Name: DL with Python: Deep learning for text (Chapter 11 1/2)
Start: 2022-04-14T20:00:00+09:00
End: 2022-04-14T21:00:00+09:00

We're excited to announce Deep Learning with Python Study Series
based on the new edition of the popular book “Deep Learning with Python” by François Chollet.
In this study series, we will go through the chapters of the book, explain the theoretical part, run the code, answer questions and discuss various topics related to Deep Learning.

The book covers a vast range of Deep Learning topics. Starting with Machine Learning and Deep Learning basics and using simple examples and easy-to-follow code, it gets us to an advanced level of DL applications. It covers many different fields of DL, from tabular data, image classification, segmentation, and generation to the use of Transformers in NLP. Due to its unique structure, one can become familiar with the code of such projects even without prior knowledge of DL.

👉 SESSION DESCRIPTION
During the session, we will go through the first half of the 11th chapter of the book. We will see ways of preprocessing text data for machine learning applications and the bag-of-words approaches and sequence-modeling approaches for text processing. The code that we will read and run is based on:
[https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/chapter11_part01_introduction.ipynb](https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/chapter11_part01_introduction.ipynb)
[https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/chapter11_part02_sequence-models.ipynb](https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/chapter11_part02_sequence-models.ipynb)

👉 SESSION STRUCTURE
At each session, we will go through the notebook(s) of one chapter of the book. The notebooks can be found here:
https://github.com/fchollet/deep-learning-with-python-notebooks

* We will explain the theoretical background needed to understand the code, read and run the code, and answer related questions. The participants will be able to ask their questions at the chat either during or at the end of the session.
* For a better experience, it is recommended that you clone the Github repository and run the code yourself before and/or during the session. If you don’t have a GPU available feel free to use Colab. Although it’s not necessary, it is highly recommended that you read the corresponding chapter of the book before the session.

👉 JOIN ZOOM
https://us02web.zoom.us/j/81679313582?pwd=Q3c3OVpNNmRrZWIxaGkrUDg4QTA0QT09

📌 PREREQUISITES
To get the most out of the sessions and the book we recommend having intermediate Python skills and a good understanding of general Machine Learning concepts.

* We strongly recommend reading this book since it’s truly well written and it is worth your time. You can also read the book chapter-wise and join specific sessions since the presentations are meant to be stand-alone. Join us on this 3-month journey of weekly study sessions, from zero to advanced Deep Learning!
* The material that will be used during the study sessions is based on the excellent python notebooks provided by F. Chollet:
https://github.com/fchollet/deep-learning-with-python-notebooks

👉 PRESENTER BIO
Dimitris Katsios is a Machine Learning Engineer at LPIXEL where he contributes to the development of Deep Learning assisted medical diagnosis tools. Before that, he carried out his internship at Fujitsu Labs where he worked on Computer Vision applications.
Dimitris studied Primary Education and worked as a primary school teacher for several years. During that period he studied Industrial Engineering, and received an MSc degree in Information and Communication Systems Engineering, and an MSc in Intelligent Information Systems among others. He has been an instructor and speaker at various Deep Learning-related workshops and talks in Tokyo where he currently lives. He’s one of the Directors at Machine Learning Tokyo - MLT, a nonprofit organization and one of the biggest communities of ML engineers and practitioners in Japan.

● MLT NEWSLETTER
Sign up for the (infrequent and low noise) newsletter if you'd like to stay up to date with events and what we're working on https://www.getrevue.co/profile/mltai

● MLT PATRON
Become an MLT Patron and help us to keep MLT meetups like this inclusive and for free. https://www.patreon.com/MLTOKYO

● FIND MLT RESOURCES
Github: https://github.com/Machine-Learning-Tokyo
Youtube: https://www.youtube.com/MLTOKYO
Slack: https://bit.ly/36ImxtW

● RECRUITING
MLT events are for community building and knowledge sharing. We politely ask that company representatives, recruiters, and consultants looking to hire or sell their services do not participate in MLT activities or approach members in any form.

● CODE OF CONDUCT
MLT promotes an inclusive environment that values integrity, openness, and respect. https://github.com/Machine-Learning-Tokyo/MLT_starterkit

Sonika Shinde

Machine Learning Tokyo

Artificial_Intelligence

Technology

Neural Networks

Big Data

Artificial Intelligence Applications

Predictive Analytics

New Technology

Machine Learning

Natural Language Processing

Machine Intelligence

Data Science

Deep Learning

Artificial Intelligence

Open Source

DL with Python: Deep learning for text (Chapter 11 1/2)

Online event

Share

Machine Learning Tokyo

DL with Python: Deep learning for text (Chapter 11 1/2)

Machine Learning Tokyo

Details

Members are also interested in