Machine Learning Week Europe’s Post

Miha Garafolj (Merantix Momentum) addresses the engineering challenges of building interactive active learning systems on a practical example of large-scale video analysis. https://ow.ly/zcvG50TJzvl #mlweek #datascience #machinelearning

If you haven't grabbed your ticket yet, then now is the time. Register before this Friday, 27 September, to secure the Early Bird ticket and save up to €400. 👉 https://ow.ly/zuGU50Tu8SC You'll have the opportunity to learn from industry leaders like Dr. Christoph Best, Dr. Axel Buddendiek, Erik Schwulera, Jack Lampka, Wiebke Apitzsch, Dr. Monika Lieb and many more. Dive deep into workshops, and get in on table discussions that will take your machine learning skills to the next level. #mlweek #predictiveanalytics #machinelearning #deeplearning #generativeAI

In AI we see large discussion around generative-AI and LLMs and the simpler methodologies are let to the side in favour of these more complex methods. Often times the data we have access to is much more basic. In this talk Hansel Palencia will show how DaVita implemented a simpler more interpretable model to attempt to reduce hospitalisations in dialysis-centres. He’ll also discuss how they balanced and communicated model performance and clinical interpretability to have physician buy-in. https://ow.ly/QUfL50Tl02Q #mlweek #HealthcareAI

For healthcare professionals, treating patients in the best way possible is a challenge in more ways than one. Extensive therapy guidelines – though necessary – contribute to the complexity of their working life. To support treatment decisions, Campana & Schott, together with Charité, developed a smart assistant which recommends treatment according to said guidelines based on the patient’s diagnosis and medical history. Ramón Roales-Welsch will present you his results and envision potential further applications. https://ow.ly/9u1w50TkZRO #mlweek #HealthcareInnovation

Model-based process characterisation is key for implementing real time release testing within pharmaceutical manufacturing. Carlos André Muñoz López illustrates the integration of data-driven modelling and machine learning to craft resilient release strategies capable of accurately predicting the products’ quality attributes. These strategies result in optimised lead times in the supply chain and foster a comprehensive and timely understanding of the process performance, thereby generating substantial value. https://ow.ly/ot4f50TkZBc #mlweek #Healthcare #DataDrivenModelling

In this session, Steffen Sass will showcase the application of artificial intelligence at Roche for assessing visible particles in drug products. This technology enables Roche not only to automatically classify particles into several subclasses but also to significantly improve the image data processing and cleaning. Steffen will illustrate how Roche designed the user-facing application in order to efficiently assist the data processing, thereby collecting new data that are used for the model improvement. https://ow.ly/mwW450TkZry #mlweek #Healthcare #AIApplications

Extracting information from different kinds of unstructured text documents is a hard task in the field of #NLP. The advent of large language models (LLMs) provided a new way to tackle the problem, exhibiting high potential. Here, Paolo Ferriani shows how Gothaer successfully applied #LLMs to extract key information out of unformatted medical records, agent emails, and insurance forms in order to provide a structured summary for life insurance underwriters, speeding up considerably the risk and premium assessment. https://ow.ly/O9aN50T7xKW #mlweek #machinelearning

The RAG (Retrieval-Augmented Generation) has been applied in many financial applications and without a careful treatment, the RAG could not really bring value to professionals, such as portfolio managers and analysts. Hungjen Wang would like to share his experience in how Franklin Templeton designed the architecture of the RAG system and which parts actually matter to its performance. https://ow.ly/aXgm50T7xqG #mlweek #machinelearning

Today’s LLMs such as #ChatGPT show an impressive performance and have the potential to revolutionize our daily life. All these LLMs are based on the Transformer architecture with the Attention mechanism at its core. Due to the quadratic scaling with context length, Attention makes processing of long sequences very expensive. In this talk, Maximilian Beck presents xLSTM, a novel architecture for #LLMs that scales only linear in context length while still outperforming Transformers on language modeling. https://ow.ly/3Q1x50T7v0F #mlweek #machinelearning

Jack Lampka and Dr. Julia Zukrigl will show how data storytelling is helping to promote data products and get buy-in at a pharma company. Tune in to learn the process of shaping the narrative and finding a data product marketing strategy. Get expert tips on how you can use #datastorytelling for your own data / AI product. https://ow.ly/GucC50SRB1Y #mlweek #data #machinelearning