/machine-learning-notes

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习,概率模型和深度学习的讲义(2000+页)和视频链接

Primary LanguageJupyter Notebook

Infinity in Deep Learning 深度学习“无限”精彩

Detailed derivation of neural networks as (1) Gaussian Process using central Limit theorem (2) Neural Tangent Kernel (NTK) (1) 使用中心极限定理详细推导神经网络作为高斯过程 (2) 神经正切核 Neural Tangent Kernel (NTK)

Discuss Neural ODE and in particular the use of adjoint equation in Parameter training 讨论神经ODE,尤其是在参数训练中使用伴随方程

Sinovasinovation DeeCamp 创新工场DeeCAMP讲义

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

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10%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

3D Geometry Computer vision 3D几何计算机视觉

Camera Models, Intrinsic and Extrinsic parameter estimation, Epipolar Geometry, 3D reconstruction, Depth Estimation 相机模型,内部和外部参数估计,对极几何,三维重建,图像深度估计

Recent research of the following topics: Single image to Camera Model estimation, Multi-Person 3D pose estimation from multi-view, GAN-based 3D pose estimation, Deep Structure-from-Motion, Deep Learning based Depth Estimation, 以下主题的最新研究:单图像到相机模型的估计,基于多视图的多人3D姿势估计,基于GAN的3D姿势估计,基于运动的深度结构,基于深度学习的深度估计

This section is co-authored with PhD student Yang Li 本部分与博士研究生李杨合写

Deep Learning 深度学习课件

Out-of-distribution, Neural Network Calibration, Gumbel-Max trick, Stochastic Beams Search (some of these lectures overlap with DeeCamp2019)

分布外、神经网络校准、Gumbel-Max 技巧、随机光束(BEAM)搜索(其中一些讲座与 DeeCamp2019 重叠)

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

basic neural networks and multilayer perceptron

神经网络: 基本神经网络和多层感知器

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

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

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

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

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

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, alphaGo learning algorithm

蒙托卡罗树搜索,alphaGo学习算法

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

Data Science 数据科学课件

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

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][soft_max.m]

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,和期中“乘法更新规则”的介绍

classic PCA and t-SNE

经典的PCA降维法和t-SNE降维法

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

Probability and Statistics Background 概率论与数理统计基础课件

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

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

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

Proof of convergence for E-M, examples of E-M through Gaussian Mixture Model, [gmm_demo.m] and [kmeans_demo.m] and [bilibili video]

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][kmeans_demo.m][B站视频链接]

explain in detail of Kalman Filter [bilibili video], [kalman_demo.m] and Hidden Markov Model [bilibili video]

状态空间模型(动态模型) 详细解释了卡尔曼滤波器 [B站视频链接], [kalman_demo.m] 和隐马尔可夫模型 [B站视频链接]

Inference 推断课件

explain Variational Bayes both the non-exponential and exponential family distribution plus stochastic variational inference. [vb_normal_gamma.m] and [bilibili video]

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][B站视频链接]

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

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][hybrid_gmm.m]

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 [bilibili video]

马尔可夫链蒙特卡洛的各种方法 [lda_gibbs_example.m][test_autocorrelation.m][gibbs.m][B站视频链接]

Sequential Monte-Carlo, Condensational Filter algorithm, Auxiliary Particle Filter [bilibili video]

粒子滤波器(序列蒙特卡洛)[B站视频链接]

Advanced Probabilistic Model 高级概率模型课件

Dircihlet Process (DP), Chinese Restaurant Process insights, Slice sampling for DP [dirichlet_process.m] and [bilibili video] and [Jupyter Notebook]

非参贝叶斯及其推导基础: 狄利克雷过程,**餐馆过程,狄利克雷过程Slice采样 [dirichlet_process.m][B站视频链接][Jupyter Notebook]

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)

Levy-Khintchine representation, Compound Poisson Process, Gamma Process, Negative Binomial Process

Levy-Khintchine表示,复合Poisson过程,Gamma过程,负二项过程

This is an alternative explanation to our IJCAI 2016 papers. The derivations are different from the paper, but portraits the same story.

这是对我的IJCAI2016论文 的一个不同解释。虽然写的方法公式推导不同,但描绘的是同一事情

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

Special Thanks

  • I would like to thank my following PhD students for help me proofreading, and provide great discussions and suggestions to various topics in these notes, including (but not limited to) Hayden Chang, Shawn Jiang, Erica Huang, Deng Chen, Ember Liang; 特别感谢我的博士生团队协助我一起校对课件,以及就课件内容所提出的想法和建议,团队成员包括(但不限于)常浩东,姜帅,黄皖鸣,邓辰,梁轩。

  • I always look for high quality PhD students in Machine Learning, both in terms of probabilistic model and Deep Learning models. Contact me on YiDa.Xu@uts.edu.au

如果你想加入我的机器学习博士生团队或有兴趣实习, 请通过YiDa.Xu@uts.edu.au与我联系。