526互联

Learning

C-pointer Learning

# 基础 ## 指针类型 ### 静态/全局内存 指在内存空间中的全局/静态数据区的指针变量 ### 自动内存 即局部作用域的指针，只有在函数被调用时才创建。 ### 动态内存 在堆区动态创建的指针变量，在不使用时需要即是释放该部分内存空间。 ## 特殊指针 ### NULL指针 在指针变量中，初始 ......
C-pointer Learning pointer

Off-Policy Deep Reinforcement Learning without Exploration

**发表时间：**2019（ICML 2019） **文章要点：**这篇文章想说在offline RL的setting下，由于外推误差（extrapolation errors）的原因，标准的off-policy算法比如DQN，DDPG之类的，如果数据的分布和当前policy的分布差距很大的话，那就 ......
Reinforcement Exploration Off-Policy Learning without

《AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks》特征交叉论文阅读

背景 这是一篇利用多头attention机制来做特征交叉的论文 模型结构 AutoInt的模型结构如上图所示，搞模型包含 Embedding Layer、Interacting Layer、Output Layer三个部分，其中Embedding Layer和Output Layer和普通模型没什么 ......
Self-Attentive Interaction Attentive Automatic Learning

【图像数据增强】Image Data Augmentation for Deep Learning: A Survey

| 原始题目 | Image Data Augmentation for Deep Learning: A Survey | | | | | 中文名称 | 深度学习的图像数据增强:综述 | | 发表时间 | 2022年4月19日 | | 平台 | arXiv | | 来源 | 南京大学 | | 文章 ......
Augmentation Learning 图像 数据 Survey

Jan 2023-Prioritizing Samples in Reinforcement Learning with Reducible Loss

#1 Introduction 本文建议根据样本的可学习性进行抽样，而不是从经验回放中随机抽样。如果有可能减少代理对该样本的损失，则认为该样本是可学习的。我们将可以减少样本损失的数量称为其可减少损失(ReLo)。这与Schaul等人[2016]的vanilla优先级不同，后者只是对具有高损失的样本给 ......
Reinforcement Prioritizing Reducible Learning Samples

Oracle 集合-Learning-1

集合-Test1 bulk collect into 批量插入，可用limit 限制插入行数 type ... is table of DataType Index by binary_Integer 其中 index by binary_integer 在定义schema级 type 时没有使用， ......
Learning Oracle

Short-Term Plasticity Neurons Learning to Learn and Forget

郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！ Proceedings of the 39th International Conference on Machine Learning ......
Short-Term Plasticity Learning Neurons Forget

论文阅读笔记《Training Socially Engaging Robots Modeling Backchannel Behaviors with Batch Reinforcement Learning》

Training Socially Engaging Robots Modeling Backchannel Behaviors with Batch Reinforcement Learning 训练社交机器人：使用批量强化学习对反馈信号行为进行建模 发表于TAC 2022。 Hussain N, ......
Reinforcement Backchannel Behaviors Training Socially

Robust Deep Reinforcement Learning through Adversarial Loss

郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！ 35th Conference on Neural Information Processing Systems (NeurIPS 2021) Abstract 最近的研究表明，深度强化学习智能体很容易受到智能体输入上的小对抗性扰动的影响 ......
Reinforcement Adversarial Learning through Robust

【五期邹昱夫】CCF-A（NeurIPS'19）Inverting gradients-how easy is it to break privacy in federated learning?

"Geiping J, Bauermeister H, Dröge H, et al. Inverting gradients-how easy is it to break privacy in federated learning?[J]. Advances in Neural Informat ......
gradients-how Inverting gradients federated learning

prompt learning如何计算损失的

在prompt learning中,对于一个类别的多个候选词,损失函数通常会计算所有词的logit和,并与真实标签作比较。以情感分类为例: 假设正面类别有两个候选词:“positive”和“optimistic”。负面类别有两个候选词:“negative”和“pessimistic”。 然后模型会计 ......
learning 损失 prompt

论文解读（ID-MixGCL）《ID-MixGCL: Identity Mixup for Graph Contrastive Learning》

论文信息 论文标题：ID-MixGCL: Identity Mixup for Graph Contrastive Learning论文作者：Gehang Zhang.....论文来源：2023 aRxiv论文地址：download 论文代码：download视屏讲解：click 介绍 ......
ID-MixGCL MixGCL Contrastive Identity Learning

Heuristic-Guided Reinforcement Learning

**发表时间：**2021 (NeurIPS 2021) **文章要点：**这篇文章提出了一个Heuristic-Guided Reinforcement Learning (HuRL)的框架，用domain knowledge或者offline data构建heuristic，将问题变成一个sho ......
Heuristic-Guided Reinforcement Heuristic Learning Guided

Medicine River ————-Learning journals 9

Dear dairy. 2020 6 May Hey, Harlan, long time no see. How have you been lately? I've been quite busy lately. I hope you don't blame me for not coming ......
Medicine Learning journals River

LLL(Life Long Learning)&灾难性遗忘(Catastrophic Forgetting)

LLL(Life Long Learning)&灾难性遗忘(Catastrophic Forgetting) https://www.youtube.com/watch?v=Y9Jay_vxOsM Life Long Learning 通常机器学习中，单个模型只解决单个或少数几个任务。对于新的任务， ......
灾难性 Catastrophic Forgetting 灾难 Learning

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！ NeurIPS 2020 ......
Reinforcement Perturbations Observations Adversarial Learning

李宏毅meta learning笔记

学习如何学习 其实就是学习模型本身，模型的超参数 定义一个function，输入是一堆训练任务，输出是一个模型，这个和传统的机器学习没有本质不同 所以也是分成三步， 定义学什么，和相应的学习模型，meta learning本身也是有meta的。。。。。。 定义loss函数 用优化算法求解，但是这个L ......
learning 笔记 meta

Learning A Single Network for Scale-Arbitrary Super-Resolution

Learning A Single Network for Scale-Arbitrary Super-Resolution abstract 现有的single image SR网络是为具有特定整数比例因子（例如，×2/3/4）的图像开发的，无法处理非整数和非对称 SR。 在本文中，作者建议从特定 ......
Super-Resolution Scale-Arbitrary Resolution Arbitrary Learning

Teachable Reinforcement Learning via Advice Distillation

**发表时间：**2021 (NeurIPS 2021) **文章要点：**这篇文章提出了一种学习policy的监督范式，大概思路就是先结构化advice，然后先学习解释advice，再从advice中学policy。这个advice来自于外部的teacher，相当于一种human-in-the-l ......
Reinforcement Distillation Teachable Learning Advice

论文阅读-sparse gpu kernels for deep learning

论文地址：https://ieeexplore.ieee.org/document/9355309 源码地址：https://github.com/google-research/sputnik 背景 深度神经网络由大量的矩阵乘法运算和卷积运算组成，这些运算中使用的矩阵可以转化成稀疏矩阵，同时不损失 ......
learning kernels sparse 论文 deep

Deep Dynamics Models for Learning Dexterous Manipulation

**发表时间：**2019 (CoRL 2019) **文章要点：**文章提出了一个online planning with deep dynamics models (PDDM)的算法来学习Dexterous multi-fingered hands，大概意思就是学习拟人的灵活的手指操控技巧。大概 ......
Manipulation Dexterous Dynamics Learning Models

2、题目：The Informed Design Teaching and Learning Matrix

期刊信息 （1）作者：Crismond, David P. （2）期刊：Journal of Engineering Education, 2012, 101(4): 738–797 （3）DOI：10.1002/j.2168-9830.2012.tb01127.x （4）ISSN：10694730 ......
Informed Teaching Learning 题目 Design

论文阅读笔记《Residual Physics Learning and System Identification for Sim to real Transfer of Policies on Buoyancy Assisted Legged Robots》

Residual Physics Learning and System Identification for Sim to real Transfer of Policies on Buoyancy Assisted Legged Robots 发表于2023年。论文较新，未找到发表期刊。 基于浮 ......
Identification Residual Learning Buoyancy Assisted

论文阅读笔记《Stochastic Grounded Action Transformation for Robot Learning in Simulation》

Stochastic Grounded Action Transformation for Robot Learning in Simulation 发表于IROS 2020(CCF C) 模拟中机器人学习的随机接地动作转换 Desai S, Karnan H, Hanna J P, et al. ......
Transformation Stochastic Simulation Grounded Learning

论文阅读笔记《Grounded Action Transformation for Robot Learning in Simulation》

Grounded Action Transformation for Robot Learning in Simulation 发表于AAAI 2017 仿真机器人学习中的接地动作变换 Hanna J, Stone P. Grounded action transformation for robo ......
Transformation Simulation Grounded Learning 笔记

Representation Learning for Attributed Multiplex Heterogeneous Network

Cen Y., Zou X., Zhang J., Yang H., Zhou J. and Tang J. Representation learning for attributed multiplex heterogeneous network. KDD, 2019. 概 本文在 Attrib ......
Representation Heterogeneous Attributed Multiplex Learning

2022AAAI_Semantically Contrastive Learning for Low-light Image Enhancement(SCL_LLE)

1. motivation 利用语义对比学习 2. network (1) 输入的是低光图像首先经过图像增强的网络（Zero-DCE), 再将它传入语义分割网络中 （2）语义分割网络用的是DeepLabv3+ ......
AAAI_Semantically Semantically Contrastive Enhancement Low-light

MEMORY REPLAY WITH DATA COMPRESSION FOR CONTINUAL LEARNING--阅读笔记

MEMORY REPLAY WITH DATA COMPRESSION FOR CONTINUAL LEARNING--阅读笔记 摘要： 在这项工作中，我们提出了使用数据压缩（MRDC）的内存重放，以降低旧的训练样本的存储成本，从而增加它们可以存储在内存缓冲区中的数量。观察到压缩数据的质量和数量之间 ......
COMPRESSION CONTINUAL LEARNING 笔记 MEMORY

Deep-Learning-Based Spatio-Temporal-Spectral Integrated Fusion of Heterogeneous Remote Sensing Images

Deep-Learning-Based Spatio-Temporal-Spectral Integrated Fusion of Heterogeneous Remote Sensing Images abstract 为了解决STF中的生成heterogeneous images问题: 为此，本 ......
Spatio-Temporal-Spectral Deep-Learning-Based Heterogeneous Integrated Learning

Medicine River-------------Learning Journals 8

htttp://www.enotes.com ......
Medicine Learning Journals River
共370篇  :10/13页 首页上一页10下一页尾页