Anthill Inside 2017

Neural Networks are rapidly gaining traction in applications such as autonomous vehicles, industrial automation and other verticals. Bounding box neural networks are fast emerging as preferred method for vision application where location accuracy, classification, speed of inference as well as minimal data size for transmission to controllers are all important. This talk aims to introduce concepts of bounding box, the metrics for measuring output, survey of techniques and performance and sample implementation of a bounding box neural network using Tensforflow

Outline

-Introduction to Bounding boxes and their advantages over other image techniques
-Annotation for bounding box neural network
-Metrics to measure performance of bounding box neural networks
-Survey of bounding box neural networks and their performance
-Tensorflow based implementation of SSD bounding box network and the results of the same

Requirements

Basic components of CNN, datasets and annotations and NNs such as VGG

Speaker bio

With background in signal processing and fascination for automotive and industrial control systems, I have been keenly following the development of neural networks and their applications in autonomous vehicles and industrial applications. As a co-founder and engineer at Minds.ai, I got opportunity to learn about and work on neural network implementation with some of the best in the field. I would like to take this chance to share whatever I have learnt and learn something new from others

Links

• https://www.minds.ai
• https://www.linkedin.com/in/anil-hebbar-2175452/