PyData Bristol - 1st Meetup

button-icon-arrow-right
button-icon-arrow-left

button-icon-arrow-leftBack

Event

PyData Bristol - 1st Meetup

15 March 2018

Bristol

Added 01-Jan-1970

We are delighted to bring to you Bristol's first PyData meetup! We have a great speaker line-up in the works, we'll introduce you to ourselves, and find out what's happening in both the local data community as well as the global PyData community.

Refreshments will be generously provided by our host OVO Energy. Whilst there is a high probability of beer and pizza, requests or suggestions are encouraged.

πŸ“Š TALKS
=========

Expect two 30-minute talks, plus two 5-minute lightning talks, plus community announcements.
——————————————

Marco Bonzanini on “Understanding Natural Language using Word Vectors”
——————————————
This talk is an introduction to word vectors, a.k.a. word embeddings, a family of Natural Language Processing (NLP) algorithms where words are mapped to vectors. An important property of these vectors is being able to capture semantic relationships, for example:
Paris - France + Italy = ???
These techniques have been driving important improvements in many NLP applications over the past few years, so the interest around word embeddings is spreading. In this talk, we'll discuss the basic linguistic intuitions behind word embeddings, we'll compare some of the most popular word embedding approaches, from word2vec to fastText, and we'll showcase their use with Python libraries.

---------------------More talks to be listed soon.---------------------

We are currently pulling together a schedule of speakers for the coming months - if you're interested in contributing either a thirty minute talk, or a five minute lightning talk, we would love to hear from you. You can get in touch @pydatabristol on Twitter.

⚑️ LIGHTNING TALKS
=====================

Adam Smith will be sharing his experiences of the last year building an algorithmic trading system in python. He'll share some things he's found which have really helped and more things he tried that didn't! The main focus will be on the model building pipeline that uses the XGBoost library to fit decision tree based models to features extracted from financial time series data.

---------------------More talks to be listed soon.---------------------

Top