Porto.AI first meetup is all about natural language processing and automation. Join us at Blip on the 18th of December, Tuesday to learn more. We are preparing a couple of surprises for all attendees as a Christmas preview.
*Snapshot of what the evening is going to be*
18.30 - registration opens
19.00 - 19.05 - Reception and Welcome Message
19.05 - 20.00 - AI Moment #1 by Wang Ling (Google Deepmind) - remote
20.15 - 21.00 - AI Moment #2 by Professor Luís Paulo Reis (UP) with Q&A
*Who you are*:
- Someone with elementary know-how in Artificial Intelligence (Machine Learning (including, Pattern Recognition, Deep Learning, Reinforcement Learning), Speech Recognition, Computer Vision, Robotics or Natural Language Processing);
- Keen to learn more on the topics above;
- Excited about new developments on each of the AI fields and interested to grow your network.
Wang Ling >> In this talk, I will describe our work on character-based models for natural language processing. This talk will be divided into two parts. In the first part, I will describe our previous work on character-based word representation, where the syntax and semantic of word-level units are leanly solely from the character-level. We show that these models can automatically learn morphologically oriented features that would be difficult to discover manually as features and show significant improvements in many natural language processing tasks. In the second part of the talk, I shall describe our ongoing work on character-based language generation and word segmentation/discovery. We show that the challenges involved in building character-level generation models, and then describe our incremental research contributions towards models that can automatically generate language but also jointly learn word segments.
Luís Paulo Reis >> RoboCup is focused on promoting Robotics and Artificial Intelligence research, by offering a publicly appealing, but formidable challenge: “Building robots able to play soccer”. Building a robot that plays soccer will not by itself generate significant social and economic impact, but the accomplishment will certainly be considered a major achievement for the field and will push the state-of-the art in multi-robot systems. In fact, in the future, humans and robots will have to work together in complex environments, to solve difficult problems and perform hard tasks, as a team. Thus, methodologies to enable robots to learn, interact and cooperate with their human counterparts are needed, in order to allow this joint work. This talk will be focused on methodologies developed for creating multi-robot and human-robot heterogeneous teams with emphasis on the cooperation, interaction and learning methodologies developed on our Robotic Soccer project: FC Portugal. This project developed methodologies for creating heterogeneous robotic soccer teams capable of following human/robot coach high-level advice using concepts such as strategy, tactics, formations and setplays. The project also developed methodologies for learning humanoid robot complex skills, using simulation, such as walking, kicking, getting up or passing/receiving a ball, although the methodologies developed may also be used for other types of skills and robots. The project enabled our research groups to win 4 World and 10 European robotic soccer championships of distinct leagues/competitions.
Thank you for BLIP and PortoTechHub supporting this meetup.
Instagram: https://www.instagram.com/porto.ai/ (use #portoai and #cityai hashtag)