Presented By O'Reilly and Cloudera
Make Data Work
31 May–1 June 2016: Training
1 June–3 June 2016: Conference
London, UK

Deep learning for web-scale text

Piotr Mirowski (Google DeepMind)
12:00–12:30 Wednesday, 1/06/2016
Hardcore data science
Location: Capital Suite 4 Level: Advanced
Average rating: ****.
(4.75, 4 ratings)

Prerequisite knowledge

Attendees should be familiar with machine learning.

Description

Deep learning algorithms can extract the meaning of text by learning representations of words. Piotr Mirowski looks under the hood of recurrent neural networks and explains how they can be applied to speech recognition, machine translation, sentence completion, and image captioning.

Photo of Piotr Mirowski

Piotr Mirowski

Google DeepMind

Piotr Mirowski is a research scientist at Google DeepMind. Previously, Piotr worked at Bell Labs and Microsoft Bing. Piotr has been trying to make sense of all sorts of sequential data, ranging from sensors (e.g., EEG for epilepsy prediction, smart meter logs for power demand prediction or WiFi, and inertial data for geolocalization) to text (speech recognition or search query completion). Piotr studied computer science at ENSEEIHT in France, followed by a PhD in deep learning in Yann LeCun’s lab at New York University.