All decks
  • Step into Open Source Contribution - My First PR

    Slides for the workshop - how to make your first open source contribution

  • I am telling you 3 things about Chatbot

    Chatbot is cool! Now we can talk to our gadgets as if it’s a real human, right? It also makes you wonder when you chat with the “customer service” online, is that a real person or a robot on the other side? My boss wanted me to build a chatbot, and here’s 3 things that I discovered.

  • Chatbots that know if you are angry

    While chatbots are a blooming thing, we always want out bots to be smarter. Imagine a chatbot that knows how angry your customer is and handle the complain more seriously. With the development of NLP, seems we can get more out of the text, like extracting the tone and the emotion form the text.

  • Do we have a diversity problem in Python community?

    Python community cares about diversity: there’s a diversity statement on the PSF website. So do we still have a problem in, especially gender, diversity? We will look at some data and see if there’s a true problem in gender diversity, discuss what the problem may be and how to fix it.

  • AI and Algorithmic Art - Could computer take over human creativity?

    Some thinks neural networks are magic boxes, let the computers to have a mind of it’s own. Beside making classifications and predictions, neural network has also been used to creating pictures, musics, jokes and plays. Can creativity, what seems to make us special, be achieved by these magic boxes?

  • Introduction to Reinforcement Learning

    Introduction to Reinforcement Learning, overview of different RL strategy and the comparisons.

  • Deep Learning with Keras : Building an AI that Talks like Shakespeare or Trump

    Computers are getting closer to speak like humans. But can we even make them speak in particular ways, like as Trump or Shakespeare? In this hands on talk we will see how this is possible with the latest deep learning techniques combined with word embeddings and other advanced NLP technique.

  • Fuzzy Matching - Smart Way of Finding Similar Names Using Fuzzywuzzy

    Ever encounter a tricky situation of knowing there’s names that are the same, but matching strings straight away leads you no where? All you need is Fuzzywuzzy, a simple but powerful open-source Python library and some wit. This talk will demonstrate how to efficiently fuzzy match company names.