文章目录
- 1.教育
- 2.人物
- 3.前沿
- 3.1 戴琼海:发现、理解与创造
- 3.2 CoRL 2021 Awards
- 3.3 IJCLR Zhi-Hua Zhou: "From Pure Learning to Learning & Reasoning"
- 3.4 UC伯克利---每个神经网络,都是一个高维向量
- 3.5 2021深度学习方向---知乎
- 3.6 字节跳动---视频抠像工具---RNN
- 3.7 飞桨图像识别套件PaddleClas
- 3.8 Small Data’s Big AI Potential
- 3.9 Bilingualism Comes Naturally to Our Brains
- 3.10 内在触感 强化学习 机械手
- 3.11 大脑学习算法模型模拟反向传播过程
- 4.学习资源
- 5.职场
- 6.机构、网站
- 7.数据集
1.教育
1.1 Albert Einstein
1.2 论学术与学术标准—李伯重
1.3 康毅滨
1.4 亲子教育
2.人物
2.1 清华大学本科生特等奖学金答辩
2.2 John von Neumann
The Unparalleled Genius of John von Neumann—Jørgen Veisdal
2.3 华科团队EDA全球冠军
2.4 Jure Leskovec
研究方向:
applied machine learning for large interconnected systems focusing on modeling complex, richly-labeled relational structures, graphs, and networks for systems at all scales, from interactions of proteins in a cell to interactions between humans in a society. Applications include commonsense reasoning, recommender systems, computational social science, and computational biology with an emphasis on drug discovery.
Paper—How Powerful are Graph Neural Networks?
2.5 Yann LeCun
法国极客Yann LeCun:掌舵Facebook人工智能 | 完美人物志
Yann LeCun专访:我不觉得自己有天分,但是我一直往聪明人堆里钻
2.6 何恺明
Masked Autoencoders Are Scalable Vision Learners
2.7 Gábor Fodor
2.8 柳叶熙
3.前沿
3.1 戴琼海:发现、理解与创造
3.2 CoRL 2021 Awards
3.3 IJCLR Zhi-Hua Zhou: “From Pure Learning to Learning & Reasoning”
YouTube—1st International Joint Conference on Learning & Reasonin
YouTube—IJCLR 2021 Keynote Talk by Zhi-Hua Zhou: “From Pure Learning to Learning & Reasoning”
3.4 UC伯克利—每个神经网络,都是一个高维向量
UC伯克利发现「没有免费午餐定理」加强版:每个神经网络,都是一个高维向量—图灵人工智能
Neural Tangent Kernel Eigenvalues Accurately Predict Generalization
3.5 2021深度学习方向—知乎
2021年深度学习哪些方向比较新颖,处于上升期或者朝阳阶段,没那么饱和,比较有研究潜力?—陀飞轮 、Zhifeng 、谢凌曦
3.6 字节跳动—视频抠像工具—RNN
Robust High-Resolution Video Matting with Temporal Guidance
3.7 飞桨图像识别套件PaddleClas
3.8 Small Data’s Big AI Potential
美国智库最新报告:长期被忽略的小数据人工智能潜力不可估量—大数据文摘
3.9 Bilingualism Comes Naturally to Our Brains
NYU—Bilingualism Comes Naturally to Our Brains
3.10 内在触感 强化学习 机械手
Paper—On the Feasibility of Learning Finger-gaiting In-hand Manipulation with Intrinsic Sensing
3.11 大脑学习算法模型模拟反向传播过程
Paper—Burst-dependent synaptic plasticity can coordinate learning in hierarchical circuits
Neuron Bursts Can Mimic Famous AI Learning Strategy
4.学习资源
4.1 《Statistical Thinking for the 21st Century》—Stanford University
《Statistical Thinking for the 21st Century》
4.2 C语言入门笔记
4.3 简单的机器学习模型线性回归
初学者指南:使用 Numpy、Keras 和 PyTorch 实现最简单的机器学习模型线性回归—数据派THU
Simple-Linear-Regression—Github
4.4 17个机器学习的常用算法!
4.5 鱼水说竞赛:竞赛模型选择
4.6 计算机早期历史-Early Computing
计算机早期历史-Early Computing–YouTube
4.7 图神经网络科普
A Gentle Introduction to Graph Neural Networks
Understanding Convolutions on Graphs
4.8 《Mathematical Foundations for Data Analysis》
《Mathematical Foundations for Data Analysis》—Jeff M. Phillips
5.职场
5.1 博士 入职 三四流高校 参考意见—知乎
6.机构、网站
6.1 北京智源人工智能研究院
6.2 FAIR
6.3 CZ Biohub
7.数据集
7.1 MedMNIST
MedMNIST:A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification