McGill Artificial Intelligence Society
McGill Artificial Intelligence Society
  • 8
  • 8 134
AI Knows Words, AI Has the Best Words: KC Tsiolis - 2021 McGill AI Learnathon
An Introduction to Natural Language Processing
Ever wondered how Siri can have conversations with you or how new AI systems like GPT-3 can generate coherent news articles? While we cannot say that any system has passed the Turing test, advances in natural language processing (NLP) over the last decade - fueled by the rise of deep learning - have brought us closer to AI systems that can understand and generate text. From virtual assistants and chatbots to captioning systems and translators, NLP is now all around us. This workshop gives an overview of what NLP is, how we can represent language in a computer, which machine learning algorithms are commonly used in NLP, which tasks NLP has been successful at, as well as which ones still require a lot of work. The workshop will conclude with an interactive coding session, where audience members get to build their own NLP system for a specific task. No previous experience required!
---
Check out more of KC Tsiolis here: kctsiolis.github.io/
Read about the other talks from the 2021 McGill AI Learnathon here:
Learn about the McGill AI Society here: mcgillai.com
Переглядів: 94

Відео

A Small Introduction to Computer Vision: Margarita Mayoral Villa - 2021 McGill AI Learnathon
Переглядів 1433 роки тому
Computer vision is the part of Artificial Intelligence whose objective is to train machines to be able to understand the world and environment in a visual way. The objective of developing technologies around Machine Vision and Computer Vision is to get the same accuracy interpreting images and scenes as the accuracy that a human brain can have. With Machine Vision and Computer Vision the machin...
Math + AI = some really cool algorithms: Sandi Mak - 2021 McGill AI Learnathon
Переглядів 3233 роки тому
Mathematics is the language of science, and in the field of AI - it is the only language that machines can understand. From Chabtbots to self-driving cars; cancer detection to speech recognition; the applications of AI and machine learning are endless. But what is precisely going on under the hood and behind the scenes? In this talk, we will take a look at the mathematics (or if you prefer the ...
Graph Representation Learning: William L. Hamilton - 2021 McGill AI Learnathon
Переглядів 6 тис.3 роки тому
Recent Advances and Open Challenges Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial if we want systems that can learn, reason, and generalize from this kind of data. Recent years have seen a surge in research on graph representati...
How to build a resilient technological society (with interactive robots): AJung Moon - McGill AI
Переглядів 2813 роки тому
In what ways should machines be part of our society exerting influence on our behaviours and decisions? How could human values be integrated into the design and deployment of autonomous intelligent systems? Drawing from examples in the domain of human-robot interaction, this explores some of the tricky questions pertaining to ethical design of interactive robots in particular, and what remains ...
Tackling Climate Change with Machine Learning: David Rolnick - 2021 McGill AI Learnathon
Переглядів 7143 роки тому
Climate change is one of the greatest challenges facing humanity, and those of us in machine learning may wonder how we can help. In this talk, we will see how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we explore high impact problems where existing gaps can be filled by m...
Machine Learning and Creativity: Pablo Samuel Castro - 2021 McGill AI Learnathon
Переглядів 1993 роки тому
The Opening keynote talk at the 2021 McGill AI Leanathon was given by Pablo Samuel Castro from Google Brain Montreal. For a brief summary of the days talks, check out this blog post: Check out mcgillai.com for more information
MAIS 202: Accelerated Introduction to Machine Learning Course (Winter 2019)
Переглядів 1885 років тому
MAIS 202: Accelerated Introduction to Machine Learning Course (Winter 2019)

КОМЕНТАРІ

  • @DataTranslator
    @DataTranslator Місяць тому

    Excellent 🙏🏾. Thank you

  • @mkwarlock
    @mkwarlock 2 місяці тому

    Mr. Hamilton's book is the best one on GNNs that I've come across, hands down. What a king, thank you!

  • @InquilineKea
    @InquilineKea 3 місяці тому

    This is way better than most

  • @derekwu9349
    @derekwu9349 Рік тому

    Thanks Sandi!

  • @gaelanmelanson8412
    @gaelanmelanson8412 2 роки тому

    Some of the figures look taken from a 2018 talk by Jure Leskovec, for example: ua-cam.com/video/fbRDfhNrCwo/v-deo.html looks very similar to: ua-cam.com/video/oQL4E1gK3VU/v-deo.html

    • @emilymcmilin94
      @emilymcmilin94 Рік тому

      Looks like they are co-authors: www-cs.stanford.edu/people/jure/pubs/graphrepresentation-ieee17.pdf

    • @jryzu8043
      @jryzu8043 Рік тому

      Considering both were working at Stanford when they pioneered GNNs, it’s likely there was already some collaboration between them

  • @LeslieSolorzanov
    @LeslieSolorzanov 3 роки тому

    Could you add some of the examples you said you could give to go from shallow to deep? and how to include node's features?

  • @danielsokil9529
    @danielsokil9529 5 років тому

    Where can I learn more?