Data Science Milan #002
Data Science Milan
The Community of Data Scientists and Machine Learning Practitioners based in the Greater Milan area.
Dear Data Science Milan Community,
Welcome back to our newsletter, bringing you another edition packed with the latest developments, inspiring projects, and invaluable insights from the world of data science!
If you haven't been living under a rock, or you're not involved in the field, chances are you've heard of LangChain and LLama 2. These two projects have been making waves in the data science community, gaining widespread attention and praise for their innovative approaches and transformative potential.
LangChain is a powerful tool that can be used to work with Large Language Models (LLMs). LLMs are very general in nature, which means that while they can perform many tasks effectively, they may not be able to provide specific answers to questions or tasks that require deep domain knowledge or expertise. We discussed this topic in our last meeting at Google Italy with an interesting use case from Generali.
The other novelty is LLaMA 2, a foundation model released by Meta with an open-source license, sending a very strong signal to the GenAi landscape and moving in the opposite direction compared to its direct competitors. As open-source lovers, we are taking a stance to promote a change of direction in the industry toward open-source models!
Data?Science?Milan?events
Building GenAI applications with LangChain on GCP
On June 27th, 2023, Ivan Nardini from Google Italia, Ivan Vigorito and Domenico Vitarella from Generali showed us an interesting Generative AI use case. ?
With an introduction from Ivan about LangChain, a framework that simplifies 'prompt piping' with large language models (LLMs) using Google Cloud. Then Ivan and Domenico shared a case study of using LangChain with PALM 2 for knowledge base Q&A in Generali. The magic is done by giving PALM 2 the ability to query a 'chunkenized' version of different documents using LangChain to 'connect' the information that are not available together.
TinyML
In this talk Pietro Montino spoke about TinyML, a core technology of modern IoT systems where data are analyzed close to where they are collected,?with benefits for energy efficiency, latency, privacy, and cost.
Explainable AI in the Banking Industry - Application of DevOps and MLOps towards digital automation in banking use cases
In the first talk Ilaria Bordino, discussed explainable AI in the banking industry, emphasizing the need for AI systems that amplify human capabilities and incorporate ethical principles. She mentioned popular methods like LIME and SHAP for model explainability and introduced the concept of counterfactual explanations.
In the second talk, Bhaskar Chakraborty explained the challenges faced in developing ML applications for automating banking workflows, such as document classification and information extraction. Bhaskar emphasized the role of DevOps in addressing these challenges by automating the continuous integration (CI) and continuous delivery (CD) processes. He explored the ML lifecycle, including data ingestion, cleaning, validation, model development, and serving.?
领英推荐
Knowledge section
Here our selected resources
The learning path offered by Google on Generative AI products and technologies - Generative AI learning path
The documentation repository on the amazing framework for developing applications powered by language models - LangChain
The learning path about Vertex AI platform developed by Google to scale applications using benefits from Google Cloud - Vertex AI
Be involved!
We want also to remind you that if you like and enjoy our events, you can get in touch with us at?[email protected]?for being involved in organizing new great online activities.
We are also very happy if you are interested in being a speaker or if you want to share your expertise or experience with the?Data?Science?Milan?community!!!
Wallboard
Would you like to become one of our sponsors and increase your popularity among the?Data?Science?community? Write?here
If instead, you would like to promote a message to the wallboard, please contact us and send us your relevant announcements. We will publish them here.