新智元推荐
来源：专知(ID:Quan_Zhuanzhi)
【新智元导读】悉尼科大徐亦达教授机器学习讲义，总共涵盖 32 个主题,1000 页讲义，包括Softmax算法、传统GAN，W-GAN数学，贝叶斯GAN, 蒙托卡罗树搜索，alphaGo学习算法等。
悉尼科大徐亦达教授近日在GitHub更新了他2019年以来的机器学习新材料，超过1000页的讲义，总共涵盖 32 个主题。
具体而言，主题涉及 Softmax 的属性，估计 softmax 时不需计算分母，概率重新参数化，Gumbel-Max 技巧和 REBAR 算法 传统 GAN，W-GAN 数学，对偶性和 KKT 条件，Info-GAN，贝叶斯 GAN, 蒙托卡罗树搜索，alphaGo 学习算法，政策梯度定理，RL 中可信区域优化的数学，TRPO 自然梯度，近似策略优化 (PPO), 共轭梯度算法等。
地址：
https://github.com/roboticcam/machine-learning-notes
- DeeCamp 2019：Story of Softmax
properties of Softmax, Estimating softmax without compute denominator, Probability re-parameterization: Gumbel-Max trick and REBAR algorithm (softmax 的故事) Softmax 的属性，估计 softmax 时不需计算分母，概率重新参数化，Gumbel-Max 技巧和 REBAR 算法
- DeeCamp 2018：When Probabilities meet Neural Networks
Expectation-Maximization & Matrix Capsule Networks; Determinantal Point Process & Neural Networks compression; Kalman Filter & LSTM; Model estimation & Binary classifier (当概率遇到神经网络) 主题包括：EM 算法和矩阵胶囊网络；行列式点过程和神经网络压缩；卡尔曼滤波器和 LSTM; 模型估计和二分类问题关系
- Video Tutorial to these notes 视频资料
I recorded about 20% of these notes in videos in 2015 in Mandarin (all my notes and writings are in English) You may find them on Youtube and bilibili and Youku
我在 2015 年用中文录制了这些课件中约 20％的内容 (我目前的课件都是英文的) 大家可以在 Youtube 哔哩哔哩 and 优酷 下载
Data Science 数据科学课件
- 30 minutes introduction to AI and Machine Learning
An extremely gentle 30 minutes introduction to AI and Machine Learning. Thanks to my PhD student Haodong Chang for assist editing
30 分钟介绍人工智能和机器学习，感谢我的学生常浩东进行协助编辑
- Regression methods
Classification: Logistic and Softmax; Regression: Linear, polynomial; Mix Effect model [costFunction.m] and [soft_max.m]
分类介绍: Logistic 回归和 Softmax 分类；回归介绍：线性回归，多项式回归；混合效果模型 [costFunction.m] 和 [soft_max.m]
- Recommendation system
collaborative filtering, Factorization Machines, Non-Negative Matrix factorisation, Multiplicative Update Rule
推荐系统：协同过滤，分解机，非负矩阵分解，和其中 “乘法更新规则” 的介绍
- Dimension Reduction
classic PCA and t-SNE
经典的 PCA 降维法和 t-SNE 降维法
- Introduction to Data Analytics and associate Jupyter notebook
Supervised vs Unsupervised Learning, Classification accuracy
数据分析简介和相关的 jupyter notebook，包括监督与无监督学习，分类准确性
Deep Learning 深度学习课件
- Optimisation methods
Optimisation methods in general. not limited to just Deep Learning
常用的优化方法。不仅限于深度学习
- Neural Networks
basic neural networks and multilayer perceptron
神经网络：基本神经网络和多层感知器
- Convolution Neural Networks: from basic to recent Research
detailed explanation of CNN, various Loss function, Centre Loss, contrastive Loss, Residual Networks, Capsule Networks, YOLO, SSD
卷积神经网络：从基础到最近的研究：包括卷积神经网络的详细解释，各种损失函数，中心损失函数，对比损失函数，残差网络，胶囊网络，YOLO，SSD
- Word Embeddings
Word2Vec, skip-gram, GloVe, Fasttext
系统的介绍了自然语言处理中的 “词表示” 中的技巧
- Deep Natural Language Processing
RNN, LSTM, Seq2Seq with Attenion, Beam search, Attention is all you need, Convolution Seq2Seq, Pointer Networks
深度自然语言处理：递归神经网络，LSTM, 具有注意力机制的 Seq2Seq，集束搜索，指针网络和 "Attention is all you need", 卷积 Seq2Seq
- Mathematics for Generative Adversarial Networks
How GAN works, Traditional GAN, Mathematics on W-GAN, Duality and KKT conditions, Info-GAN, Bayesian GAN
GAN 如何工作，传统 GAN，W-GAN 数学，对偶性和 KKT 条件，Info-GAN，贝叶斯 GAN
- Restricted Boltzmann Machine
basic knowledge in Restricted Boltzmann Machine (RBM)
受限玻尔兹曼机 (RBM) 中的基础知识
Reinforcement Learning 强化学习
- Reinforcement Learning Basics
basic knowledge in reinforcement learning, Markov Decision Process, Bellman Equation and move onto Deep Q-Learning
深度增强学习：强化学习的基础知识，马尔可夫决策过程，贝尔曼方程，深度 Q 学习
- Monto Carlo Tree Search
Monto Carlo Tree Search, alphaGo learning algorithm
蒙托卡罗树搜索，alphaGo 学习算法
- Policy Gradient
Policy Gradient Theorem, Mathematics on Trusted Region Optimization in RL, Natural Gradients on TRPO, Proximal Policy Optimization (PPO), Conjugate Gradient Algorithm
政策梯度定理，RL 中可信区域优化的数学，TRPO 自然梯度，近似策略优化 (PPO), 共轭梯度算法
Probability and Statistics Background 概率论与数理统计基础课件
- Bayesian model
revision on Bayes model include Bayesian predictive model, conditional expectation
复习贝叶斯模型，包括贝叶斯预测模型，条件期望等基础知识
- Probabilistic Estimation
some useful distributions, conjugacy, MLE, MAP, Exponential family and natural parameters
一些常用的分布，共轭特性，最大似然估计，最大后验估计，指数族和自然参数
- Statistics Properties
useful statistical properties to help us prove things, include Chebyshev and Markov inequality
一些非常有用的统计属性可以帮助我们在机器学习中的证明，包括切比雪夫和马尔科夫不等式
Probabilistic Model 概率模型课件
- Expectation Maximisation
Proof of convergence for E-M, examples of E-M through Gaussian Mixture Model, [gmm_demo.m] and [kmeans_demo.m]and [Youku]
最大期望 E-M 的收敛证明，E-M 到高斯混合模型的例子， [gmm_demo.m] 和 [kmeans_demo.m] 和 [优酷链接]
- State Space Model (Dynamic model)
explain in detail of Kalman Filter [Youku], [kalman_demo.m] and Hidden Markov Model [Youku]
状态空间模型 (动态模型) 详细解释了卡尔曼滤波器 [优酷链接], [kalman_demo.m] 和隐马尔可夫模型 [优酷链接]
Inference 推断课件
- Variational Inference
explain Variational Bayes both the non-exponential and exponential family distribution plus stochastic variational inference. [vb_normal_gamma.m] and [优酷链接]
变分推导的介绍：解释变分贝叶斯非指数和指数族分布加上随机变分推断。[vb_normal_gamma.m] 和 [优酷链接]
- Stochastic Matrices
stochastic matrix, Power Method Convergence Theorem, detailed balance and PageRank algorithm
随机矩阵，幂方法收敛定理，详细平衡和谷歌 PageRank 算法
- Introduction to Monte Carlo
inverse CDF, rejection, adaptive rejection, importance sampling [adaptive_rejection_sampling.m] and [hybrid_gmm.m]
累积分布函数逆采样，拒绝式采样，自适应拒绝式采样，重要性采样 [adaptive_rejection_sampling.m] 和 [hybrid_gmm.m]
- Markov Chain Monte Carlo
M-H, Gibbs, Slice Sampling, Elliptical Slice sampling, Swendesen-Wang, demonstrate collapsed Gibbs using LDA [lda_gibbs_example.m] and [test_autocorrelation.m] and [gibbs.m] and [Youku]
马尔可夫链蒙特卡洛的各种方法 [lda_gibbs_example.m] 和 [test_autocorrelation.m] 和 [gibbs.m] 和 [优酷链接]
- Particle Filter (Sequential Monte-Carlo)
Sequential Monte-Carlo, Condensational Filter algorithm, Auxiliary Particle Filter [Youku]
粒子滤波器（序列蒙特卡洛）[优酷链接]
Advanced Probabilistic Model 高级概率模型课件
- Bayesian Non Parametrics (BNP) and its inference basics
Dircihlet Process (DP), Chinese Restaurant Process insights, Slice sampling for DP [dirichlet_process.m] and [优酷链接] and [Jupyter Notebook]
非参贝叶斯及其推导基础：狄利克雷过程，中国餐馆过程，狄利克雷过程 Slice 采样 [dirichlet_process.m] 和 [优酷链接] 和 [Jupyter Notebook]
- Bayesian Non Parametrics (BNP) extensions
Hierarchical DP, HDP-HMM, Indian Buffet Process (IBP)
非参贝叶斯扩展：层次狄利克雷过程，分层狄利克雷过程 - 隐马尔可夫模型，印度自助餐过程 (IBP)
- Determinantal Point Process
explain the details of DPP’s marginal distribution, L-ensemble, its sampling strategy, our work in time-varying DPP
行列式点过程解释：行列式点过程的边缘分布，L-ensemble，其抽样策略，我们在 “时变行列式点过程” 中的工作细节.
