Tutorial: Fast Deep Learning Prototypes with Tensorflow and Keras

The Rochester Signal Processing Society hosted a virtual zoom session on Thurs, April 30th entitled “Fast Deep Learning Prototypes with Tensorflow and Keras Tutorial”, by RIT PhD student Miguel Dominguez. 63 people registered for this hour-long session which included the distribution of iPython notebook sample code and deep learning software installation instructions. This tutorial was very well attended, in spite of being held, non-traditionally, via Zoom.

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. This tutorial discussed using Tensorflow 2.0 with the Keras API to enable rapid prototyping of DNNs with a minimum of code. All software is free open-source code. The tutorial demonstrated how to get several variants of Convolutional Networks up and running, for training, prediction, and logging.

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

The TensorBoard dashboard pictured here shows the performance of models as they are being trained.

TensorBoard dashboard showing training performance of Deep Learning Models

2020 Terra Science Fair

Two of our members, Sreeram Dhurjaty and Mark Schrader, helped judge entries in the 2020 Terra Science and Engineering Fair. Due to the COVID-19 shutdowns and the need for physical distancing, the entrants used electronic communications to present their work to the judges, who participated from as far away as Texas. More than 50 students, from 19 schools and homeschooling in Monroe, Ontario, and Wayne counties, entered with impressive projects. The judges awarded six “Highest Honor Commendations” to these projects: “Watching our Water 2.0”, “A Comparative Analysis of Underactuated 3D Printed Hands”, “Bridges”, “SODIS Method”, “The Effects of K-12 Bliss on Antibiotic Resistant Organisms”, and “Green Tea as a Preventive Measure Against Disease Pathways Originating in the Oral Cavity”.

April 2020 Newsletter

Dear Colleagues,

This year’s IEEE Rochester Section Joint Chapter Meeting will feature a keynote presentation from Katherine J. Duncan, Ph.D., the IEEE-USA President-Elect. Dr. Duncan is an expert in the development of novel nanomaterials for next-generation communication systems, and currently is a Visiting Research Fellow in the Department of Electrical Engineering and Computer Science at the U.S. Military Academy West Point. She will be discussing the impact of IEEE on her career and the future of IEEE.

Congratulations to the newest IEEE Senior Members in the Rochester Section:

  • James Chwalek, Director of Research & Development at Imaginant, Inc.
  • Amlan Ganguly, Associate Professor of Computer Engineering at RIT
  • Sujatha Ramanujan, Managing Direction of NextCorps Luminate Accelerator

IEEE Senior Membership recognizes the recipient’s history of technical and professional excellence. In the Rochester Section, just 21% of active members have Senior Member or Life Senior Member status.

Best regards,

Eric Brown
Chair, Rochester IEEE Section

 

James Chwalek, Director of Research & Development at Imaginant, Inc
Amlan Ganguly, Associate Professor of Computer Engineering at RIT
Sujatha Ramanujan, Managing Direction of NextCorps Luminate Accelerator

 

 

Featured image:

 

IEEE Distinguished Lecturer Gaurav Sharma: RIT presentation

 

Submitted by:

 

Howard {Person submitting the newsletter (Last):1.6

 

Here is the 03 Newsletter