Machine Learning & AI Meetup

Tickets only available via humanitix:
https://events.humanitix.com/learn-to-pitch-and-ai-startup?discountcode=MLAICREW

It's a fun, low-stakes pitch competition 🚀🚀🚀

Come, one come all! Validate that crazy AI startup idea you've been thinking about 🎃

This is how it works:
💡- Arrive with a vague idea for a cool AI startup, or no idea at all!

🤝 - Form a team of 2-4 at the event (if you came with friends you can keep them in your team, it's ok)

👀- Watch a 10 minute talk on how to do a great AI pitch delivered by Dr. Sam Donegan from Support Sorted

🧠 - You have 30 minutes to workshop the team's best idea for a startup involving AI and refine it into a 90 second pitch

🥇- Four Finalists will be chosen by popular demand and pitch in front of the whole crowd

💰 - One winner will be chosen by Melbourne Based Venture Capitalists and awarded cold hard cash as investment

🚀 - Youre now an AI startup! Congratulations! Time to move to San Francisco I guess...

We'll also be supplying light refreshments 🍕🍹, it's gonna be really fun and literally the best way there is to learn about how to pitch tech related startups.

Talk: Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language Detection

Abstract: This paper proposes a novelty approach to mitigate the negative transfer problem. In the field of machine learning, the common strategy is to apply the Single-Task Learning approach in order to train a supervised model to solve a specific task. Training a robust model requires a lot of data and a significant amount of computational resources, making this solution unfeasible in cases where data are unavailable or expensive to gather. Therefore another solution, based on the sharing of information between tasks, has been developed: Multi-task Learning (MTL). Despite the recent developments regarding MTL, the problem of negative transfer has still to be solved. Negative transfer is a phenomenon that occurs when noisy information is shared between tasks, resulting in a drop in performance. This paper proposes a new approach to mitigate the negative transfer problem based on the task awareness concept. The proposed approach results in diminishing the negative transfer together with an improvement of performance over classic MTL solution. Moreover, the proposed approach has been implemented in two unified architectures to detect Sexism, Hate Speech, and Toxic Language in text comments. The proposed architectures set a new state-of-the-art both in EXIST-2021 and HatEval-2019 benchmarks.

Speaker Bio: Angel Magnossão de Paula (Angel) is a third-year PhD candidate in the Computer Science program at the Universitat Politècnica de València in Valencia, Spain. He earned his B.Sc. in engineering from FEI University Center in 2015 and his M.Sc. in computer engineering from the Universidade de São Paulo in 2021, both in São Paulo, Brazil. Angel is also an assistant researcher at the University of Melbourne and RMIT University. His research interests include machine learning, deep learning, and natural language processing.