Papers with Code 아카이브

Neural Architecture Search

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 26
보존된 평가 기록: 424

Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.

Image Credit : NAS with Reinforcement Learning

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/industryessentials/ymir

공식 코드

ALBench: A Framework for Evaluating Active Learning in Object Detection

https://github.com/innvariant/sparsity-experiments-2021

공식 코드

Experiments on Properties of Hidden Structures of Sparse Neural Networks

https://github.com/intellabs/hardware-aware-automated-machine-learning

공식 코드

Shears: Unstructured Sparsity with Neural Low-rank Adapter Search

https://github.com/intelligent-computing-lab-yale/neural-architecture-search-for-spiking-neural-networks

공식 코드

Neural Architecture Search for Spiking Neural Networks

https://github.com/ito-rafael/once-for-all-2

공식 코드

OFA$^2$: A Multi-Objective Perspective for the Once-for-All Neural Architecture Search

https://github.com/jack-willturner/nas-as-program-transformation-exploration

공식 코드

Neural Architecture Search as Program Transformation Exploration

https://github.com/jayaneetha/emoDARTS

공식 코드

emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition

https://github.com/jdai-cv/cm-nas

공식 코드

CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification

https://github.com/jeya-maria-jose/TransWeather

공식 코드

TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions

https://github.com/jhl-hust/circularkernel

공식 코드

Integrating Large Circular Kernels into CNNs through Neural Architecture Search

https://github.com/jhu-lcsr/costar_plan

공식 코드

The CoSTAR Block Stacking Dataset: Learning with Workspace Constraints

https://github.com/jihan4431/CAP

공식 코드

CAP: A Context-Aware Neural Predictor for NAS

https://github.com/jin-s13/COCO-WholeBody

공식 코드

ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild

https://github.com/jingjing-nlp/knas

공식 코드

KNAS: Green Neural Architecture Search

https://github.com/jovitalukasik/AG-Net

공식 코드

Learning Where To Look -- Generative NAS is Surprisingly Efficient

https://github.com/jovitalukasik/SVGe

공식 코드

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search

https://github.com/jovitalukasik/vs_gae

공식 코드

A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction

https://github.com/justincui03/dc_benchmark

공식 코드

DC-BENCH: Dataset Condensation Benchmark

https://github.com/kaist-dmlab/monaq

공식 코드

MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices

https://github.com/kalifou/data-driven-initialization-to-search

공식 코드

A Data-driven Approach to Neural Architecture Search Initialization

https://github.com/kcyu2014/eval-nas

공식 코드

Evaluating the Search Phase of Neural Architecture Search

https://github.com/kcyu2014/nas-landmarkreg

공식 코드

Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

https://github.com/kexin-kxzhang/optfusion

공식 코드

Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models

https://github.com/kirthevasank/nasbot

공식 코드

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

https://github.com/klightz/Firefly

공식 코드

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

https://github.com/lars-research/coldnas

공식 코드

ColdNAS: Search to Modulate for User Cold-Start Recommendation

https://github.com/lars-research/lrgnn

공식 코드

Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification

https://github.com/larsboecking/time_series_fingerprint

공식 코드

Utilizing Data Fingerprints for Privacy-Preserving Algorithm Selection in Time Series Classification: Performance and Uncertainty Estimation on Unseen Datasets

https://github.com/lcai-gz/manas

공식 코드

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

https://github.com/leeyeehoo/GenNAS

공식 코드

Generic Neural Architecture Search via Regression

https://github.com/leeyeehoo/gennas-zero

공식 코드

Extensible Proxy for Efficient NAS

https://github.com/leoiv/baxus

공식 코드

Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces

https://github.com/leoiv/bounce

공식 코드

Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces

https://github.com/leopard-ai/betty

공식 코드

Betty: An Automatic Differentiation Library for Multilevel Optimization

https://github.com/lephuoccat/Fisher-Information-NAS

공식 코드

Fisher Task Distance and Its Application in Neural Architecture Search

https://github.com/lephuoccat/Task-Aware-NAS

공식 코드

Task-Aware Neural Architecture Search

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.