University of Southern California - Electrical and Computer Engineering (Machine Learning & Data Science)
- EE 503: Probability for Electrical and Computer Engineers (Spring 2022)Outline
- Truth table; Sigma-algebra(CUT); Probability measure(CAT); De. Morgans; Injective, Surjective & Bijective
- Conditional Prob.; Total Prob.; Baye's Theorem; Boole's Inequality; Multiplication Theorem; Naive Bayes
- Cartesian Product; Gamma Function; Pascal's Formula; Bi&Multi-nomial Theorem; Prob. Continuity; Borel Cantelli Lemma
- Archimedian Property; Bolzano·Weierstrass Theorem; Cauchy Sequence; i.i.d.; Binomial; Hypergeometric; Negative Binomial; Geometric; Poisson; Stirling's Approx
- Random Variable(PAM); CDF; Uniform Convergence; Beta; Cauchy; Gaussian & its Integral; Signal Detection; Exponential; Bayesian Inference
- Expectations & Moments & Variance of Random Variables; Unconscious Statistician; Sample & Population's E & V
- Joint & Conditional PDF/CDF; Random Process; Jointly Normal; Vector population covariance; Correlation; Uncertainty Principle; Holder's Inequality
- Convergence in ueopd(mpd); Law of Large Numbers; Sampling Statistics; Markov Inequality; Chebyshev Inequality; Consistency; Bias of r.v.; Mean-Square Error
- Covatiance Matrix; Whitening Process; Total Expectation/Variance; Conditional Expectation/Variance; Doubly Random Sum; Maximum Likelihood Estimation; MLE Invariance Principle
- Sampling from a Distribution; Transform of r.v.; Monte Carlo Simulation; Monte Carlo Integration; Importance Sampling; Information Theory; Entropy; Mutual Information
- Central Limit Theorem; Berry-Essen Theorem; Continiuty Correction; Confidence Intervals; Moment Generating Function; Characteristic Function; Levy's Continuity Theorem; Inversion Theorem
- Bond Present Value; Rational Asset Pricing(RAP); Random/Bankruptcy RAP; 2-stage RAP; Martingale; 10-k Form
- Markov Chains; Discrete Time and Finite Space(DTFS); Irreducible & Aperiodic; Stationary PDF; Optimal Estimators
- Simple Linear Regression; Least Squares; Multiple Regression(OLS)
- EE 510: Linear Algebra for Engineering (Spring 2022)Outline
- Vectors & Scalers; Schwerz & Triangular Inequality; Hyperplanes & Lines
- Matrices; Hermitian, Unitary & Normal; Linear Equations; Elementary Operations
- Echelon Forms; Gauss Elimination; Row Canonical Form; Gauss-Jordan; Homogeneous & Non-homogeneous
- LU Decomposition; Determinant; Cofactors; Laplace Expansion; Classical Adjoint; Cramer's Rule; Principle Minors
- Volumn & Cross Product; Permutation Matrix; Left/Right Inverse; Matrix Norm; Matrix Condition Number
- Vector Spaces; Spanning Sets; Subspace
- Intersection of Subspaces; Row Space; Column Space; Linear Dependence; Basis; Dimension
- Four Fundamental Subspaces; Zero Null Space; Rank plus Nullity
- Linear/Affine Function; Invariant Subspace; Isomorphism; Inner Product Space; Characteristic Polynomial; Cayley-Hamilton
- Eigenvalues & Eigenvectors; Algebraic/Geometric Multiplicity; Diagonalization; Minimal Polynomial
- Monic; Jordan Block; Companion Matrix; Block Triangular Matrix
- Diagonal & Block Diagonal; Jordan Matrix; Nilpotent; Jordan Basis;
- Differential Equations; Stability; Difference Equations; Fourior Coefficient or Component; Gram-Schmidt Orthogonalization; Least Square Problem
- QR Decomposition; Positive (semi-)Definite; Negative (semi-)Definite; Local Maximum/Minimum; Hessian Matrix; Singular Value Decomposition(SVD)
- Kronecker Product; Kronecker Sum; Vandermonde Matrix; Lagrange Interpolation; Sparse Matrix; Toeplitz Matrix
- EE 559: Machine Learning I: Supervised Methods (Spring 2022)Outline
- Introduction to Machine Learning: Supervised, Semi-supervised, Unsupervised, Reinforcement, Transfer
- Basic Concepts: Preprocessing, Feature Engineering, Learning, Prediction
- Regression & Classification; Nearest-means classifier; OvR, OvO, Maximal Value Method(MVM); Computational Complexity
- Feature/Weight Space; Indicator Function; Criterion Function; Optimization: Gradient Descent
- Perceptron Learning; MSE for regression: Least Squares; MSE for classification
- Degree of Freedom; Constraints; Regularization: Ridge Regression; Lagrangian Optimization; Kernels
- Support Vector Machine; Slack Variables; Cross Validation; Support Vector Regression
- ANN; Proof for ANNs as universal function approximators
- ANN; RBF networks; K-means Clustering; Principal Components Analysis(PCA)
- Fisher’s Linear Discriminant(FLD); Multivariate Normal; Mahalanobis Distance; Orthonormal/Whitening Transformation
- Bayes Decision Theory; Minimum-error Classifiers; Minimum-risk Criterion; Density Estimation(Non-parametric): KDE, kNN
- kNN Classification & Regression; Parameter Estimation: MLE, MAP, Bayesian regression
- EE 541: A Computational Introduction to Deep Learning (Fall 2022)Outline
- Estimation Theory; KL-Expansion; Linear/Affine MMSE; Gaussian Random Vectors; LMS Algorithm
- Regression and maximum likelihood; Regularization
- Decision Theory; Logistic regression; multilayer perceptrons (MLPs)
- Universal Approximation; MLP backpropagation (scalar, vector); Activations; Optimizers; dropout, batch normalization
- PyTorch Practice; Vanishing Gradient; Parameter Initialization; Loss Functions; Learning Rate Scheduler
- Dealing with Data; Convolutional Neural Networks
- EE 547: Applied and Cloud Computing for Electrical Engineers (Fall 2022)Outline
- Architecture (local vs. distributed), containers, virtualization, and cloud PaaS; Create a backend
- Overview of JavaScript and Node.js
- Backend development: Node.js and express middleware
- Frontend overview: HTML, CSS, JavaScript
- Databases: NoSQL, Document, MongoDB; Rational, MySQL, Maria, Postgres
- AWS and CLI; VPC standup
- Serverless compute; cloud storage; Application scalability
- Frontend development and application frameworks
- Backend API patterns: REST vs GraphQL
- Authentication and Access control
- Lifecycle: testing, continuous deployment, maintenance
- EE 660: Machine Learning II: Mathematical Foundations and Methods (Fall 2022)Outline
- Regression and Regularization: Lasso, Ridge, Bridge, Logistic, Linear Regression
- Tree: CART and Ensemble of trees
- Bagging: Bootstrap Aggregating; Random Forest
- Boosting (Exponential loss & Forward Stagewise Additive Modeling) and Adaboost
- Learning Theory I: In/Out-sample error, Hoeffding Inequality, loose bound, Generalization Error, Dichotomy, Growth Function, Break Points, VD Dimension
- Learning Theory II: VC Generalization Bound, Bound & Assumptions, Bias & Variance, Overfitting (Stochastic & Deterministic Noise), Regularization, Multi-class case
- Learning Theory III: Occam's Razor; Axiom of Non-Falsifiability; Sampling Bias; Data Snooping; Regression Case Error Bound
- Transfer Learning I: Notation, Symmetric difference hypothesis divergence (SDHD), Cross Domain Generalization Error, General version of Error, Empirical measurement of SDHD
- Transfer Learning II: Common Data Shifts (Prior, Covariance, Concept shifts), Importance Weighting, TrAdaBoost, Subspace Alignment (SA), TL modes (Inductive, Transductive, Unsupervised), TL - Knowledge to transfer (Instances, feature representations, parameters)
- Semi-Supervised Learning I: Assumptions, Inductive & Transductive SSL, Self-Training, Mixture Models, Expectation Maximization
- Semi-Supervised Learning II: Semi-Supervised Support Vector Machine (S3VM), Graph-based techniques (Mincut algo, Harmonic Function algo, Manifold regularization), Co-Training
- Unsupervised Learning: Mixture Models, K-means Clustering, K-medoids Clustering (PAM algo, Voronoi iteration), Similarity & Dissimilarity Measures, Hierarchical Clustering, Dandogram, Nearest/Farthest Neighbor Algo, Choose K (BIC, Stepwise, CH index)
- Human Interpretability: Intrinsic & Post-hoc, Model-agnostic & model-specific, Globally & Locally Interpretable, Mimic Learning, Partial Dependence Plot, Individual Conditional Expectation (ICE), Local interpretable model-agnostic explanations (LIME)
China Agricultural University - Computer Science and Technology
This is a subset of the advanced classes I took at CAU.
Mathematics |
Core Courses |
Hardware |
Selectives |
- Discrete Mathematics Ⅰ
- Discrete Mathematics Ⅱ
- Discrete Mathematics Ⅲ
- Computer Graphics
|
- Data Structure
- Algorithms Design and Analysis
- Computer Organization & Architecture
- Principles of Database Systems
- Operating System
- Computer Networks
- Compiling Principle
- Software Engineering
- Artificial Intelligence
|
- Interface Technology
- Digital Electronic Technology
- Analog Electronic Technology
|
- Virtual Reality Technology
- Digital Image Processing
- Data Mining
- Android Development
|