Fast Deep Learning Prototypes with Tensorflow and Keras

Share

https://rit.zoom.us/j/91216440248

Deep Neural Networks (DNN) are a powerful tool for computer vision, signal processing, and natural language processing tasks. The last few years have seen the development of a plethora of software tools for the development of DNNs. Many of these tools provide a library of building blocks that the engineer or researcher can assemble in whatever form they desire. However, there are some common use cases that are implemented nearly identically every time. This leads to a lot of boilerplate code that slows down development. In this tutorial we discuss using Tensorflow 2.0 with the Keras API to enable rapid prototyping of DNNs with a minimum of code. Within the hour we will have several functioning Convolutional Networks, an efficient data pipeline, training and prediction, and logging. Some basic knowledge of Deep Learning and Python is assumed, as this tutorial focuses on the tool.



  Date and Time

  Location

  Hosts

  Registration



  • Rochester Institute of Technology
  • Rochester, New York
  • United States 14623
  • Starts 18 April 2020 10:00 AM
  • Ends 30 April 2020 11:59 AM
  • All times are US/Eastern
  • No Admission Charge
  • Register


  Speakers

Miguel

Topic:

Fast Deep Learning Prototypes with Tensorflow and Keras

Deep Neural Networks (DNN) are a powerful tool for computer vision, signal processing, and natural language processing tasks. The last few years have seen the development of a plethora of software tools for the development of DNNs. Many of these tools provide a library of building blocks that the engineer or researcher can assemble in whatever form they desire. However, there are some common use cases that are implemented nearly identically every time. This leads to a lot of boilerplate code that slows down development. In this tutorial we discuss using Tensorflow 2.0 with the Keras API to enable rapid prototyping of DNNs with a minimum of code. Within the hour we will have several functioning Convolutional Networks, an efficient data pipeline, training and prediction, and logging. Some basic knowledge of Deep Learning and Python is assumed, as this tutorial focuses on the tool.

Biography:

Miguel Dominguez is a PhD candidate in Engineering at Rochester Institute of Technology set to graduate in Summer 2020. His research interests include graph and point cloud neural networks as well as speech processing.





Agenda

Join Zoom Meeting

https://rit.zoom.us/j/91216440248

 

Meeting ID: 912 1644 0248

 

One tap mobile

+16465588656,,91216440248# US (New York)

+13126266799,,91216440248# US (Chicago)

 

Dial by your location

+1 646 558 8656 US (New York)

+1 312 626 6799 US (Chicago)

+1 346 248 7799 US (Houston)

+1 669 900 6833 US (San Jose)

+385 1300 0988 Croatia

+385 1777 6333 Croatia

Meeting ID: 912 1644 0248

Find your local number: https://rit.zoom.us/u/abKqiXYHsJ

 

Join by SIP

91216440248@zoomcrc.com

 

Join by H.323

162.255.37.11 (US West)

162.255.36.11 (US East)

221.122.88.195 (China)

115.114.131.7 (India Mumbai)

115.114.115.7 (India Hyderabad)

213.19.144.110 (EMEA)

103.122.166.55 (Australia)

209.9.211.110 (Hong Kong)

64.211.144.160 (Brazil)

69.174.57.160 (Canada)

207.226.132.110 (Japan)

Meeting ID: 912 1644 0248