engineering thinking teaching learning
深度学习应用篇-元学习[16]：基于模型的元学习-Learning to Learn优化策略、Meta-Learner LSTM
# 深度学习应用篇-元学习[16]：基于模型的元学习-Learning to Learn优化策略、Meta-Learner LSTM # 1.Learning to Learn Learning to Learn by Gradient Descent by Gradient Descent 提出了 ......
[Fullstack] Learning note for Fullstack developer - FrontendMaster
Command Line 1. Navigate to your home directory cd ~ 2. Make a directory call "temp" mkdir temp 3. Move into temp cd temp 4. List the idrectory conten ......
English Learning Articles 2022-06-11 Your teen wants to get in shape this summer? What to say and when to worry
Your teen wants to get in shape this summer? What to say and when to worry | CNN If your children say they want to start exercising or working out mor ......
COMP9417 Machine Learning 机器学习
COMP9417 - Machine LearningHomework 1: Regularized Regression & NumericalOptimizationIntroduction In this homework we will explore some algorithms for ......
会议主题：Federated Learning in Healthcare
主题: Federated Learning in Healthcare日期: 2023-06-07 08:47:33录制文件：https://meeting.tencent.com/v2/cloud-record/share?id=ec65d257-69ab-4807-b670-9312fb2a5 ......
Supervised Machine Learning Regression and Classification - Week 1
# 1. 机器学习定义 > Field of study that gives computers the ability to learn without being explicitly programmed. -- Arthur Samuel(1959) :自动调整学习速率 (Learning Rate)
# 1. 自适应学习率调整(Adaptive Learning Rate) ## 1.1 为什么需要调整学习率 首先认识一个现象.Training stuck ≠ Small Gradient 训练卡住的原因不一定是因为 gradient 太小,即critical point，也有可能是因为振荡. ......
Learning to Pre-train Graph Neural Networks 学习如何预训练GNN
 ![image](https://img2023.cnblogs.com/blog/2992171/20 ......
解决使用yarn安装依赖出现“The engine "node" is incompatible with this module. Expected version "^14.18.0 || ^16.14.0 || >=18.0.0". Got "17.9.0"”的问题
# 1、问题描述 某天在使用`yarn`安装依赖的时候，突然出现如下错误导致安装依赖终止： **The engine "node" is incompatible with this module. Expected version "^14.18.0 || ^16.14.0 || >=18.0.0 ......
gdb_learn
# GDB ## 基本gdb命令 ### 运行有关命令 ```shell run（简写r）： 运行程序，当遇到断点后，程序会在断点处停止运行，等待用户输入下一步的命令。 continue（简写c）：继续执行，到下一个断点处（或运行结束） next（简写n）： 单步跟踪程序，当遇到函数调用时，直接调用 ......
Reward Modelling（RM）and Reinforcement Learning from Human Feedback（RLHF）for Large language models（LLM）技术初探
Reward Modelling（RM）and Reinforcement Learning from Human Feedback（RLHF）for Large language models（LLM）技术初探 ......
Rogue7: Rogue Engineering-Station Attacks on S7 Simatic PLCs 阅读笔记
 ### **基本信息** **题目：** **Rogue7: Rogue Engineering-Sta ......
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
[TOC] > [Qiu R., Huang Z., Ying H. and Wang Z. Contrastive learning for representation degeneration problem in sequential recommendation. WSDM, 2022.] ......
Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning论文阅读笔记
## 摘要 连续学习过程中的稳定性-可塑性权衡是一个重要的问题。作者提出了Auxiliary Network Continual Learning (ANCL)，通过auxiliary network提高了模型的可塑性。 ## 方法 ### The Formulation of Auxiliary ......
火山引擎DataLeap的Catalog系统搜索实践（三）：Learning to rank与后续工作
Learning to rank Learning to rank主要分为数据收集，离线训练和在线预测三个部分。搜索系统是一个Data-driven system，因此火山引擎DataLeap的Catalog系统设计之初就需要考虑数据收集。收集的数据可以用来评估和提升搜索的效果。数据收集和在线预测前 ......
使用 ChatGPT 的 7 个技巧 | Prompt Engineering 学习笔记
### 概述 前段时间在 [DeepLearning](https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/) 学了一门大火的 Prompt 的课程，吴恩达本人授课，讲的通俗易懂，感觉 ......
Some details for the Shell which I think is important
拼接字符串, 在定义好变量之后, 输出时候的拼接, 注意无意输出一些空格 。 比如: #!/bin/bash a1="China" a2="${a1}, Japan and Korean are the three important countries in east asia. \n" a3=" ......
Reinforcement Learning之Q-Learning - Python实现
- **算法特征** ①. 以真实reward训练Q-function; ②. 从最大Q方向更新policy $\pi$ - **算法推导** **Part Ⅰ: RL之原理** 整体交互流程如下, 定义策略函数(policy)$\pi$, 输入为状态(state)$s$, 输出为动作(action ......
WebSocket-Learning-1
#### WebSocket ##### 1.什么是WebSocket >> WebSocket 是一种通讯协议，目标就是替代XmlHttpRequest 和长期轮询的解决方案。应用在实时弹幕、消息推送、棋牌游戏、聊天等需要及时通讯的场景。 ##### 2.WebSocket 连接有两个阶段 >>握 ......
强化学习基础篇[2]：SARSA、Q-learning算法简介、应用举例、优缺点分析
# 强化学习基础篇[2]：SARSA、Q-learning算法简介、应用举例、优缺点分析 # 1.SARSA SARSA（State-Action-Reward-State-Action）是一个学习马尔可夫决策过程策略的算法，通常应用于机器学习和强化学习学习领域中。它由Rummery 和 Niran ......
Machine Learning 【note_02】
# note_02 Keywords: Classification, Logistic Regression, Overfitting, Regularization ## 1 Motivation Classification: - "binary classification": $y$ ca ......
Machine Learning 【note_01】
Declaration (2023/06/02): This note is the first note of a series of machine learning notes. At present, the main learning resource is *the 2022 Andre ......
MySQL 存储引擎（storage engine)
show engines ; https://dev.mysql.com/doc/refman/5.7/en/storage-engines.html 创建表时（CREATE TABLE Statement）可以指定存储引擎类型 简介 InnoDB: The default storage engi ......
[网鼎杯 2020 朱雀组]Think Java——wp
##源文件代码审计 这里使用IDEA打开 ###Test.class  ![](https://img2023.cn ......
论文阅读 | Learn from Others and Be Yourself in Heterogeneous Federated Learning
**在异构联邦学习中博采众长做自己** 代码：https://paperswithcode.com/paper/learn-from-others-and-be-yourself-in **摘要** 联邦学习中有异质性问题和灾难性遗忘。首先，由于非I.I.D（相同独立分布）数据和异构体系结构，模型在 ......
April 2023-Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation
本文基于深度q网络算法提出了记忆高效的强化学习算法来缓解这一问题。通过将目标q网络中的知识整合Knowledge Consolidation到当前q网络中，所提算法减少了遗忘并保持了较高的样本效率。 ......