“Efficient and Scalable Deep Learning Based Object Recognition Methods” : vTools Events

IEEE.org | IEEE Xplore Digital Library | IEEE Standards | IEEE Spectrum | More Sites

Registration is closed for the event requested

“Efficient and Scalable Deep Learning Based Object Recognition Methods”

#communications #comsoc #network #computer #networks #vision #ML #infrastructure #Deep #Neural #Network #(DNN)

In-Person Location: Ingram School of Engineering, San Marcos University, Room IGRM 4104

Virtual: Zoom (https://txstate.zoom.us/j/91084259333)

Date: April 21, 2023

Time: 11:00 am – 1:00 pm

Talk Title: “Efficient and Scalable Deep Learning Based Object Recognition Methods”

Speaker: Mr. Vittal Siddaiah,

Senior Engineering Lead, Intel

F&B is included for in-person format

Cost: none

Abstract:

Artificial Intelligence (AI) is the panacea for prescriptive and predictive analytics through Machine Learning (ML) techniques, demands for computational performance, and snowballing over the decades. Pattern Recognition is increasingly demanding in AI applications that include neural networks-based machine learning. In this research, we are dealing face recognition domain of pattern recognition and person detection, popularly classified under computer vision.

Training deep-learning models are compute-intensive, and there is an industry-wide trend toward hardware specialization to improve performance. This research uses a DNN-based generic, efficient, scalable, and platform-independent framework that can be extendable across platforms. The proposed framework involves computer vision techniques suitable for unsupervised learning with low latency and high performance. The proposed framework is validated across diverse datasets, compatible and scalable across platforms, has low latency, and has a small footprint. The framework would serve as a benchmark and publish the rating parameters of response times, latencies, and accuracy that grade and differentiates various platforms.

Bio:

Vittal is a senior engineering lead at Intel with 19 years of experience architecting several silicon validation tools.

He has led several designs of a validation tool suite for pre- and post-silicon validation. He is distinguished for his contributions to the machine learning-based, high-performance design of tools. Some of his innovations include defining metrics and measurements of power and performance. He has earned several recognitions and awards, including “One Generation Ahead Award” and “Waste Elimination Award.”

Vittal has developed multiple teams, mentored leaders, and is passionate about mentoring engineers and students. He has won the “Best Trainer Award” at Intel. Some domains include Hardware-software co-design, Operations Research, Image Processing, Operating systems, System Design and Optimization, and High-Performance Computing.

Vittal is an avid learner with his Masters in Electrical Engineering, Masters in Management, M Phil in Management, and Masters in Mathematics.

If help is needed, please connect with:

Prof. Semih Aslan, aslan@txstate.edu or

Fawzi Behmann, f.behmann@ieee.org