• 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 and Where to Find Them
Priyank Pathak, Amir Erfan Eshratifar, Michael Gormish
AAAI, February 2020
• Coarse2Fine: A Two-stage Training Method for Fine-grained Visual Classification
Amir Erfan Eshratifar, David Eigen, Michael Gormish, Massoud Pedram
Machine Vision and Applications, January 2020
• JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services
Amir Erfan Eshratifar, Mohammad Saeed Abrishami, Massoud Pedram
IEEE Mobile Computing Journal, October 2019
• BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services
Amir Erfan Eshratifar, Amirhossein Esmaili, Massoud Pedram
IEEE International Symposium on Low Power Electronics and Design, August 2019
• Towards Collaborative Intelligence Friendly Architectures for Deep Learning
Amir Erfan Eshratifar, Amirhossein Esmaili, Massoud Pedram
International Symposium on Quality Electronic Design, March 2019
• Gradient Agreement as an Optimization Objective for Meta-Learning
Amir Erfan Eshratifar, David Eigen, Massoud Pedram
NeurIPS Meta-Learning Workshop, December 2018
• A Meta-Learning Approach for Custom Model Training
Amir Erfan Eshratifar, Mohammad Saeed Abrishami, David Eigen, Massoud Pedram
AAAI, February 2019
• Energy and Performance Efficient Computation Offloading for Deep Neural Networks in a Mobile Cloud Computing Environment
Amir Erfan Eshratifar, Massoud Pedram
ACM Great Lakes Symposium on VLSI, May 2018
• A Hardware-Friendly Algorithm for Scalable Training and Deployment of Dimensionality Reduction Models on FPGA
Mahdi Nazemi, Amir Erfan Eshratifar, Massoud Pedram
International Symposium on Quality Electronic Design, March 2018
• 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
Jan 2023: Joined Yahoo as a research engineer!
Jan 2022: I'm selling my Numerai model predictions as a Gumroad monthly subscription. Click here for more.
Oct 2021: Defended my Ph.D. thesis: "Edge-Cloud Collaboration for Enhanced Artificial Intelligence"
Feb 2021: Joined Clarifai as a research scientist!
Jan 2021: Coarse2Fine paper accepted in Machine Vision and Applications journal.
Oct 2020: DNN Multiplexing paper accepted in ICCD conference.
Nov 2019: JointDNN paper accepted in IEEE Mobile Computing journal.
May 2019: BottleNet paper accepted in ISLPED conference.
Jan 2019: Gradient Agreement has been introduced in this book!
Dec 2018: One paper on collaborative intelligence accepted in ISQED conference.
Nov 2018: One paper on meta-learning accepted in NeurIPS 2018 meta-learning workshop. Link
Oct 2018: One paper on meta-learning accepted in AAAI 2019 conference. Link
May 2022: Micha is my new family member! 
August 2021: Mocha is my new family member! 
