Cloud Hosting

For more than 30 years, the models that researchers and government agencies use to forecast earthquake aftershocks have remained largely unchanged. While these older models work well with limited data, they struggle with the huge seismology datasets that are now available.

To address this limitation, a team of researchers at the University of California, Santa Cruz and the Technical University of Munich created a new model that uses deep learning to forecast aftershocks: the Recurrent Earthquake foreCAST (RECAST). In a paper published today in Geophysical Research Letters, the scientists show how the deep learning model is more flexible and scalable than the earthquake forecasting models currently used.

The new model outperformed the current model, known as the Epidemic Type Aftershock Sequence (ETAS) model, for earthquake catalogs of about 10,000 events and greater.

The ETAS model approach was designed for the observations that we had in the 80s and 90s when we were trying to build reliable forecasts based on very few observations, said Kelian Dascher-Cousineau, the lead author of the paper who recently completed his PhD at UC Santa Cruz. Its a very different landscape today. Now, with more sensitive equipment and larger data storage capabilities, earthquake catalogs are much larger and more detailed

Weve started to have million-earthquake catalogs, and the old model simply couldnt handle that amount of data, said Emily Brodsky, a professor of earth and planetary sciences at UC Santa Cruz and co-author on the paper. In fact, one of the main challenges of the study was not designing the new RECAST model itself but getting the older ETAS model to work on huge data sets in order to compare the two.

The ETAS model is kind of brittle, and it has a lot of very subtle and finicky ways in which it can fail, said Dascher-Cousineau. So, we spent a lot of time making sure we werent messing up our benchmark compared to actual model development.

To continue applying deep learning models to aftershock forecasting, Dascher-Cousineau says the field needs a better system for benchmarking. In order to demonstrate the capabilities of the RECAST model, the group first used an ETAS model to simulate an earthquake catalog. After working with the synthetic data, the researchers tested the RECAST model using real data from the Southern California earthquake catalog.

They found that the RECAST model which can, essentially, learn how to learn performed slightly better than the ETAS model at forecasting aftershocks, particularly as the amount of data increased. The computational effort and time were also significantly better for larger catalogs.

This is not the first time scientists have tried using machine learning to forecast earthquakes, but until recently, the technology was not quite ready, said Dascher-Cousineau. New advances in machine learning make the RECAST model more accurate and easily adaptable to different earthquake catalogs.

The models flexibility could open up new possibilities for earthquake forecasting. With the ability to adapt to large amounts of new data, models that use deep learning could potentially incorporate information from multiple regions at once to make better forecasts about poorly studied areas.

We might be able to train on New Zealand, Japan, California and have a model that's actually quite good for forecasting somewhere where the data might not be as abundant, said Dascher-Cousineau.

Using deep-learning models will also eventually allow researchers to expand the type of data they use to forecast seismicity.

Were recording ground motion all the time, said Brodsky. So the next level is to actually use all of that information, not worry about whether were calling it an earthquake or not an earthquake but to use everything."

In the meantime, the researchers hope the model sparks discussions about the possibilities of the new technology.

It has all of this potential associated with it, said Dascher-Cousineau. Because it is designed that way.

Read the original post:
Seismologists use deep learning to forecast earthquakes - University of California, Santa Cruz

Researchers have improved deep learning by selecting the most efficient overall path to the output, leading to a more effective AI without added layers.

Like climbing a mountain via the shortest possible path, improving classification tasks can be achieved by choosing the most influential path to the output, and not just by learning with deeper networks.

Deep Learning (DL) performs classification tasks using a series of layers. To effectively execute these tasks, local decisions are performed progressively along the layers. But can we perform an all-encompassing decision by choosing the most influential path to the output rather than performing these decisions locally?

In an article published today (August 31) in the journal Scientific Reports, researchers from Bar-Ilan University in Israel answer this question with a resounding yes. Pre-existing deep architectures have been improved by updating the most influential paths to the output.

Like climbing a mountain via the shortest possible path, improving classification tasks can be achieved by training the most influential path to the output, and not just by learning with deeper networks. Credit: Prof. Ido Kanter, Bar-Ilan University

One can think of it as two children who wish to climb a mountain with many twists and turns. One of them chooses the fastest local route at every intersection while the other uses binoculars to see the entire path ahead and picks the shortest and most significant route, just like Google Maps or Waze. The first child might get a head start, but the second will end up winning, said Prof. Ido Kanter, of Bar-Ilans Department of Physics and Gonda (Goldschmied) Multidisciplinary Brain Research Center, who led the research.

This discovery can pave the way for better enhanced AI learning, by choosing the most significant route to the top, added Yarden Tzach, a PhD student and one of the key contributors to this work.

This exploration of a deeper comprehension of AI systems by Prof. Kanter and his experimental research team, led by Dr. Roni Vardi, aims to bridge between the biological world and machine learning, thereby creating an improved, advanced AI system. To date they have discovered evidence for efficientdendriticadaptationusingneuronal cultures, as well as how toimplement those findingsin machine learning, showing howshallow networkscan compete with deep ones, and finding themechanism underlying successful deep learning.

Enhancing existing architectures using global decisions can pave the way for improved AI, which can improve its classification tasks without the need for additional layers.

Reference: Enhancing the accuracies by performing pooling decisions adjacent to the output layer 31 August 2023, Scientific Reports.DOI: 10.1038/s41598-023-40566-y

Read more:
Smarter AI: Choosing the Best Path to Optimal Deep Learning - SciTechDaily

Development of an ML prediction model involves a multi-step process [11]. Briefly, labeled data are partitioned into training and test subsets. The data subsets undergo preprocessing to minimize the impact of dataset anomalies (e.g., missing values, outliers, redundant features) on the algorithms learning process. The algorithm is applied to the training data, learning the relationship between the features and predictive target. Performance is typically evaluated via cross-validation to estimate the models performance on new observations (internal validation). However, this only approximates a models ability to generalize to unseen data. Prediction models must demonstrate the ability to generalize to independent datasets (external validation) [12]. Ideally, external validation should occur in a separate study by a different analytic team [13]. Clinical validation involves assessing a models generalization to real world data as well as potential clinical utility and impact. Randomized cluster trials, for instance, evaluate groups of patients randomly assigned to receive care based on a models prediction versus care-as-usual.

Few examples exist of predictive ML models advancing to clinical validation in psychiatry, indicative of a sizeable translational gap. Delgadillo et al. compared the efficacy and cost of stratified care compared to stepped care for a psychological intervention for depression (n=951 patients) in a cluster randomized trial [14]. The investigators previously developed a ML prediction model to classify patients as standard or complex cases using self-reported measures and sociodemographic information extracted from clinical records (n=1512 patients) [15]. In the prospective trial, complex cases were matched to high-intensity treatment and standard cases to low-intensity treatment. Stratified care was associated with a 7% increase in the probability of improvement in depressive symptoms at a modest ~$140 increase in cost per patient [14].

What is driving this translational gap? Much of it may relate to challenges in generalizing models beyond their initial training data. There are no silver bullets in the development of ML prediction models and many potential pitfalls. The most common are overfitting and over-optimism due to insufficient training data, excess complexity improper (or lack of) cross-validation, and/or data leakage [16,17,18].

Most published ML studies in psychiatry suffer these methodological flaws [3,4,5]. Tornero-Costa et al. reviewed 153ML applications in mental health and found only one study to be at low risk of bias by the Prediction model Risk Of Bias ASsessment Tool (PROBAST) criteria [3]. Approximately 37.3% of studies used a sample size of 150 or less to train models. Details on preprocessing were completely absent in 36.6% of studies and 47.7% lacked a description of data missingness. Only 13.7% of studies attempted external validation. Flaws in the analysis domain (e.g., attempts to control overfitting and optimism) contributed significantly to bias risk in most applications (90.8%). Furthermore, in 82.3% of the studies, data and developed model were not publicly accessible. Two other systematic reviews also found overall high risk of bias (>90%) among ML prediction studies, including poor reporting of preprocessing steps as well as low rates of internal and external validation [4, 5]. Meehan et al. additionally reported that only 22.7% of studies (of those meeting statistical standards) appropriately embedded feature selection within cross-validation to avoid data leakage [5].

The precise degree to which published ML prediction models overestimate their ability to generalize is difficult to estimate. In the area of prognosis prediction, Rosen et al. assessed 22 published prediction models of transition to psychosis in individuals at clinical high-risk [19]. Models were assessed for external validation from a multisite, naturalistic study. Only two models demonstrated good (AUC>=0.7) performance and 9 models failed to achieve better than chance (AUC=0.5) prediction. None of the models outperformed the clinician raters (AUC=0.75) [19].

The model development process is vulnerable to human inductive biases, which can inflate model performance estimates due to unintentional errors or deliberate gaming for publication [17, 20]. Performance scores have become inappropriately prioritized in peer review due to erroneous higher=better assumptions. Most studies employ a single algorithm without justifying its selection or compare multiple algorithms performance on the same dataset, then select the best performing one (multiple testing issue) [17, 21]. Software packages like PyCaret (Python) offer the ability to screen the performance of a dozen or more algorithms on a dataset in a single step. This analytic flexibility creates risk, because even random data can be tuned to significance solely through manipulation of hyperparameters [17].

Methodological shortcomings offer only partial explanation for the observed translational gap. As the saying goes, garbage in, garbage out. Low quality, small, or biased training data can generate unreliable models with poor generalization to new observations or worse, make unfair predictions that adversely impact patients. Ideal ML training data is large, representative of the population of interest, complete (low missingness), balanced, and possesses accurate and consistent feature and predictive target labels or values (low noise). Per the systematic reviews above, these data quality criteria have been often neglected [3,4,5].

EHR data share many of the same quality issues impacting data collected explicitly for research, as well as some unique challenges that have deterred its use for ML in the past [22,23,24]. EHR data are highly heterogenous, encompassing both structured and unstructured elements. Structured data is collected through predefined fields (e.g., demographics, diagnoses, lab results, medications, sensor readings). Unstructured data is effectively everything else, including imaging and text. Extracting meaningful features from unstructured EHR data is non-trivial and often requires supervised and unsupervised ML techniques.

The quality of EHR data can vary by physician and clinical site. Quality challenges with EHR data that can adversely impact ML models for stratified psychiatry include:

EHR populations are non-random samples, which may create differences between the training data population and the target population [25]. Patients with more severe symptoms or treatment resistance may be frequently referred. Factors other than need for treatment (e.g., insurance status, referral, specialty clinics) can lead to systematic overrepresentation or underrepresentation of certain groups or disorders in the data. Marginalized populations, such as racial and ethnic minorities, for example, face barriers to accessing care and may be absent in the data [26]. When an algorithm trains on data that is not diverse, the certainty of the models predictions is questionable for unrepresented groups (high epistemic uncertainty) [27]. This may lead to unfair predictions (algorithmic bias) [28].

Missing data are common in EHRs. The impacts of missing data on model performance can be severe, especially when the data are missing not at random or missing at random but with a high proportion of missing values [29]. Furthermore, the frequency of records can vary substantially by patient. One individual may have multiple records in a period, others may have none [30]. Does absence of a diagnosis indicate true lack of a disorder or simply reflect that the patient received care elsewhere during a given interval? Structured self-reported patient outcome measures (e.g., psychometric measures) are often missing or incomplete [31].

Feature and target labels or values provide the ground truth for learning. Inaccuracies and missingness generate noise, which can hinder effective learning. The lineage of a given data element is important in considering its reliability and validity. For example, a patients diagnoses may be extracted from clinical notes, encounter/billing data, or problem lists (often not dated or updated) [32]. In some cases, the evaluating practitioner enters the encounter-associated diagnostic codes; in other instances, these are abstracted by a medical billing agent, creating uncertainty.

Imaging and sensor-based data may be collected using different acquisition parameters and equipment, leading to variability in measurements across EHRs and over time [33]. Data may be collected using different coding systems (e.g., DSM, ICD), the criteria for which also change over time. These issues can hinder external validation as well as contribute to data drift with the potential for deterioration in model performance [34].

When data are imbalanced, ML classification models may be more likely to predict the majority class, resulting in a high accuracy but low sensitivity or specificity for the minority class [35]. The consequences of data imbalance can be severe, particularly when the minority class is the most clinically relevant (e.g., patients with suicidal ideation who go on to attempt, adverse drug reactions).

Patient records represent a sequence of events over time [36]. Diagnostic clarification may create conflicts (e.g., depression later revealed to be bipolar disorder), depending on the forward and lookback windows used to create a dataset. Failure to appropriately account for the longitudinal nature of a patients clinical course can contribute to data leakage. Temporal data leakage occurs when future information is inadvertently used to make predictions for past events (e.g., including a future co-morbidity when predicting response to past treatment). Feature leakage occurs when variables expose information about the prediction target.

Empirical evidence indicates that preprocessing techniques can just as easily mitigate as exacerbate underlying data quality and bias issues. For example, missing data may be handled by complete case analysis (i.e., removal of observations with missing features) or imputation [37]. If data are not missing completely at random, deletion may eliminate key individuals [29]. Fernando et al. found that records containing missing data tended to be fairer than complete records and that their removal could contribute to algorithmic bias [38]. In the case of imputation, if the estimated values do not accurately represent the true underlying data, replacing missing values may inject error (e.g., imputing scores for psychometric scale items absent due to skip logic) and impact feature selection [39].

EHR data often require the creation of proxy features and outcomes to capture concepts (e.g., continuous prescription refills as an indicator of treatment effectiveness) or to reduce feature and label noise [40, 41]. No standards currently exist to guide such decisions or their reporting, creating high risk for bias. For example, if attempting to determine cannabis use when a patient was treated with a given antidepressant, one could check for a DSM/ICD diagnosis in their encounters or problem list, mine clinical notes to see whether use was endorsed/denied, or examine urine toxicology for positive/negative results. Each choice carries a different degree of uncertainty. Absence of evidence does not indicate evidence of absence [42], although studies often make that assumption.

See the original post here:
Electronic health records and stratified psychiatry: bridge to ... - Nature.com

Head over to our on-demand library to view sessions from VB Transform 2023. Register Here

Generative AI is gaining wider adoption, particularly in business.

Most recently, for instance, Walmart announced that it is rolling-out a gen AI app to 50,000 non-store employees. As reported by Axios, the app combines data from Walmart with third-party large language models (LLM) and can help employees with a range of tasks, from speeding up the drafting process, to serving as a creative partner, to summarizing large documents and more.

Deployments such as this are helping to drive demand for graphical processing units (GPUs) needed to train powerful deep learning models. GPUs are specialized computing processors that execute programming instructions in parallel instead of sequentially as do traditional central processing units (CPUs).

According to the Wall Street Journal, training these models can cost companies billions of dollars, thanks to the large volumes of data they need to ingest and analyze. This includes all deep learning and foundational LLMs from GPT-4 to LaMDA which power the ChatGPT and Bard chatbot applications, respectively.

VB Transform 2023 On-Demand

Did you miss a session from VB Transform 2023? Register to access the on-demand library for all of our featured sessions.

The gen AI trend is providing powerful momentum for Nvidia, the dominant supplier of these GPUs: The company announced eye-popping earnings for their most recent quarter. At least for Nvidia, it is a time of exuberance, as it seems nearly everyone is trying to get ahold of their GPUs.

Erin Griffiths wrote in the New York Times that start-ups and investors are taking extraordinary measures to obtain these chips: More than money, engineering talent, hype or even profits, tech companies this year are desperate for GPUs.

In his Stratechery newsletter this week, Ben Thompson refers to this as Nvidia on the Mountaintop. Adding to the momentum, Google and Nvidia announced a partnership whereby Googles cloud customers will have greater access to technology powered by Nvidias GPUs. All of this points to the current scarcity of these chips in the face of surging demand.

Does this current demand mark the peak moment for gen AI, or might it instead point to the beginning of the next wave of its development?

Nvidia CEO Jensen Huang said on the companys most recent earnings call that this demand marks the dawn of accelerated computing. He added that it would be wise for companies to divert the capital investment from general purpose computing and focus it on generative AI and accelerated computing.

General purpose computing is a reference to CPUs that have been designed for a broad range of tasks, from spreadsheets to relational databases to ERP. Nvidia is arguing that CPUs are now legacy infrastructure, and that developers should instead optimize their code for GPUs to perform tasks more efficiently than traditional CPUs.

GPUs can execute many calculations simultaneously, making them perfectly suited for tasks like machine learning (ML), where millions of calculations are performed in parallel. GPUs are also particularly adept at certain types of mathematical calculations such as linear algebra and matrix manipulation tasks that are fundamental to deep learning and gen AI.

However, other classes of software (including most existing business applications), are optimized to run on CPUs and would see little benefit from the parallel instruction execution of GPUs.

Thompson appears to hold a similar view: My interpretation of Huangs outlook is that all of these GPUs will be used for a lot of the same activities that are currently run on CPUs; that is certainly a bullish view for Nvidia, because it means the capacity overhang that may come from pursuing generative AI will be backfilled by current cloud computing workloads.

He continued: That noted, Im skeptical: Humans and companies are lazy, and not only are CPU-based applications easier to develop, they are also mostly already built. I have a hard time seeing what companies are going to go through the time and effort to port things that already run on CPUs to GPUs.

Matt Assay of InfoWorld reminds us that we have seen this before. When machine learning first arrived, data scientists applied it to everything, even when there were far simpler tools. As data scientist Noah Lorang once argued, There is a very small subset of business problems that are best solved by machine learning; most of them just need good data and an understanding of what it means.'

The point is, accelerated computing and GPUs are not the answer for every software need.

Nvidia had a great quarter, boosted by the current gold-rush to develop gen AI applications. The company is naturally ebullient as a result. However, as we have seen from the recent Gartner emerging technology hype cycle, gen AI is having a moment and is at the peak of inflated expectations.

According to Singularity University and XPRIZE founder Peter Diamandis, these expectations are about seeing future potential with few of the downsides. At that moment, hype starts to build an unfounded excitement and inflated expectations.

To this very point, we could soon reach the limits of the current gen AI boom. As venture capitalists Paul Kedrosky and Eric Norlin of SK Ventures wrote on their firms Substack: Our view is that we are at the tail end of the first wave of large language model-based AI. That wave started in 2017, with the release of the [Google] transformers paper (Attention is All You Need), and ends somewhere in the next year or two with the kinds of limits people are running up against.

Those limitations include the tendency to hallucinations, inadequate training data in narrow fields, sunsetted training corpora from years ago, or myriad other reasons. They add: Contrary to hyperbole, we are already at the tail end of the current wave of AI.

To be clear, Kedrosky and Norlin are not arguing that gen AI is at a dead-end. Instead, they believe there needs to be substantial technological improvements to achieve anything better than so-so automation and limited productivity growth. The next wave, they argue, will include new models, more open source, and notably ubiquitous/cheap GPUs which if correct may not bode well for Nvidia, but would benefit those needing the technology.

As Fortune noted, Amazon has made clear its intentions to directly challenge Nvidias dominant position in chip manufacturing. They are not alone, as numerous startups are also vying for market share as are chip stalwarts including AMD. Challenging a dominant incumbent is exceedingly difficult. In this case, at least, broadening sources for these chips and reducing prices of a scarce technology will be key to developing and disseminating the next wave of gen AI innovation.

The future for gen AI appears bright, despite hitting a peak of expectations existing limitations of the current generation of models and applications. The reasons behind this promise are likely several, but perhaps foremost is a generational shortage of workers across the economy that will continue to drive the need for greater automation.

Although AI and automation have historically been viewed as separate, this point of view is changing with the advent of gen AI. The technology is increasingly becoming a driver for automation and resulting productivity. Workflow company Zapier co-founder Mike Knoop referred to this phenomenon on a recent Eye on AI podcast when he said: AI and automation are mode collapsing into the same thing.

Certainly, McKinsey believes this. In a recent report they stated: generative AI is poised to unleash the next wave of productivity. They are hardly alone. For example, Goldman Sachs stated that gen AI could raise global GDP by 7%.

Whether or not we are at the zenith of the current gen AI, it is clearly an area that will continue to evolve and catalyze debates across business. While the challenges are significant, so are the opportunities especially in a world hungry for innovation and efficiency. The race for GPU domination is but a snapshot in this unfolding narrative, a prologue to the future chapters of AI and computing.

Gary Grossman is senior VP of the technology practice at Edelman and global lead of the Edelman AI Center of Excellence.

Welcome to the VentureBeat community!

DataDecisionMakers is where experts, including the technical people doing data work, can share data-related insights and innovation.

If you want to read about cutting-edge ideas and up-to-date information, best practices, and the future of data and data tech, join us at DataDecisionMakers.

You might even considercontributing an articleof your own!

Read More From DataDecisionMakers

Continued here:
Generative AI at an inflection point: What's next for real-world ... - VentureBeat