they work and are often the source of enduring change and development. The Covid-19 pandemic is a humanitarian crisis more huge than any recently experienced.

IBM Joins Effort by UN and Vatican to Use Ethical AI in Fight Against Hunger


The Vatican's Pontifical Academy for Life, which began the year by urging the ethical development and application of artificial intelligence (AI), has announced an effort to use technology to fight world hunger, which has worsened during the pandemic. The Vatican institution, in collaboration with IBM, Microsoft and the UN Food and Agriculture Organization, or FAO, is encouraging governments, nonprofits and corporations to assure that technology is used to feed everyone, and to make farmers' lives more efficient and productive. In its quest to assure the transparent, responsible and inclusive use of AI, the Vatican and FAO are pushing for solutions in agriculture that will benefit not just the well off, but also the poor. "We need to face the biggest challenges on the planet," said John E. Kelly III, executive vice president of IBM. Kelly, who participated in the FAO and Pontifical Academy's Sept. 24 virtual conference announcing the effort against hunger, was one of the signers of the Vatican's call for AI ethics in February. The Vatican's effort to promote ethical AI for social good includes a new program to use digital technology to ensure a more sustainable and efficient global food supply.

Machine learning approaches classify clinical malaria outcomes based on haematological parameters


Background: Malaria is still a major global health burden, with more than 3.2 billion people in 91 countries remaining at risk of the disease. Accurately distinguishing malaria from other diseases, especially uncomplicated malaria (UM) from non-malarial infections (nMI) remains a challenge. Furthermore, the success of rapid diagnostic tests (RDT) is threatened by Pfhrp2/3 deletions and decreased sensitivity at low parasitemia. Analysis of haematological indices can be used to support identification of possible malaria cases for further diagnosis, especially in travelers returning from endemic areas. As a new application for precision medicine, we aimed to evaluate machine learning (ML) approaches that can accurately classify nMI, UM and severe malaria (SM) using haematological parameters.

Microsoft unveils updates across Azure Cognitive Services and Azure Machine Learning


During its Ignite 2020 conference, which kicked off virtually this morning, Microsoft announced updates to Azure Cognitive Services and Azure Machine Learning aimed at streamlining business processes during the coronavirus pandemic. The company also launched two features in Azure Cognitive Search -- Private Endpoints and Managed Identities -- plus enhancements to Bot Framework Composer and the broader Azure Bot Service. "We're seeing AI touching every business across the planet, and so one of the key focuses we have with Azure Machine Learning is to provide our customers with the tools to really simplify the ability to create new models because we know they're going to need them in every area of their business," Microsoft corporate vice president Eric Boyd told VentureBeat in a phone interview. "This continues to be a key theme for us -- how we will really help our customers, enable more of their developers, and even more of their data analysts to build machine learn models and apply them in all aspects of their business." Private Endpoints in Cognitive Search, which is generally available as of today, allow a client on a virtual network to access data in an index over a private link.

French virus testing labs under strain amid resurgent demand

Associated Press

France's COVID-19 resurgence is palpable in the buzzing biology lab of this public hospital in the Paris suburb of Argenteuil. Tube after tube arrive with new nasal swabs, now about 240 per day. And the lab director struggles to obtain enough reagents to keep up with escalating demand. More than 1 million of France's 67 million people took a virus test over the past week, putting labs like this under growing strain. Getting a virus test in Paris this month has involved long waits, both to be tested and to receive the result, complicating authorities' efforts to trace the epidemic in real time. "Since Aug. 15, we're seeing a constant increase in the number of positive patients," Laurence Courdavault, head of the Argenteuil hospital's medical biology department, said Friday.

A machine learning approach to define antimalarial drug action from heterogeneous cell-based screens


Drug resistance threatens the effective prevention and treatment of an ever-increasing range of human infections. This highlights an urgent need for new and improved drugs with novel mechanisms of action to avoid cross-resistance. Current cell-based drug screens are, however, restricted to binary live/dead readouts with no provision for mechanism of action prediction. Machine learning methods are increasingly being used to improve information extraction from imaging data. These methods, however, work poorly with heterogeneous cellular phenotypes and generally require time-consuming human-led training. We have developed a semi-supervised machine learning approach, combining human- and machine-labeled training data from mixed human malaria parasite cultures. Designed for high-throughput and high-resolution screening, our semi-supervised approach is robust to natural parasite morphological heterogeneity and correctly orders parasite developmental stages. Cell-based screens have substantially advanced our ability to find new drugs (1). However, most screens are unable to predict the mechanism of action (MoA) of identified hits, necessitating years of follow-up after discovery. In addition, even the most complex screens frequently find hits against cellular processes that are already targeted (2).

Artificial Intelligence (AI) In Fintech Market Growth by Top Companies, Region, Application, Driver, Trends and Forecasts by 2027 – Crypto Daily


The Artificial Intelligence (AI) In Fintech Market report predicts promising growth and development during the period 2020-2027. The Artificial Intelligence (AI) In Fintech Market survey report represents vital statistical data represented in an organized format such as graphs, charts, tables, and figures to provide a detailed understanding of the Artificial Intelligence (AI) In Fintech Market in a simple manner. The report covers an in-depth analysis of the Artificial Intelligence (AI) In Fintech market and offers key insights on current and emerging trends, market drivers, and market insights offered by industry experts. The report examines the impact of COVID-19 on market growth. The study provides comprehensive coverage of the impact of the COVID-19 pandemic on the Artificial Intelligence (AI) In Fintech market and its key segments.

Face-mask recognition has arrived--for better or worse


Critics of mask recognition also think that this new technology could be prone to some of the same pitfalls as facial recognition. Many of the training datasets used for facial recognition are dominated by light-skinned individuals. In 2019 Joy Buolamwini, a researcher at the Massachusetts Institute of Technology's Media Lab, and the AI Now Institute's Deborah Raji investigated the accuracy of commercially available datasets used by major tech companies. When they checked the performance of recognition systems using an algorithm trained with the standard datasets, and then using a new set of faces with much more racial and ethnic balance, the researchers found that the algorithm was less than 70 percent accurate in identifying new faces.

Facebook AI Wav2Vec 2.0: Automatic Speech Recognition From 10 Minute Sample


Speech-to-text applications have never been so plentiful, popular or powerful, with researchers' pursuit of ever-better automatic speech recognition (ASR) system performance bearing fruit thanks to huge advances in machine learning technologies and the increasing availability of large speech datasets. Current speech recognition systems require thousands of hours of transcribed speech to reach acceptable performance. However, a lack of transcribed audio data for the less widely spoken of the world's 7,000 languages and dialects makes it difficult to train robust speech recognition systems in this area. To help ASR development for such low-resource languages and dialects, Facebook AI researchers have open-sourced the new wav2vec 2.0 algorithm for self-supervised language learning. The paper Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations claims to "show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler." A Facebook AI tweet says the new algorithm can enable automatic speech recognition models with just 10 minutes of transcribed speech data.