Loading…
PAPIs Latam 2019 has ended
Back To Schedule
Monday, June 24 • 09:00 - 17:00
Deep Learning Kickstart with Keras — Training Workshop

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
This training workshop will take place before the main conference. It will be given in a small classroom, to maximize interaction and so you can ask even more questions than in a conference setting.

IMPORTANT:
  • A specific ticket is required to get access to the workshop ("Workshop WORKSHOP_NAME + Conference 24-26/6").
  • The venue is different from that of the main conference. The workshop will be held at Dafiti — many thanks to them for providing the space!
  • Students should bring their own laptops, for practical work. They will be given access to GPU-equipped machines in the cloud, for hands-on experiments with deep learning.
----

SUMMARY
Deep Learning is one of the most exciting research areas in artificial intelligence. It has achieved outstanding results in Computer Vision and Natural Language Processing. In this hands-on workshop for beginners, we will teach you about the basic concepts of Deep Learning and present some popular models: Deep Feedforward Neural Networks (DFNs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). Our focus is on applying these models to real life problems. Hence we will show how to formulate those problems in a way that can be solved by Deep Learning methods.


LEARNING OBJECTIVES
  • Understand how to build basic Deep Learning models for image and text.
  • Practical guidance on how to structure and train your model.
  • Learn Keras for a faster transition from idea to product.


PROGRAM
Introduction
  • Machine learning review
  • Neural network basics
  • Keras: basic usage
  • Hands-on: Lane following as regression (self-driving car task)

Convolutional Neural Networks (CNN)
  • Convolution in image processing
  • Transfer Learning
  • Hands-on: Lane following as image classification with CNN

Recurrent Neural Networks (RNN)
  • Text as training data
  • Word Embeddings
  • Understating RNN and its extensions: LSTM and GRU
  • Hands-on: Sentiment analysis

Conclusions
  • Recap
  • Advanced topics:
  • Transferability analysis (transfer learning tips)
  • What's new in NLP? BERT
  • Useful resources


 STUDENT REQUIREMENTS
  • All the Hands-on exercises will be coded in Python. Therefore, we expect basic knowledge of that language. If you want to review basic Python concepts, you can refer to https://www.codecademy.com/learn/learn-python 
  • Bring your own laptop for hands-on practical work.

Speakers
avatar for Paula Moraes

Paula Moraes

MSc Candidate, IME-USP
avatar for Felipe Salvatore

Felipe Salvatore

PhD Candidate, USP
Felipe Salvatore is a Ph.D. candidate at the University of São Paulo where he focuses on the natural language problem of dialog generation using Machine Learning. After graduating from a Master's in Logic, he became interested in Artificial Intelligence and started collaborating... Read More →


Monday June 24, 2019 09:00 - 17:00 GMT-03
Dafiti Group — Room MARSEILLES Av. Francisco Matarazzo, 1350 - Água Branca, São Paulo - SP, 05001-100, Brazil