526互联

unsupervised ego-motion learning motion

阅读文献《SCNet：Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System》

该文献的作者是清华大学的高飞飞老师，于2019年11月发表在IEEE COMMUNICATIONS LETTERS上。 文章给出了当用户位置到信道的映射是双射时上行到下行的确定映射函数；还提出了一个**稀疏复值神经网络( sparse complex-valued neural network，SC ......
Learning-Based Prediction 文献 Learning Downlink

文献阅读《AcsiNet: Attention-Based Deep Learning Network for CSI Prediction in FDD MIMO Systems》

这篇文献的作者是南华大学的林文斌老师，于2023年3月3日发表在IEEE WIRELESS COMMUNICATIONS LETTERS。 文章直接对上行 CSI 矩阵使用离散傅里叶逆变换进行压缩，然后将其输入一个基于注意力（attention-based）的深度学习网络，该网络可以专注于关键的 C ......
Attention-Based Prediction Attention 文献 Learning

GCR Gradient Coreset based Replay Buffer Selection for Continual Learning

GCR: Gradient Coreset based Replay Buffer Selection for Continual Learning 摘要：本文提出了一种创新的重放缓冲区选择和更新策略，梯度核心集重放（GCR），使用一种设计优化标准。 该方法选择和维持一个“coreset” ，它非常 ......
Continual Selection Gradient Learning Coreset

论文解读《Automatically discovering and learning new visual categories with ranking statistics》

论文信息 论文标题：Automatically discovering and learning new visual categories with ranking statistics论文作者：K. Han, Sylvestre-Alvise Rebuffi, Sébastien Ehrhard ......
Automatically discovering categories statistics learning

五天学会Deep Learning

五天学完deep learning。。。。。。是时候来证明chatGPT和new bing的能力了。。。。。。 DAY1 Sigmoid function Sigmoid 函数是一种常用的激活函数，它将输入值映射到 0 和 1 之间。它的公式为 f(x) = 1 / (1 + e^-x)。Sigmo ......
Learning Deep

论文解读（PAWS）《Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples》

论文信息 论文标题：Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples论文作者：Mahmoud Assran, Mathi ......
Non-Parametrically Semi-Supervised Parametrically Assignments Predicting

迁移学习（CLDA）《CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation》

论文信息 论文标题：CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation论文作者：Ankit Singh论文来源：NeurIPS 2021论文地址：download 论文代码：download视屏讲解：click 1 简介 ......
CLDA Semi-Supervised Contrastive Adaptation Supervised

FastGCN Fast Learning with Graph Convolutional Networks via Importance Sampling

Chen J., Ma T. and Xiao C. FastGCN: fast learning with graph convolutional networks via importance sampling. ICLR, 2018. 概 一般的 GCN 每层通常需要经过所有的结点的 prop ......
Convolutional Importance Learning Networks Sampling

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

Li Q., Han Z. and Wu X. Deeper insights into graph convolutional networks for semi-supervised learning. AAAI, 2018. 概 本文分析了 GCN 的实际上就是一种 Smoothing, 但是 ......
Semi-Supervised Convolutional Supervised Insights Networks

Pytorch深度学习全流程代码框架——Base Codes for Deep Learning Using Pytorch

# 导入必要的库 import torch import torch.nn as nn import torch.optim as optim from torch.utils.data import DataLoader, Dataset # 定义超参数 epochs = 10 # 训练轮数 lr ......
Pytorch 框架 深度 Learning 流程

scikit-learn 中 Boston Housing 数据集问题解决方案

scikit-learn 中 Boston Housing 数据集问题解决方案 在部分旧教程或教材中是 sklearn，现在【2023】已经变更为 scikit-learn 作用：开源机器学习库，支持有监督和无监督学习。它还提供了用于模型拟合、数据预处理、模型选择、模型评估和许多其他实用程序的各种工 ......
scikit-learn 解决方案 Housing 方案 数据

基于强化学习（Q-learning算法）的需求响应动态定价研究

代码关键词：需求响应 强化学习 动态定价 编程语言：python平台 主题：16、基于强化学习（Q-learning算法）的需求响应动态定价研究 代码内容： 代码提出了一种考虑服务提供商（SP）利润和客户（CUs）成本的分层电力市场能源管理动态定价DR算法。 用强化学习（RL）描述了动态定价问题为离 ......
算法 Q-learning learning 需求 动态

强化学习 Reinforcement Learning

强化学习 Reinforcement Learning 强化学习是一种机器学习思想，其关心一个智能体如何采取行动以达到最大化激励回报。 基本的强化学习模型以马尔可夫决策过程建模。 马尔可夫决策过程 Markov Decision Process 系统要素 A 行动空间； S状态空间； $P^a_{s ......
Reinforcement Learning

【论文阅读笔记】Distiling Causal Effect of Data in Class-Incremental Learning

Author: Hanwang Zhang, Xinting Hu Create_time: April 24, 2022 11:01 AM Edited_by: Huang Yujun Publisher: CVPR 2021 Org: Nanyang Technological Universi ......
Class-Incremental Incremental Distiling Learning 笔记

【论文阅读笔记】Learning to Prompt for Continual Learning

Create_time: April 27, 2022 5:21 PM Edited_by: Huang Yujun Org: Google Research, Northeastern University Learning to Prompt for Continual Learning [38 ......
Learning Continual 笔记 Prompt 论文

【论文阅读笔记】iCaRL: Incremental Classifier and Representation Learning

Author: Alexander Kolesnikov Key_words: nearest-mean-of-exemplar rule, prioritized exampler selection,representation learning Create_time: September 1 ......
Representation Incremental Classifier Learning 笔记

迁移学习（）《Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation》

论文信息 论文标题：Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation论文作者：Taekyung Kim论文来源：2020 ECCV论文地址 ......
Semi-supervised Adaptation supervised Alignment Learning

MULTIINSTRUCT: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning

指令调优是一种新的学习范式，它可以根据指令指定的任务对预先训练好的语言模型进行微调，在各种自然语言处理任务中显示出良好的零目标性能。然而，对于视觉和多模态任务，它仍然没有被探索。在这项工作中，我们介绍了multiinstruction，这是第一个多模态指令调优基准数据集，由47个不同的多模态任务组成 ......
MULTIINSTRUCT Instruction Multi-Modal Improving Zero-Shot

利用强化学习Q-Learning实现最短路径算法

如果你是一名计算机专业的学生，有对图论有基本的了解，那么你一定知道一些著名的最优路径解，如Dijkstra算法、Bellman-Ford算法和a*算法(A-Star)等。 这些算法都是大佬们经过无数小时的努力才发现的，但是现在已经是人工智能的时代，强化学习算法能够为我们提出和前辈一样好的解决方案吗? ......
算法 Q-Learning Learning

异常检测 | 迁移学习《Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning》

论文信息 论文标题：Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning论文作者：Abhay Rawat, Isha Dua, Saurav Gupta, Rahul Tallamraju ......
Contrastive Supervised Detection Learning Anomaly

ubuntu安装python环境scikit-learn低版本

Ubuntu默认使用的是python3.8，要安装插件需要先安装几个依赖包 安装uwsgi需要安装gcc python3.8-dev python-dev 安装scikit-learn旧版本需要安装python3-sklearn python3-sklearn-lib这两个包，python3.8支持 ......
scikit-learn 版本 环境 ubuntu python

Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation

**发表时间：**2021（ICML 2021） **文章要点：**这篇文章提出了demonstration-conditioned reinforcement learning (DCRL)来做Few-Shot Imitation，将demonstration和当前状态作为输入，通过强化学习最大化 ......
Demonstration-Conditioned Demonstration Reinforcement Conditioned Imitation

About Spoken word poetry-----Learning journals6

In this world, poetry has many forms of expression, short and long, written on paper or carved on walls, but this time our focus is on Spoken word poe ......
journals6 Learning journals Spoken poetry

About Spoken word poetry-----Learning journals 6

In this world, poetry has many forms of expression, short and long, written on paper or carved on walls, but this time our focus is on Spoken word poe ......
Learning journals Spoken poetry About

About spoken word poetry----Learning journals 6

In this world, poetry has many forms of expression, short and long, written on paper or carved on walls, but this time our focus is on Spoken word poe ......
Learning journals spoken poetry About

Do you know the bitwise sum sample demonstrated in "Neural Networks and Deep Learning" by autor Michael Nielsen?

Do you know the bitwise sum sample demonstrated in "Neural Networks and Deep Learning" by autor Michael Nielsen? Yes, I am familiar with the bitwise s ......
quot demonstrated Networks Learning bitwise

论文阅读笔记《Sim-to-real learning for bipedal locomotion under unsensed dynamic loads》

发表于ICRA 2022 无感知动态负载下双足运动的虚实迁移学习 ### 背景 机器人携带负载时的运动控制问题还没有得到充分的研究，尤其是动态负载。 在这项工作中，我们特别感兴趣的是动态载荷，比如一个附加的推车或液体容器，而不是简单的静态载荷，比如刚性附着的固定质量。 ......
Sim-to-real locomotion learning unsensed bipedal

EECS 280 Project 5: Machine Learning

EECS 280 Project 5: Machine LearningDue 8:00pm Tuesday April 18, 2023. You may work alone or with a partner (partnership guidelines).Winter 2023 relea ......
Learning Project Machine EECS 280

GNN-learning-notes

GNN 学习笔记 Datetime: 2023-04-01T16:28+08:00 Categories: MachineLearning 初学者一定要看：【GNN 入门】综述篇 - 知乎用户 MxLVSX 的文章 - zhihu.com，包括频域和空域、任务类型、经典模型。 最早的 GNN，介于迭 ......
GNN-learning-notes learning notes GNN

迁移学习《Efficient and Robust Pseudo-Labeling for Unsupervised Domain Adaptation》

论文信息 论文标题：Efficient and Robust Pseudo-Labeling for Unsupervised Domain Adaptation论文作者：Hochang Rhee、Nam Ik Cho论文来源：2019——ICML论文地址：download 论文代码：downloa ......
Pseudo-Labeling Unsupervised Adaptation Efficient Labeling
共510篇  :15/17页 首页上一页15下一页尾页