Description: Personal webpage of Amir Erfan Eshratifar
• Runtime Deep Model Multiplexing for Reduced Latency and Energy Consumption Inference Amir Erfan Eshratifar, Massoud Pedram IEEE International Conference on Computer Design, October 2020 • Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space Mohammad Saeed Abrishami, Amir Erfan Eshratifar, David Eigen, Yanzhi Wang, Shahin Nazarian, Massoud Pedram IEEE International Symposium on Quality Electronics Design, August 2020 • Video Person Re-ID: Fantastic Techniques
• Variational Auto Encoders (VAE) for the Numerai Dataset • Zero-Shot Object Detection using OpenAI's CLIP Model • How to build a deep learning GPU workstation while saving $1500? • Cloud vs On-device AI? Maybe something in between! • Defining user restrictions for GPUs • BottleNet: learnable feature compression for accelerated edge intelligence
I had a lot of research and teaching experiences which you can find on my CV. In addition, I have about one year experience on Smart Home Solutions.