Skip to content
rshu.dev
Neural Networks
Initializing search
Home
Notes
Projects
Coursework
rshu.dev
Home
Notes
Notes
CMPUT 340 - Numerical Methods
CMPUT 340 - Numerical Methods
Absolute and Relative Error (numerical analysis)
Covariance
Data and Computational Error
Eigenvalues and Eigenvectors
**Existence and Uniqueness of Matrices (and singular matrices)
Existence and Uniquness of Interpolants
General strategy for solutions of computational problems
Hermite Cubic Interpolation
Intermediate Value Theorem
Interpolation (numerical analysis)
Inverse Function Theorem
Linear Least Squares Problems
Linear Systems (numerical analysis)
Matrix Norms
Nonlinear Equations
Optimization Problems (numerical methods)
Orthogonal Transformations (numerical analysis)
Orthogonalization Methods
Overdetermined System (numerical analysis)
Piecewise Interpolation
Polynomial Interpolation
Power Iteration (computing eigen values and vectors)
Problem solving process in Computational Simulation
QR Factorization
Scientific Computing (numerical analysis)
Sensitivity and Conditioning (numerical analysis)
Sensitivity and Conditioning of Rectangular Matrices (numerical analysis)
Square Matrix Condition Number (and amplification factor) (numerical analysis)
Sources of Approximation in Numerical Analysis
Spectral Radius (eigenstuff)
Spectrum (eigenstuff)
Stability and Accuracy (numerical analysis)
Triangular Least Squares Problems
Truncation Error and Rounding Error (numerical analysis)
Vector Norms
Well-posed (numerical analysis)
CMPUT 467 - Machine Learning II
CMPUT 467 - Machine Learning II
Aleatoric Uncertainty
Autoencoders
Bayesian Linear Regression
Bias, Variance, and Generalization Error (more in depth)
Bootstrap Resampling
Bottleneck Layer
Classification Accuracy
Conditional Generative Models
Conditional Variational Autoencoders (CVAE)
Conjugate Prior
Connection of Generative Models to PPCA
Covariance Matrix
Covariate Shift
Cross Validation
Cross Validation to select Hyperparameters
Cumulative Distribution Function (CDF)
Data Representation in Machine Learning
Dealing with Missing Data
Derivation for ELBO from KL Divergence in VAE's
Direct Methods for Missing Data
Epistemic Uncertainty
Estimating Uncertainty for Nonlinear Models
Evaluating Generative Models
Expectation-Maximization (EM Algorithm)
Finding the dictionary to get latent factors
Gaussian Process
Generalization Error
Generalization Error for Logistic Regression
Generalized Linear Models (GLM)
Generative Models
Generative Models using Data Representations
GLM Preface
Gradient Descent with Lasso
Gradient of MSE in Matrix form
Hessian Matrix
How the derivative of a(θ) is equal to the mean
Kernel Model
Kernel Trick in Machine Learning
Kernelizing Bayesian Linear Regression (Gaussian Process Regression)
Kullback-Leibler Divergence (KL)
k-fold Cross Validation
L1 Norm
L2 Norm
Laplace Distribution
Latent Factors and Factor Analysis
Matrix Completion (Imputing Data)
Matrix Factorization Approaches
Maximum A Posteriori (MAP)
Midterm Notes for ML2
Missing Data (Machine Learning)
Mixture Models
More details on log-normalizer function a(θ)
Multinomial Logistic Regression
Multivariate Gaussian Distribution
Natural Exponential Family
Neural Networks
Neural Networks
Table of contents
Definition
Example
Normal-Inverse Gamma Distribution
One-Hot Encoding
Ordinary Least Squares (OLS)
Overparametrized Neural Networks
Partial Observability (Machine Learning)
Positive Definite Matrices
Precision in Machine Learning
Principal Component Analysis (PCA)
Probabilistic Principal Component Analysis (PPCA)
Prototype Representations
Proximal Methods
Proximal Operator
Proximal Update
Radial Basis Function Networks
ReLU
Reparametrization Trick in VAE's (Machine Learning)
Repeated Random Subsampling
SGD has Implicit Regularization
Simple Generative Models, Mixture Models
Simplex
Sparse Coding
Sparse Solution
Student-t Distribution
The Reparemeterization Trick in Machine Learning
Transfer Function
Translation Invariance
Uncertainty Estimation and Bayesian Approaches
Uncertainty Estimation for Neural Networks using Ensembles
Uncertainty in Predictions via Bayesian Inference
Variational Autoencoder (VAE)
Why do we project to higher dimensions?
ℓ1 Regularization
ℓ2 Regularization
STAT 372 - Mathematical Statistics
STAT 372 - Mathematical Statistics
Introduction
Asymptotic Unbiasedness
Convergence in Distribution
Convergence in Probability
Delta Method
Jensen's Inequality
Maximum Likelihood Estimation
MGFs and the Central Limit Theorem
Score function, Fisher Information, Cramer-Rao Lower Bound and Efficiency
Slutsky's Theorem
Systems Design
Systems Design
Availability Patterns
Availability vs Consistency
Background Jobs
Consistency Patterns in Distributed Systems
Distributed Systems
Latency vs Throughput
Partition
Performance vs Scalability
Queue-Based Load Levelling pattern
Redundancy
Projects
Projects
Coursework
Coursework
Table of contents
Definition
Example
Neural Networks
¶
Definition
¶
to be added ...
Example
¶
Back to top