Search:
Match:
3 results
Research#llm📝 BlogAnalyzed: Dec 29, 2025 07:50

The Future of Human-Machine Interaction with Dan Bohus and Siddhartha Sen - #499

Published:Jul 8, 2021 17:38
1 min read
Practical AI

Analysis

This article from Practical AI discusses the future of human-AI interaction, focusing on research projects by Dan Bohus and Siddhartha Sen from Microsoft Research. The conversation centers around two projects, Maia Chess and Situated Interaction, exploring the evolution of human-AI interaction. The article highlights the commonalities between the projects, the importance of understanding the human experience, the models and data used, and the complexity of the setups. It also touches on the challenges of enabling computers to better understand and interact with humans more fluidly, and the researchers' excitement about the future of their work.
Reference

“We explore some of the challenges associated with getting computers to better understand human behavior and interact in ways that are more fluid.”

PermalinkPractical AI
Research#Computer Vision📝 BlogAnalyzed: Dec 29, 2025 08:18

Trends in Computer Vision with Siddha Ganju - TWiML Talk #218

Published:Jan 7, 2019 21:00
1 min read
Practical AI

Analysis

This article from Practical AI discusses trends in Computer Vision with Siddha Ganju, an autonomous vehicles solutions architect at Nvidia. The focus is on her insights into the field in 2018 and beyond. The conversation covers her favorite Computer Vision papers of the year, touching on areas like neural architecture search, learning from simulation, and the application of CV to augmented reality. The article also mentions various tools and open-source projects. The interview format suggests a focus on practical applications and current research directions within the Computer Vision domain.

Key Takeaways

Reference

“Siddha, who is now an autonomous vehicles solutions architect at Nvidia shares her thoughts on trends in Computer Vision in 2018 and beyond.”

PermalinkPractical AI
Research#embedded AI📝 BlogAnalyzed: Dec 29, 2025 08:32

Embedded Deep Learning at Deep Vision with Siddha Ganju - TWiML Talk #95

Published:Jan 12, 2018 18:25
1 min read
Practical AI

Analysis

This article discusses the challenges and solutions for implementing deep learning models on edge devices, focusing on the work of Siddha Ganju at Deep Vision. It highlights the constraints of compute power and energy consumption in these environments and how Deep Vision's embedded processor addresses these limitations. The article delves into techniques like model pruning and compression used to optimize models for edge deployment, and mentions use cases such as facial recognition and scene description. It also touches upon Siddha's research interests in natural language processing and visual question answering.
Reference

“Siddha provides an overview of Deep Vision’s embedded processor, which is optimized for ultra-low power requirements, and we dig into the data processing pipeline and network architecture process she uses to support sophisticated models in embedded devices.”

PermalinkPractical AI