Time: April 20, 2016 from 6pm to 8:30pm
Location: General Assembly - WeWork
Street: 1550 Wewatta St
City/Town: Denver, CO 80202
Website or Map: http://www.meetup.com/Data-Sc…
Event Type: free, and, open, to, all
Organized By: Michael Walker
Latest Activity: Jul 6, 2017
Wednesday April 20, 2016 from 6pm to 8:30pm MST
Location: Industry Denver - 3001 Brighton Blvd, Denver, CO 80216 - Map: https://goo.gl/maps/xax6m7f87Jo
6:00 - 6:20 Schmooze - Food shall be served
6:20 - 6:30 Announcements
6:30 - 7:30 Overview of Tensorflow
7:30 - 8:00 Differences between Caffe and Tensorflow
8:00 - 8:30 Networking
Overview of Tensorflow - Abstract
Google recently open sourced TensorFlow providing access to a powerful machine learning system. TensorFlow is a machine learning library with tools for data scientists to design intelligent systems (interface for expressing machine learning algorithms and implementation for executing such algorithms). It runs on CPUs or GPUs, and on desktop, server, laptop, or mobile platforms with a single API. Originally developed by the Google Brain Team in Machine Intelligence Research, TensorFlow has a flexible, portable and general architecture for a wide variety of applications. The system has been used for deploying machine learning systems for information retrieval, simulations, speech recognition, computer vision, robotics, natural language processing, geographic information extraction, and computational drug discovery.
The system uses data flow graphs where data with multiple dimensions (values) are passed along from mathematical computation to mathematical computation. Complex bits of data are tensors and math-y bits are nodes, and tensors flow through the graph of nodes. The way data transforms from node to node tells the system relationships in the data.
Differences between Caffe and Tensorflow - Abstract
- Comparison of architectures of Caffe and TensorFlow.
- Introduction to recurrent networks.
- Functions supporting recurrent nets in TensorFlow.
Ilya Zharkov - Bio
Ilya is a software engineer at Uber Technologies in Louisville. He works on computer vision and machine learning problems to improve map data for Uber services. He graduated from Moscow State University with an MS in Physics in 2005. In 2008 he moved to Colorado to work in Parascript LLC on OCR and medical imaging. In 2011 I joined Google where heworked on automatic map creation using aerial imagery. In 2015 he started to work in Microsoft Bing Maps which was acquired by Uber in August. He’s been using several in-house deep learning libraries in Microsoft and Google, in Uber we use open source libraries like Caffe and recently TensorFlow.