6:00 - Doors open. Networking. Beer and Pizza
7:00 - Text Classification Techniques Using TensorFlow by Arseni Anisimovich, R&D Engineer at Gluru
7:30 - Q&A break.
7:45 - Predicting congestion on London's roads with TensorFlow by Oliver Gindele, Data Scientist at Datatonic
8:10 - Q&A break
8:20 - Wrap-up.
Text Classification Techniques Using TensorFlow
Today, humanity is generating data in numerous forms. One of the most prevalent is the textual data we write in e.g. social media, email and other forms of online communication. One of the tasks machine learning is applied to is text classification which comes in many forms with different bases. TensorFlow, a powerful tool for machine learning and neural networks in particular, provides us with all the means to implement any approach for text classification, but which approach to pursue is usually unclear. Taking a sentiment analysis task as an example, this talk will describe and showcase the ‘classic’ and the most promising approaches to text classification using TensorFlow.
Speaker: Arseni Anisimovich, R&D Engineer at Gluru
Arseni is R&D Engineer with 6 years of expertise in natural language processing and machine learning, starting with low-level language processing (syntactic and semantic parsing) and going to high-level tasks like machine translation and knowledge extraction. At Gluru, we are building a platform to serve as the future of truly smart IOT, using artificial intelligence to predict the semantic needs of a user allowing products and services to pre-empt and serve the information or action when the user requires it.
Predicting congestion on London's roads with TensorFlow
Predicting congestion is an important part of any traffic management system. With accurate forecasting traffic can be effectively regulated, ensuring safe and fast journeys on the roads. Based on data from Transport for London (TfL) we trained a neural network in TensorFlow that predicts congestion in south-west London. With this use case as example we will demonstrate how TensorFlow can be used to build predictive models for time series data.
Speaker: Oliver Gindele
Oliver is a Data Scientist at Datatonic with a background in computational physics and high performance computing. He is a machine learning practitioner who recently started exploring the world of deep learning.
Datatonic partners with Google Cloud Platform to build state of the art machine learning and data analytics solutions, providing customers with actionable business insight.