Cloud Hosting

Machine learning and other artificial intelligence (AI) methods have had immense success with scientific and technical tasks such as predicting how protein molecules fold and recognising faces in a crowd. However, the application of these methods to the humanities are yet to be fully explored.

What can AI tell us about philosophy and religion, for example? As a starting point for such an exploration, we used deep learning AI methods to analyse English translations of the Bhagavad Gita, an ancient Hindu text written originally in Sanskrit.

Using a deep learning-based language model called BERT, we studied sentiment (emotions) and semantics (meanings) in the translations. Despite huge variations in vocabulary and sentence structure, we found that the patterns of emotion and meaning were broadly similar in all three.

This research opens a path to the use of AI-based technologies for comparing translations and reviewing sentiments in a wide range of texts.

The Bhagavad Gita is one of the central Hindu sacred and philosophical texts. Written more than 2,000 years ago, it has been translated into more than 100 languages and has been of interest to western philosophers since the 18th century.

The 700-verse poem is a part of the larger Mahabharata epic, which recounts the events of an ancient war believed to have occurred at Kurukshetra near modern-day Delhi in India.

Read more: Indian philosophy helps us see clearly, act wisely in an interconnected world

The text of the Bhagavad Gita relates a conversation between the Hindu deity Lord Krishna and a prince called Arjuna. They discuss whether a soldier should go to war for ethics and duty (or dharma) if they have close friends or family on the opposing side.

The text has been instrumental in laying the foundations of Hinduism. Among many other things, it is where the philosophy of karma (a spiritual principle of cause and effect) originates.

Scholars have also regarded the Bhagavad Gita as a book of psychology, management, leadership and conflict resolution.

There have been countless English translations of the Bhagavad Gita, but there is not much work that validates their quality. Translations of songs and poems not only break rhythm and rhyming patterns, but can also result in the loss of semantic information.

In our research, we used deep learning language models to analyse three selected translations of the Bhagavad Gita (from Sanskrit to English) with semantic and sentiment analyses which help in the evaluation of translation quality.

We used a pre-trained language model known as BERT, developed by Google. We further tuned the model using a human-labelled training dataset based on Twitter posts, which captures 10 different sentiments.

These sentiments (optimistic, thankful, empathetic, pessimistic, anxious, sad, annoyed, denial, surprise, and joking) were adopted from our previous research into social media sentiment during the onset of the COVID-19 pandemic.

The three translations we studied used very different vocabulary and syntax, but the language model recognised similar sentiments in the different chapters of the respective translations. According to our model, optimistic, annoyed and surprised sentiments are the most expressed.

Moreover, the model showed how the overall sentiment polarity changes (from negative to positive) over the course of the conversation between Arjuna and Lord Krishna.

Arjuna is pessimistic towards the beginning and becomes optimistic as Lord Krisha imparts knowledge of Hindu philosophy to him. The sentiments expressed by Krishna show that with philosophical knowledge of dharma and mentorship, a troubled mind can get clarity for making the right decisions in times of conflict.

One limitation of our model is that it was trained on data from Twitter, so it recognises joking as a common sentiment. It applies this label inappropriately to some parts of the Bhagavad Gita. Humour is complicated and strongly culturally constrained, and understanding it is too much to ask of our model at this stage.

Due to the nature of the Sanskrit language, the fact that the Bhagavad Gita is a song with rhythm and rhyme, and the varied dates of the translations, different translators used different vocabulary to describe the same concepts.

The table below shows some of the most semantically similar verses from the three translations.

Our research points the way to the use of AI-based technologies for comparing translations and reviewing sentiments in a wide range of texts.

This technology can also be extended to review sentiments expressed in entertainment media. Another potential application is analysing movies and songs to provide insights to parents and authorities about the suitability of content for children.

The author would like to acknowledge the invaluable contribution of Venkatesh Kulkarni to this research.

Link:
AI, philosophy and religion: what machine learning can tell us about the Bhagavad Gita - The Conversation

SANTA CLARA, Calif.--(BUSINESS WIRE)--Metas VP of Infrastructure Hardware, Alexis Black Bjorlin, will open the flagship AI Hardware Summit with a keynote, while her colleague Vikas Chandra, Metas Director of AI Research will open Edge AI Summit. Other notable keynotes include Microsoft Azures CTO, Mark Russinovich, plus Wells Fargos EVP of Model Risk, Agus Sudjianto; Synopsys President & COO, Sassine Ghazi; Cadences Executive Chairman, Lip-Bu Tan; and Siemens EVP, IC EDA, Joseph Sawicki, among many others

Machine learning and deep learning are fast becoming major line items on agendas in board rooms in every organization across the globe. The technology stack needed to support these workloads, and to execute them quickly, efficiently, and affordably, is fast developing in both the datacenter and in client systems at the edge.

In 2018, a new Silicon Valley event called the AI Hardware Summit launched to provide a platform to discuss innovations in hardware necessary for supporting machine learning both at the very large scale, and in small resource-constrained environments. The event attracted enormous interest from the semiconductor and systems sectors, welcomed Habana Labs into the industry in its inaugural year, and subsequently hosted Alphabet Inc.s Chairman and Turing Award Winner, John L. Hennessy, as a keynote speaker in 2019. Shortly after, the Edge AI Summit was launched to focus specifically on deploying machine learning in commercial use cases in client systems.

Hennessy said of the AI Hardware Summit: Its a great place where lots of people interested in AI Hardware are coming together and exchanging ideas, and together we make the technology better. Theres a synergistic effect at these summits which is really amazing and powers the entire industry.

Fast forward a few years of virtual shows and the events are back in-person with a fresh angle. An all-star cast of tech visionary speakers will address optimizing and accelerating machine learning hardware and software, focusing on the intersection between systems design and ML development. Developer workshops with HuggingFace are a new feature this year focused on helping bring new hardware innovation into leading enterprises.

The co-location of the two industry-leading summits combines the proposition to focus on building, optimizing and unifying software-defined ML platforms across the cloud-edge continuum. Attendees of the AI Hardware Summit can expect content spanning from hardware and infrastructure up to models/applications, whereas the Edge AI Summit has a much tighter focus on case studies of ML in enterprise.

This years audience will consist of machine learning practitioners and technology builders from various engineering disciplines, discussing topics such as systems-first ML, AI acceleration as a full-stack endeavour, software defined systems co-design, boosting developer efficiency, optimizing applications across diverse ML platforms and bringing state of the art production performance into the enterprise.

While the AI Hardware Summit has broadened its scope beyond focusing purely on hardware, there will still be plenty for hardware-focused attendees to explore. The event website, http://www.aihardwaresummit.com, gives accessible information on why a software-focused or hardware-focused attendee should register.

The Edge AI Summit features more end user use cases than any other event of its kind, and is a must attend for anyone moving ML workloads to the edge. The event website, http://www.edgeaisummit.com, gives more information.

Read the original:
Tech Visionaries to Address Accelerating Machine Learning, Unifying AI Platforms and Taking Intelligence to the Edge, at the Fifth Annual AI Hardware...

Study design and participants

This retrospective study involved the UK Biobank cohort12. UK Biobank consists of approximately 500,000 people now aged 50 to 84years (mean age=69.4years). Baseline data was collected in 20062010 at 22 centers across the United Kingdom13,14. Summary data are listed in Table 1. This research involved deidentified epidemiological data. All UK Biobank participants gave written, informed consent. Ethics approval for the UK Biobank study was obtained from the National Health Service Health Research Authority North WestHaydock Research Ethics Committee (16/NW/0274), in accordance with relevant guidelines and regulations from the Declarations of Helsinki. All analyses were conducted in line with UK Biobank requirements.

The following categories of predictors were downloaded: (1) demographics; (2) health behaviors and long-term disability or illness status; (3) anthropometric and bioimpedance measures of fat, muscle, or water content; (4) pulse and blood pressure; (5) a serum panel of thirty biochemistry markers commonly collected in a clinic or hospital setting; and (6) a complete blood count with a manual differential.

These factors included participant age in years at baseline, sex, education qualifications, ethnicity, and Townsend Deprivation Index. Sex was coded as 0 for female and 1 for male. For education, higher scores roughly correspond to progressively more skilled trade/vocational or academic training. Ethnicity was coded as UK citizens who identified as White, Black/Black British, or Asian/Asian British. The Townsend index15 is a standardized score indicating relative degree of deprivation or poverty based on permanent address.

This category consisted of self-reported alcohol status, smoking status, a subjective health rating on a 14 Likert scale (Excellent to Poor), and whether the participant had a self-described long-term medical condition. As noted in Table 1, 48.4% of participants indicated having such an ailment. We independently confirmed self-reported data with ICD-10 codes while at hospital. These conditions included all-cause dementia and other neurological disorders, various cancers, major depressive disorder, cardiovascular or cerebrovascular diseases and events, cardiometabolic diseases (e.g., type 2 diabetes), renal and pulmonary diseases, and other so-called pre-existing conditions.

The first automated reading of pulse, diastolic and systolic blood pressure at the baseline visit were used.

Anthropometric measures of adiposity (Body Mass Index, waist circumference) were derived as described16. Data also included bioelectrical impedance metrics that estimate central body cavity (i.e., trunk) and whole body fat mass, fat-free muscle mass, or water content17.

Serum biomarkers were assayed from baseline samples as described18. Briefly, using immunoassay or clinical chemistry devices, spectrophotometry was used to initially quantify values for 34 biochemistry analytes. UK Biobank deemed 30 of these markers to be suitably robust. We rejected a further 4 markers due data missingness>70% (estradiol, rheumatoid factor), or because there was strong overlap with multicollinear variables that had more stable distributions or trait-like qualities (glucose rejected vs. glycated hemoglobin/hba1c; direct bilirubin rejected vs. total bilirubin). A complete blood count with a manual differential was separately processed for red and white blood cell counts, as well as white cell sub-types.

As described (http://biobank.ctsu.ox.ac.uk/crystal/crystal/docs/infdisease.pdf), among 9695 randomized UK Biobank participants selected from the full 500,000 participant cohort, baseline serum was thawed and pathogen-specific assays run in parallel using flow cytometry on a Luminex bead platform19.

Here, the goal of the multiplex serology panel was to measure multiple antibodies against several antigens for different pathogens, reducing noise and estimating the prevalence of prior infection and seroconversion in at least UK Biobank. All measures were initially confirmed in serum samples using gold-standard assays with median sensitivity and specificity of 97.0% and 93.7%, respectively. Antibody load for each pathogen-specific antigen was quantified using median fluorescence intensity (MFI). Because seropositivity is difficult to assess for several pathogens, we did not use pathogen prevalence as a predictor in models.

Table 2 shows the selected pathogens, their respective antigens, estimated prevalence of each pathogen based roughly on antibody titers, and assay values. This array ranges from delta-type retroviruses like human T-cell lymphotropic virus 1 that are rare (<1%) to human herpesviruses 6 and 7 that have an estimated prevalence of more than 90%.

Our study was based on COVID PCR test data available from March 16th to May 19th 2020. Specifically, we used the May 26th, 2020 tranche of COVID-19 polymerase chain reaction (PCR) data from Public Health England. There were 4510 unique participants that had 7539 individual tests administered, hereafter called test cases. To characterize each test case, UK Biobank had a binary variable for test positivity (result) and a separate binary variable for test location (origin). For the positivity variable, a COVID-19 test was coded as negative (0) or positive (1). The second binary variable represented whether the COVID-19 test occurred through a setting that was out-patient (0) or in-patient at hospital (1). As a proxy for COVID-19 severity later verified by electronic health records and death certificates20, and as done in other UK Biobank reports21, a test case first needed to be positive for COVID-19 (i.e., the test had a 1 value for the positivity variable). Next, if the positive test case occurred in an out-patient setting the infection was considered mild (i.e., 0), whereas for in-patient hospitalization it was considered severe (i.e., 1). Thus, two separate sets of analyses were run to predict: (1) COVID-19 positivity; and (2) COVID-19 severity.

For a more technical description of the specific machine learning algorithm used to predict test case outcomes, see Supplementary Text 1. Supplementary Text 2 has an in-depth description and analysis of within-subject variation for outcome measures and number of test cases done per participant. Briefly, this variability was modest and had no significant impact on classifier model performance. SPSS 27 was used for all analyses and Alpha set at 0.05. Preliminary findings suggested that baseline serology data performed well in classifier models, despite a limited number of participants with serology. To determine if this serology sub-group was noticeably different from the full sample, MannWhitney U and KruskalWallis tests were done (Alpha=0.05). Hereafter, separate sets of classification analyses were performed for: (1) the full cohort; and (2) the sub-group of participants that had serology data. In other words, due to the imbalance of sample sizes and by definition the absence or presence of serology data, classifier performance in the serology sub-group was never statistically compared to the full cohort.

Next, linear discriminant analysis (LDA) was used in two separate sets of analyses to predict either: (1) COVID-19 diagnosis (negative vs. positive); or (2) COVID-19 infection severity (mild vs. severe). Again, for a given test case, COVID-19 severity would be examined only among participants who tested positive for COVID-19. LDA is a regression-like classification technique that finds the best linear combination of predictors that can maximally distinguish between groups of interest. To determine how useful a given predictor or related group of predictors (e.g., demographics) were for classification, simple forced entry models were first done. Subsequently, to derive best fit, robust models of the data, stepwise entry (Wilks Lambda, F value entry=3.84) was used to exclude predictors that did not significantly account for unique variance in the classification model. This data reduction step is critical because LDA can lead to model overfitting when there are too many predictors relative to observations22,23, which are COVID-19 test cases for our purposes. Finally, because there were multiple test cases that could occur for the same participant, this would violate the assumption of independence. To guard against this problem, we used Mundry and Sommers permutation LDA approach. Specifically, for each LDA model, permutation testing (1000 iterations, P<0.05) was done by randomizing participants across groupings of test cases to confirm robustness of the original model24.

LDA model overfitting can also occur when there is a sample size imbalance. Because there were many more negative vs. positive COVID-19 test cases in the full sample (5329 vs. 2210), the negative test group was undersampled. Specifically, a random number generator was used to discard 2500 negative test cases at random, such that the proportion of negative to positive tests was now 55% to 45% instead of 70.6 to 29.4%. Results without undersampling were similar (data not shown). No such imbalance was seen for COVID-19 severity in the full sample or for the serology sub-group. A typical holdout method of 70% and 30% was used for classifier training and then testing25. Finally, a two-layer non-parametric approach was used to determine model significance and estimated fit of one or more predictors. First, bootstrapping26 (95% Confidence Interval, 1000 iterations) was done to derive estimates robust against any violations of parametric assumptions. Next, leave-one-out cross-validation22 was done with bootstrap-derived estimates to ensure that models themselves were robust. Collectively, the stepwise LDA models ensured that estimation bias of coefficients would be low because most predictors are thrown out before models are generated using the remaining predictors.

For each LDA classification model, outcome threshold metrics included: specificity (i.e., true negatives correctly identified), sensitivity (i.e., true positives correctly identified), and the geometric mean (i.e., how well the model predicted both true negatives and positives). The area under the curve (AUC) with a 95% confidence interval (CI) was reported to show how well a given model could distinguish between a COVID-19 negative or positive test result, and separately for COVID-19+test cases if the disease was mild or severe. Receiver operating characteristic (ROC) curves plotted sensitivity against 1-specificity to better visualize results for sets of predictors and a final stepwise model. For stepwise models, the Wilks Lambda statistic and standardized coefficients are reported to see how important a given predictor was for the model. A lower Wilks Lambda corresponds to a stronger influence on the canonical classifier.

Ethics approval for the UK Biobank study was obtained from the National Health Service Health Research Authority North WestHaydock Research Ethics Committee (16/NW/0274). All analyses were conducted in line with UK Biobank requirements.

See the rest here:
Using machine learning to predict COVID-19 infection and severity risk among 4510 aged adults: a UK Biobank cohort study | Scientific Reports -...

Collaboration will enable AI-powered decentralized clinical trials

BOSTON, May 10, 2022 /PRNewswire/ -- Beacon Biosignals, which applies AI to EEG to unlock precision medicine for brain conditions,today announced a partnership with Stratus Research Labs, the nation's leading provider of EEG services, to enable expanded clinical trial service capabilities by leveraging Beacon's machine learning neuroanalytics platform.

EEG is standard of care in the clinical diagnosis and management of many neurologic diseases and sleep disorders, yet features of clinical significance often are difficult to extract from EEG data. Broader adoption of EEG technology has been further limited by labor-intensive workflows and variability in clinician expert interpretation. By linking their platforms, Beacon and Stratus will unlock AI-powered at-home clinical trials, addressing these challenges head-on.

"The benefits of widely incorporating EEG data into pharmaceutical trials has been desired for years, but the challenge of uniformly capturing and interpreting the data has been an issue," said Charlie Alvarez, chief executive officer for Stratus. "Stratus helps solve data capture issues by providing accessible, nationwide testing services that reduce the variability in data collection and help ensure high-quality data across all sites. Stratus is proud to partner with Beacon and its ability to complete the equation by providing algorithms to ensure the quality of EEG interpretations."

Stratus offers a wide variety of EEG services, including monitored long-term video studies and routine EEGs conducted in the hospital, clinic, and in patients' homes. Stratus has a strong track record of high-quality data acquisition, enabled by an industry-leading pool of registered EEG technologists and a national footprint for EEG deployment logistics. The announced agreement establishes Stratus as a preferred data acquisition partner for Beacon's clinical trial and neurobiomarker discovery efforts using Beacon's analytics platform.

"Reliable and replicable quantitative endpoints help drive faster, better-powered trials," said Jacob Donoghue, MD, PhD, co-founder of Beacon Biosignals. "A barrier to their development, along with performing the necessary analysis, can often be the acquisition of quality EEG at scale. Partnering with Stratus and benefiting from its infrastructure and platform eliminates that hurdle and paves the way toward addressing the unmet need for endpoints, safety tools and computational diagnostics."

Beacon's platform provides an architectural foundation for discovery of robust quantitative neurobiomarkers that subsequently can be deployed for patient stratification or automated safety or efficacy monitoring in clinical trials. The powerful and validated algorithms developed by Beacon's machine learning teams can replicate the consensus interpretation of multiple trained epileptologists while exceeding human capabilities over many hours or days of recording. These algorithms can be focused on therapeutic areas such as neurodegenerative disorders, epilepsy, sleep disorders and mental illness.For example, Beacon is currently assessing novel EEG signatures in Alzheimer's disease patients to identify which patients may or may not benefit from a specific type of therapy.

"This collaboration will enable at-home studies for diseases like Alzheimer's," Donoghue said. "It has traditionally been difficult to obtain clinical-grade EEG for these patients at the scale required for phase 3 and phase 4 clinical trials. Stratus' extensive expertise in scaling EEG operations in at-home settings unlocks real opportunities to harness brain data to evaluate treatment efficacy."

About Beacon BiosignalsBeacon's machine learning platform for EEG enables and accelerates new treatments that transform the lives of patients with neurological, psychiatric or sleep disorders. Through novel machine learning algorithms, large clinical datasets, and advances in software engineering, Beacon Biosignals empowers biopharma companies with unparalleled tools for efficacy monitoring, patient stratification, and clinical trial endpoints from brain data. For more information, visit https://beacon.bio/. For careers, visit https://beacon.bio/careers; for partnership inquiries, visit https://beacon.bio/contact. Follow us on Twitter (@Biosignals) or LinkedIn (https://www.linkedin.com/company/beacon-biosignals).

About StratusStratus is the nation's leading provider of EEG solutions, including ambulatory in-home video EEG. The company has served more than 80,000 patients across the U.S. Stratus offers technology, services, and proprietary software solutions to help neurologists accurately and quickly diagnose their patients with epilepsy and other seizure-like disorders. Stratus also provides mobile cardiac telemetry to support the diagnostic testing needs of the neurology community. To learn more, visit http://www.stratusneuro.com.

MEDIA CONTACTMegan MoriartyAmendola Communications for Beacon Biosignals913.515.7530mmoriarty@acmarketingpr.com

View original content to download multimedia:https://www.prnewswire.com/news-releases/beacon-biosignals-announces-partnership-with-stratus-to-advance-at-home-brain-monitoring-and-machine-learning-enabled-neurodiagnostics-301543440.html

SOURCE Beacon Biosignals

Excerpt from:
Beacon Biosignals announces partnership with Stratus to advance at-home brain monitoring and machine learning-enabled neurodiagnostics - BioSpace