Fair ML models and Cross-Attentional Neural Network for Image and Text
Date and time
UniCredit will host this event covering those two topics in the field of Machine Learning
About this event
Towards fair ML models - Riccardo Monetti, Group Data & Intelligence UniCredit
Fairness is a key pillar of AI trustworthiness. How fairness should be handled, assessed and monitored while developing and deploying a machine learning application? The need to establish a workflow based approach to manage these points is rising rapidly and could soon become a regulatory requirement. This presentation’s objective is to propose a possible workflow solution highlighting pros and cons.
Riccardo Monetti is a Data Scientist with a mathematics background. He has a M.Sc. In Statistics and an internship experience in USA. He joined UniCredit in 2018 and worked on e2e ML and data applications across different group functions.
Topics: bias, E2E workflow, fair machine learning
Cross-Attentional Neural Network to Compare Image and Text - Dario Saccavino, Group Data & Intelligence UniCredit
Starting from a simple use case concerning the automatic processing of bank cheques, we study a novel multimodal learning problem: given an image containing a single line of text and a candidate text transcription, the goal is to assess whether the text represented in the image corresponds to the candidate text. The proposed model, via end-to-end training, compares the two inputs by applying a cross-attention mechanism over the embedding representations of image and text. Results show a good performance achieved on a variety of configurations.
Dario Saccavino, born in Milan in 1982, is a mathematician who loves coding. He joined UniCredit in 2019 to work as data scientist. Recently he developed further interest into Quantum Computing topics.
Topics: cross attention, joint embedding learning, multimodal learning, text recognition, text matching
---
Event details
This event is hosted by UniCredit at the Tower A (2nd floor) office located in Piazza Gae Aulenti, Milan. The event will be held in English. At the end of the talks will follow a networking aperitif with food and drinks.
Attending in presence:
This event is hosted by UniCredit. There will be 40 seats reserved to the community. If the tickets are sold out you can register on the waitlist, we will apply a first-in first-out policy to assign seats in case of cancellations.
The final list of attendee names will be confirmed 2 days before the event.
During the event we will share a Slido code (#479004) that you can use to interact with the speakers and ask questions.
Attending remotely:
The event will be streamed live via the UniCredit streaming platform (https://multimedia.unicredit.eu/view/17052022-MeetUp) or on our Youtube channel (https://www.youtube.com/c/DataScienceMilan).
Agenda:
19:00 Welcome and Opening
19.05 Intro to the Data Science Milan community
19.10 Tech talks start
20.15 Networking aperitivo
---
Would you be happy to host one of our events? Increase your popularity and be known by our community by hosting one of our interesting events. Contact us at datasciencemilan@gmail.com.
If you are interested in doing a lightning talk or want to propose an event, hackathon, panel discussion, roundtable, or any sort of initiative please submit your proposal by getting in touch with a member of the staff. More info at www.datasciencemilan.org.
---
This event is supported by IAML (Italian Association of Machine Learning).
