Skip to content

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (1000+ slides) 我不间断更新的机器学习,概率模型和深度学习的讲义(1000+页)和视频链接

Notifications You must be signed in to change notification settings

south-ocean/machine-learning-notes

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

[News] Presentation at DeeCamp & Peking University, July 2018

Topics include: Expectation-Maximization & Matrix Capsule Networks; Determinantal Point Process & Neural Networks compression; Kalman Filter & LSTM; Model estimation & Binary classifier; Probability density re-parameterization; Stochastic matrices and Monte Carlo Inference

Video Tutorial to these notes.

  • 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 哔哩哔哩 and 优酷

  • I always look for high quality PhD students in Machine Learning, both in terms of probabilistic model and Deep Learning models. Contact me on [email protected]

Data Science

An extremely gentle 30 minutes introduction to AI and Machine Learning. Thanks to my PhD student Haodong Chang for assist editing

Classification: Logistic and Softmax; Regression: Linear, polynomial; Mix Effect model [costFunction.m] and [soft_max.m]

collaborative filtering, Factorization Machines, Non-Negative Matrix factorisation, Multiplicative Update Rule

classic PCA and t-SNE

Three perspectives into machine learning and Data Science. Supervised vs Unsupervised Learning, Classification accuracy

Deep Learning (jupyter style notes coming in 2018)

Optimisation methods in general. not limited to just Deep Learning

basic neural networks and multilayer perceptron

detailed explanation of CNN, various Loss function, Centre Loss, contrastive Loss, Residual Networks, YOLO, SSD

Word2Vec, skip-gram, GloVe, Noise Contrastive Estimation, Negative sampling, Gumbel-max trick

RNN, LSTM, Seq2Seq with Attenion, Beam search, Attention is all you need, Convolution Seq2Seq, Pointer Networks

basic knowledge in reinforcement learning, Markov Decision Process, Bellman Equation and move onto Deep Q-Learning

basic knowledge in Restricted Boltzmann Machine (RBM)

Probability and Statistics Background

revision on Bayes model include Bayesian predictive model, conditional expectation

some useful distributions, conjugacy, MLE, MAP, Exponential family and natural parameters

useful statistical properties to help us prove things, include Chebyshev and Markov inequality

Probabilistic Model

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

explain in detail of Kalman Filter and Hidden Markov Model, [kalman_demo.m] and [HMM 优酷链接] and [Kalman Filter 优酷链接]

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]

stochastic matrix, Power Method Convergence Theorem, detailed balance and PageRank algorithm

inverse CDF, rejection, adaptive rejection, importance sampling [adaptive_rejection_sampling.m] and [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 [优酷链接]

Sequential Monte-Carlo, Condensational Filter algorithm, Auxiliary Particle Filter [优酷链接]

Advanced Probabilistic Model

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

Hierarchical DP, HDP-HMM, Indian Buffet Process (IBP)

explain the details of DPP’s marginal distribution, L-ensemble, its sampling strategy, our work in time-varying DPP

About

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (1000+ slides) 我不间断更新的机器学习,概率模型和深度学习的讲义(1000+页)和视频链接

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%