Peter Jin

Computer Science · Purdue University West Lafayette

Mid career · publishing since 2015

Advanced Neural Network Applications Domain Adaptation and Few-Shot Learning Stochastic Gradient Optimization Techniques Reinforcement Learning in Robotics Sparse and Compressive Sensing Techniques

Publications

Citations

718

Est. group size

—

Recurring co-author estimate

Active years

Publishing since 2015

Research summary

AI-generated

Peter Jin's research focuses on making deep learning more efficient and practical, including designing neural network architectures that use fewer computational resources, scaling distributed training across many machines, and applying these methods to tasks like object detection for self-driving cars, medical image analysis, and reinforcement learning for navigation. The work sits at the intersection of efficient machine learning systems and applied computer vision.

Efficient neural network architecturesDistributed and large-scale deep learningComputer vision for autonomous drivingDomain adaptation and few-shot learningReinforcement learning

Publication output was concentrated between 2016 and 2019, followed by a multi-year gap and only sporadic activity resuming around 2024-2026, indicating a slowing and irregular publication cadence over the last decade.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence

Publications per year over the last 10 years — averaging 0.8/year recently

Recent publications

A Novel Domain Adaptation Framework for Medical Image Segmentation
Lecture notes in computer science · 2019
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
2018
SqueezeNext: Hardware-Aware Neural Network Design
2018
Spatially Parallel Convolutions.
International Conference on Learning Representations · 2018
Regret Minimization for Partially Observable Deep Reinforcement Learning
International Conference on Learning Representations · 2018
Learning to Navigate in Visual Environments
eScholarship (California Digital Library) · 2018
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
arXiv (Cornell University) · 2017
Regret Minimization for Partially Observable Deep Reinforcement Learning
arXiv (Cornell University) · 2017
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
arXiv (Cornell University) · 2016
How to scale distributed deep learning?
arXiv (Cornell University) · 2016

Publishes in

arXiv (Cornell University)×7
International Conference on Learning Representations×2
Society for Industrial and Applied Mathematics eBooks×2
Lecture notes in computer science×1
eScholarship (California Digital Library)×1

Similar researchers

By research-topic overlap

Zijian He
Computer Science · Purdue University West Lafayette
Jianyang Gu
Computer Science · The Ohio State University
Xiangyu Zhang
Computer Science · Purdue University West Lafayette
Shujon Naha
Computer Science · Indiana University
Hongyang Li
Computer Science · Purdue University West Lafayette

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 20, 2026.

Claim or correct this profile