Table of Contents

• About This Project
• Some Statistics of the Papers
• The Chronological Listing of Papers

About This Project

This project aims to collect and summarize the AI-related papers for readers who are interested in AI research in academia. We plan to collect all the AI-related papers in the top-tier architecture conferences such as ISCA, MICRO and HPCA in recent years. Now, we have collected them in ISCA from 2015 to 2019 with some basic analysis. These papers will be listed below and you can find our brief summaries in "/Summarys/#year_of_the_paper/". We are glad to have your suggestions of anything about this project!

Some Statistics of the Papers

1. The yearly paper count (now only based on ISCA 2015-2019 statistics)

The trend of AI is generaly increasing. But now it slightly slow down in 2019. And we can find out that year 2018 takes almost half of the counts, implicating the hottest year of AI accelerators.

2. The countries and regions that contribute (now only based on ISCA 2015-2019 statistics)

America is definitely the origin area of most papers. China and North Korea are still two chasing character in AI research though they have done somg terrific ahievements.

3. Top researchers and their information (now only based on ISCA 2015-2019 statistics)

Here are the names appear most frequently on the collected papers. We collect thier public information and list below to help you find the leader researchers in this area.

Rank	Author	Counts of paper	Region	Lab or Corp.
1	Hadi Esmaeilzadeh	4	US	Alternative Computing Technologies (ACT) Laboratory, University of California
2	Mingcong Song	3	US	Intelligent Design of Efficient Architectures Laboratory (IDEAL), University of Florida
2	Reetuparna Das	3	US	EECS department, University of Michigan
2	Tao Li	3	US	Intelligent Design of Efficient Architectures Laboratory (IDEAL), University of Florida
2	Tianshi Chen	3	China	Cambricon Technologies Corporation Limited(寒武纪科技)
2	Yunji Chen	3	China	Institute of Computing Technology, Chinese Academy of Sciences
2	Zidong Du	3	China	Institute of Computing Technology, Chinese Academy of Sciences

The Chronological Listing of Papers

Now we list all the papers we have collected. If it is linkable, it is linked to the summary of the paper and the summaries are still updating.

ISCA 2015

	Title	Authors	Area	Organization
1	ShiDianNao: Shifting Vision Processing Closer to the Sensor	Zidong Du	China	ICT

ISCA 2016

	Title	Authors	Area	Organization
1	Cnvlutin: Ineffectual-Neuron-Free Deep Neural Network Computing	Jorge Albericio, Tayler Hetheringto	Canada	University of Toronto, University of British Columbia
2	ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars	Ali Shafiee, Vivek Srikumar	US	University of Utah，Hewlett Packard Labs
3	PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory	Ping Chi, Yuan Xie	US	University of California
4	EIE: Efficient Inference Engine on Compressed Deep Neural Network	Song Han, William J. Dally	US	Stanford University, NVIDIA
5	RedEye: Analog ConvNet Image Sensor Architecture for Continuous Mobile	Robert LiKamWa, Lin Zhong	US	Rice University
6	Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators	Brandon Reagen, David Brooks	US	Harvard University
7	Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks	Yu-Hsin Chen, Vivienne Sze	US	MIT, NVIDIA
8	Neurocube: A Programmable Digital Neuromorphic Architecture with High-Density 3D Memory	Duckhwan Kim, Saibal Mukhopadhyay	US	Georgia Institute of Technology
9	Cambricon: An Instruction Set Architecture for Neural Networks	Shaoli Liu, Tianshi Chen	China	CAS, Cambricon Ltd.
10	Energy Efficient Architecture for Graph Analytics Accelerators	Muhammet Mustafa Ozdal, Ozcan Ozturk	Turkey	Bilkent University
11	Accelerating Markov Random Field Inference Using Molecular Optical Gibbs Sampling Units	Siyang Wang, Alvin R. Lieberk	US	Duke University

ISCA 2017

	Title	Authors	Area	Organization
1	In-Datacenter Performance Analysis of a Tensor Processing Unit	Norman P. Jouppi	US	Google
2	Maximizing CNN Accelerator Efficiency Through Resource Partitioning	Yongming Shen	US	Stony Brook University
3	SCALEDEEP: A Scalable Compute Architecture for Learning and Evaluating Deep Networks	Swagath Venkataramani, Anand Raghunathan	US	Purdue University, Parallel Computing Lab, Intel Corporation
4	Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism	Jiecao Yu, Scott Mahlke	US	University of Michigan, ARM
5	SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks	Angshuman Parashar, William J. Dally	US	NVIDIA, MIT, UC-Berkeley, Stanford University
6	Stream-Dataflow Acceleration	Tony Nowatzki	US	University of California, University of Wisconsin
7	Understanding and Optimizing Asynchronous Low-Precision Stochastic Gradient Descent	Christopher De Sa, Kunle Olukotun	US	Stanford University

ISCA 2018

	Title	Authors	Area	Organization
1	A Configurable Cloud-Scale DNN Processor for Real-Time AI	Jeremy Fowers, Doug Burger	US	Microsoft
2	PROMISE: An End-to-End Design of a Programmable Mixed-Signal Accelerator for Machine- Learning Algorithms	Prakalp Srivastava, Mingu Kang	US	University of Illinois at Urbana-Champaign, IBM
3	Computation Reuse in DNNs by Exploiting Input Similarity	Marc Riera, Antonio Gonza ?lez	Spain	Universitat Polite ?cnica de Catalunya
4	GenAx: A Genome Sequencing Accelerator	Daichi Fujiki, Satish Narayanasamy	US	University of Michigan
5	Flexon: A Flexible Digital Neuron for Efficient Spiking Neural Network Simulations	Dayeol Lee, Jangwoo Kim	North Korea,US	Seoul National University, University of California
6	Space-Time Algebra: A Model for Neocortical Computation	James E. Smith	US	University of Wisconsin-Madison
7	Architecting a Stochastic Computing Unit with Molecular Optical Devices	Xiangyu Zhang, Alvin R. Lebeck	US	Duke University, Parabon Labs
8	RANA: Towards Efficient Neural Acceleration with Refresh-Optimized Embedded DRAM	Fengbin Tu, Shaojun Wei	China	Tsinghua University
9	Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks	Charles Eckert, Reetuparna Das	US	University of Michigan, Intel Corporation
10	RoboX: An End-to-End Solution to Accelerate Autonomous Control in Robotics	Jacob Sacks, Hadi Esmaeilzadeh	US	Georgia Institute of Technology, University of California, San Diego
11	EVA2: Exploiting Temporal Redundancy in Live Computer Vision	Mark Buckler, Adrian Sampson	US	Cornell University
12	Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision	Yuhao Zhu, Paul Whatmough	US	University of Rochetster, ARM Research
13	GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks	Amir Yazdanbakhsh, Hadi Esmaeilzadeh	US	Georgia Institute of Technology, UC San Diego, Qualcomm Technologies, Inc.
14	SnaPEA: Predictive Early Activation for Reducing Computation in Deep Convolutional Neural Networks	Vahideh Akhlaghi, Hadi Esmaeilzadeh	US	Georgia Institute of Technology, UC San Diego, Qualcomm Technologies, Inc.
15	UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition	Kartik Hegde, Christopher W. Fletche	US	University of Illinois at Urbana-Champaign, NVIDIA
16	Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation	Eunhyeok Park, Sungjoo Yoo	North Korea	Seoul National University
17	Prediction Based Execution on Deep Neural Networks	Mingcong Song, Tao Li	US	University of Flirida
18	Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Network	Hardik Sharma, Hadi Esmaeilzadeh	US	Georgia Institute of Technology, University of California
19	Gist: Efficient Data Encoding for Deep Neural Network Training	Animesh Jain, Gennady Pekhimenko	US,Canada	Microsoft Research, University of Toronto, Univerity of Michigan
20	The Dark Side of DNN Pruning	Reza Yazdani, Antonio Gonza ?lez	Spain	Universitat Polite ?cnica de Catalunya

ISCA 2019

	Title	Authors	Area	Organization
1	3D-based Video Recognition Acceleration by Leveraging Temporal Locality	Huixiang Chen, Tao Li	US	University of Florida
2	A Stochastic-Computing based Deep Learning Framework using Adiabatic Quantum-Flux-Parametron Superconducting Technology	Ruizhe Cai, Ao Ren, Nobuyuki Yoshikawa, Yanzhi Wang	US	Northeastern University
3	Accelerating Distributed Reinforcement Learning with In-Switch Computing	Youjie Li, Jian Huang	US	UIUC
4	Eager Pruning: Algorithm and Architecture Support for Fast Training of Deep Neural Networks	Jiaqi Zhang, Tao Li	US	University of Florida
5	Laconic Deep Learning Inference Acceleration	Sayeh Sharify, Andreas Moshovos	Canada	University of Toronto
6	MnnFast: A Fast and Scalable System Architecture for Memory-Augmented Neural Networks	Hanhwi Jang, Jangwoo Kim	North Korea	POSTECH, Seoul National University
7	Sparse ReRAM Engine: Joint Exploration of Activation and Weight Sparsity in Compressed Neural Networks	Tzu-Hsien Yang	China Twain	National Taiwan University, Academia Sinica, Macronix International Co., Ltd.
8	TIE: Energy-efficient Tensor Train-based Inference Engine for Deep Neural Network	Chunhua Deng, Bo Yuan	US	Rutgers University
9	FloatPIM_ in-memory acceleration of deep neural network training with high precision	Mohsen Imani, Tajana Rosing	US	UC San Diego
10	Cambricon-F_ machine learning computers with fractal von neumann architecture	Yongwei Zhao, Yunji Chen	China	ICT, Cambricon
11	Master of none acceleration_ a comparison of accelerator architectures for analytical query processing	Andrea Lottarini, Martha A. Kim	US	Google, Columbia University