In this GitHub we fine tune a bert model from HuggingFace on review data like Yelp reviews.

The objective of this GitHub is to simulate a simple use case of Machine Learning in IRIS :
We have an IRIS Operation that, on command, can fetch data from the IRIS DataBase to train an existing model in local, then if the new model is better, the user can override the old one with the new one.
That way, every x days, if the DataBase has been extended by the users for example, you can train the model on the new data or on all the data and choose to keep or let go this new model.

On this GitHub you can find all the information on how to use a HuggingFace machine learning / AI model on the IRIS Framework using python.

1. iris-huggingface

Usage of Machine Learning models in IRIS using Python; For text-to-text, text-to-image or image-to-image models.

Hi Community,

In a hard work of data curation and data quality, the Health Dataset application deploy to you the above datasets.

These datasets can be used in your ML applications/models, AutoML and analytics projects. See more details here:

Challenges of real-time AI/ML computations

We will start from the examples that we faced as Data Science practice at InterSystems:

• A “high-load” customer portal is integrated with an online recommendation system. The plan is to reconfigure promo campaigns at the level of the entire retail network (we will assume that instead of a “flat” promo campaign master there will be used a “segment-tactic” matrix). What will happen to the recommender mechanisms? What will happen to data feeds and updates into the recommender mechanisms (the volume of input data having increased 25000 times)? What will happen to recommendation rule generation setup (the need to reduce 1000 times the recommendation rule filtering threshold due to a thousandfold increase of the volume and “assortment” of the rules generated)?
• An equipment health monitoring system uses “manual” data sample feeds. Now it is connected to a SCADA system that transmits thousands of process parameter readings each second. What will happen to the monitoring system (will it be able to handle equipment health monitoring on a second-by-second basis)? What will happen once the input data receives a new bloc of several hundreds of columns with data sensor readings recently implemented in the SCADA system (will it be necessary, and for how long, to shut down the monitoring system to integrate the new sensor data in the analysis)?
• A complex of AI/ML mechanisms (recommendation, monitoring, forecasting) depend on each other’s results. How many man-hours will it take every month to adapt those AI/ML mechanisms’ functioning to changes in the input data? What is the overall “delay” in supporting business decision making by the AI/ML mechanisms (the refresh frequency of supporting information against the feed frequency of new input data)?

What is Distributed Artificial Intelligence (DAI)?

Attempts to find a “bullet-proof” definition have not produced result: it seems like the term is slightly “ahead of time”. Still, we can analyze semantically the term itself – deriving that distributed artificial intelligence is the same AI (see our effort to suggest an “applied” definition) though partitioned across several computers that are not clustered together (neither data-wise, nor via applications, not by providing access to particular computers in principle). I.e., ideally, distributed artificial intelligence should be arranged in such a way that none of the computers participating in that “distribution” have direct access to data nor applications of another computer: the only alternative becomes transmission of data samples and executable scripts via “transparent” messaging. Any deviations from that ideal should lead to an advent of “partially distributed artificial intelligence” – an example being distributed data with a central application server. Or its inverse. One way or the other, we obtain as a result a set of “federated” models (i.e., either models trained each on their own data sources, or each trained by their own algorithms, or “both at once”).

Artificial intelligence has solved countless human challenges – and medical coding might be next.
As organizations prepare for ICD-11, medical coding is about to become more complicated. Healthcare organizations in the United States already manage 140,000+ codes in ICD-10. With ICD-11, that number will rise.
Some propose artificial intelligence as a solution. AI could aid computer-based medical coding systems, identifying errors, enhancing patient care, and optimizing revenue cycles, among other benefits.

IRIS is an excellent option for machine learning projects with massive data operation scenarios, because the following reasons:

Keywords: IRIS, IntegratedML, Flask, FastAPI, Tensorflow Serving, HAProxy, Docker, Covid-19

Whats NLP Stands For?

NLP stands for Natural Language Processing which is a field of Artificial Intelligence with a lot of complexity and
techniques to in short words "understand what are you talking about".

And FHIR is...???

FHIR stands for Fast Healthcare Interoperability Resources and is a standard to data structures for healthcare. There are
some good articles here explainig better how FHIR interact with Intersystems IRIS.

This is the third post of a series explaining how to create an end-to-end Machine Learning system.

Training a Machine Learning Model

When you work with machine learning is common to hear this work: training. Do you what training mean in a ML Pipeline?
Training could mean all the development process of a machine learning model OR the specific point in all development process
that uses training data and results in a machine learning model.

This is the second post of a series explaining how to create an end-to-end Machine Learning system.

Exploring Data

The Intersystem IRIS already has what we need to explore the data: an SQL Engine! For people who used to explore data in
csv or text files this could help to accelerate this step. Basically we explore all the data to understand the intersection
(joins) which should help to create a dataset prepared to be used by a machine learning algorithm.

A few months ago, I read this interesting article from MIT Technology Review, explaing how COVID-19 pandemic are issuing challenges to IT teams worldwide regarding their machine learning (ML) systems.

Such article inspire me to think about how to deal with performance issues after a ML model was deployed.

Keywords: PyODBC, unixODBC, IRIS, IntegratedML, Jupyter Notebook, Python 3

Purpose

A few months ago I touched on a brief note on "Python JDBC connection into IRIS", and since then I referred to it more frequently than my own scratchpad hidden deep in my PC. Hence, here comes up another 5-minute note on how to make "Python ODBC connection into IRIS".

Hi all. Yesterday I tried to connect Apache Spark, Apache Zeppelin, and InterSystems IRIS. During the process, I experienced troubles connecting it all together and I did not find a useful guide. So, I decided to write my own.