Understanding Hyperdimensional Computing for Parallel Single-Pass Learning

Overview

Understanding Hyperdimensional Computing for Parallel Single-Pass Learning

Authors:

*: Equal Contribution

Introduction

This repo contains implementation of the group VSA and binary HDC model with random Fourier feature (RFF) encoding, described in the paper Understanding Hyperdimensional Computing for Parallel Single-Pass Learning.

Our RFF method and group VSA can outperform the state-of-the-art HDC model while maintaining hardware efficiency. For example, on MNIST,

Model 1-Epoch Accuracy 10-Epoch Accuracy Circuit-Depth Complexity
Percep. 94.3 % 94.3 % 1299
SOTA HDC NA 89.0 % 295
RFF HDC 95.4 % 95.4 % 295
RFF G(2^3)-VSA 96.3 % 95.7 % 405

Dependencies and Data

Numpy and PyTorch>=1.0.0 are required to run the implementation. Supported datasets include MNIST, Fashion-MNIST, CIFAR-10, ISOLET and UCI-HAR. We provide the ISOLET and UCI-HAR data in dataset folder.

Usage

Please create the ./encoded_data folder before running the following code.

$ python main.py [-h] [-lr LR] [-gamma GAMMA] [-epoch EPOCH] [-gorder GORDER] [-dim DIM] 
[-data_dir DATA_DIR] [-model MODEL]
optional arguments:
  -h, --help            show this help message and exit
  -lr LR                learning rate for optimizing class representative
  -gamma GAMMA          kernel parameter for computing covariance
  -epoch EPOCH          epochs of training
  -gorder GORDER        order of the cyclic group required for G-VSA
  -dim DIM              dimension of hypervectors
  -resume               resume from existing encoded hypervectors
  -data_dir DATA_DIR    Directory used to save encoded data (hypervectors)
  -dataset {mnist,fmnist,cifar,isolet,ucihar}
                        dataset (mnist | fmnist | cifar | isolet | ucihar)
  -raw_data_dir RAW_DATA_DIR
                        Raw data directory to the dataset
  -model {rff-hdc,linear-hdc,rff-gvsa}
                        feature and model to use: (rff-hdc | linear-hdc | rff-gvsa)

For example,

$ python main.py -gamma 0.3 -epoch 10 -gorder 8 -dim 10000 -dataset mnist -model rff-gvsa

Citation

If you find this repo useful, please cite:


Owner
Cornell RelaxML
Chris De Sa's Research Group
Cornell RelaxML
Computer Vision Paper Reviews with Key Summary of paper, End to End Code Practice and Jupyter Notebook converted papers

Computer-Vision-Paper-Reviews Computer Vision Paper Reviews with Key Summary along Papers & Codes. Jonathan Choi 2021 The repository provides 100+ Pap

Jonathan Choi 2 Mar 17, 2022
Predicting Auction Sale Price using the kaggle bulldozer auction sales data: Modeling with Ensembles vs Neural Network

Predicting Auction Sale Price using the kaggle bulldozer auction sales data: Modeling with Ensembles vs Neural Network The performances of tree ensemb

Mustapha Unubi Momoh 2 Sep 13, 2022
Image-popularity-score - A novel deep regression method for image scoring.

Image-popularity-score - A novel deep regression method for image scoring.

Shoaib ahmed 1 Dec 26, 2021
Code for "Unsupervised State Representation Learning in Atari"

Unsupervised State Representation Learning in Atari Ankesh Anand*, Evan Racah*, Sherjil Ozair*, Yoshua Bengio, Marc-Alexandre Côté, R Devon Hjelm This

Mila 217 Jan 03, 2023
chen2020iros: Learning an Overlap-based Observation Model for 3D LiDAR Localization.

Overlap-based 3D LiDAR Monte Carlo Localization This repo contains the code for our IROS2020 paper: Learning an Overlap-based Observation Model for 3D

Photogrammetry & Robotics Bonn 219 Dec 15, 2022
Implicit Graph Neural Networks

Implicit Graph Neural Networks This repository is the official PyTorch implementation of "Implicit Graph Neural Networks". Fangda Gu*, Heng Chang*, We

Heng Chang 48 Nov 29, 2022
[NeurIPS 2021] "Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems"

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems Introduction Multi-agent control i

VITA 6 May 05, 2022
Code and hyperparameters for the paper "Generative Adversarial Networks"

Generative Adversarial Networks This repository contains the code and hyperparameters for the paper: "Generative Adversarial Networks." Ian J. Goodfel

Ian Goodfellow 3.5k Jan 08, 2023
ULMFiT for Genomic Sequence Data

Genomic ULMFiT This is an implementation of ULMFiT for genomics classification using Pytorch and Fastai. The model architecture used is based on the A

Karl 276 Dec 12, 2022
Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides

Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides Project | This repo is the officia

CVSM Group - email: <a href=[email protected]"> 33 Dec 28, 2022
An essential implementation of BYOL in PyTorch + PyTorch Lightning

Essential BYOL A simple and complete implementation of Bootstrap your own latent: A new approach to self-supervised Learning in PyTorch + PyTorch Ligh

Enrico Fini 48 Sep 27, 2022
The PyTorch implementation of Directed Graph Contrastive Learning (DiGCL), NeurIPS-2021

Directed Graph Contrastive Learning Paper | Poster | Supplementary The PyTorch implementation of Directed Graph Contrastive Learning (DiGCL). In this

Tong Zekun 28 Jan 08, 2023
Adaptive Prototype Learning and Allocation for Few-Shot Segmentation (CVPR 2021)

ASGNet The code is for the paper "Adaptive Prototype Learning and Allocation for Few-Shot Segmentation" (accepted to CVPR 2021) [arxiv] Overview data/

Gen Li 91 Dec 23, 2022
EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings

SimCSE: Simple Contrastive Learning of Sentence Embeddings This repository contains the code and pre-trained models for our paper SimCSE: Simple Contr

Princeton Natural Language Processing 2.5k Dec 29, 2022
Benchmark VAE - Library for Variational Autoencoder benchmarking

Documentation pythae This library implements some of the most common (Variational) Autoencoder models. In particular it provides the possibility to pe

1.1k Jan 02, 2023
Establishing Strong Baselines for TripClick Health Retrieval; ECIR 2022

TripClick Baselines with Improved Training Data Welcome 🙌 to the hub-repo of our paper: Establishing Strong Baselines for TripClick Health Retrieval

Sebastian Hofstätter 3 Nov 03, 2022
Official Code for "Non-deep Networks"

Non-deep Networks arXiv:2110.07641 Ankit Goyal, Alexey Bochkovskiy, Jia Deng, Vladlen Koltun Overview: Depth is the hallmark of DNNs. But more depth m

Ankit Goyal 567 Dec 12, 2022
Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

(ACMMM 2021 Oral) SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment This repository shows two tasks: Face landmark detection and Fac

BoomStar 51 Dec 13, 2022
Progressive Image Deraining Networks: A Better and Simpler Baseline

Progressive Image Deraining Networks: A Better and Simpler Baseline [arxiv] [pdf] [supp] Introduction This paper provides a better and simpler baselin

190 Dec 01, 2022
Source code for the Paper: CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints}

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints Installation Run pipenv install (at your own risk with --skip-lo

Autonomous Learning Group 65 Dec 27, 2022