Latest Posts

2. Orthogonal Decomposition

$$

OIDC and GCP

**OIDC (OpenID Connect)** is an authentication protocol built on top of OAuth 2.0. Think of it as a standardized way to prove "who you are" across dif...

C Linkage

---

Git Actions for GCP

```yaml

Mocking and Testing

```python

Pytest 101

**Fixtures** are reusable setup functions that provide data, objects, or state to your tests. They help you avoid code duplication and ensure consiste...

Service Account

```bash

Homework 4 Solutions

Solutions to ML Homework 4 covering bias-variance decomposition in Ridge Regression, optimal classifier under squared loss, and model selection using k-fold cross-validation

11. Cross Validation and Model Selection

- Let's say we have the following two models:

10. Bias-Variance Tradeoff

- $\mathcal{D} = \{(x^{(i)}, y^{(i)})\}_{i = 1}^N$

14. Color Spaces

**RGB** stands for **Red–Green–Blue**, an **additive color model** used in displays, cameras, and digital imaging.

13. Single-view Metrology and Cameras

$$

9. Gradient Descent

- Function $f: \R^d \rightarrow \R $ is `convex` if $\forall x_1 \in \R^d, x_2 \R^d, 0 \le t \le 1$

Supplement: Full SVM Derivation

$$

Homework 3 Solutions

Solutions to ML Homework 3 covering Support Vector Machines (SVM), dual optimization, kernel methods, and linear regression techniques including Ridge and Lasso with ISTA

8. Empirical Risk Minimization (ERM)

$$

7. SVM

> [!CAUTION]

6. Linear Regression

$$

11. Image Morphing

- Affine transformation

12. Pinhole Camera

- Angless and length are lost

10. Image Warping

$$

8. Histogram Equalization

- Reassign values so that the number of pixels with each values is more evenly distributed

7. Graph Cut-Based Segmentation

- Good region is similar to foreground color model and dissimilar from background color

9. Image Compositing

- small segmentation errors noticeable

Makefile

```

Lab: Error Path Quilting

```python

Homework 2 Solutions

Solutions to ML Homework 2 covering Naive Bayes classification, Gaussian Naive Bayes, Logistic Regression theory, and optimization techniques including gradient descent variants

Supplement: Binary Cross-Entropy Loss Derivation

For a single training example:

6. Texture Synthesis

- Create new samples of a given texture

1. Hessian Matrix

If you have a real-valued function

3. Beta and Gamma Distribution Proofs

$$

5. Naive Bayes

- **Dataset $\mathcal{D}$**: i.i.d (independent and identically distributed) drawn from some unknonw distribution

2. MLE and MAP Proofs

- **$\mathcal{D}$:** $\alpha_H$ heads, $\alpha_T$ tails.

Supplement: Probability Distributions

- The number of successes in a fixed number of independent trials, each with the same probability of success.

Supplement: Representer Theorem

The proof of representer theorem

1. Distribution Proofs

$$

Homework 1 Solutions

Solutions to CS 446/ECE 449 Homework 1 covering K-NN, Perceptron Algorithm, and MLE/MAP estimation

Lab: Image Filtering

$$

Lab: Image Formation

$$

Lab: Color Swapping

- Substituting a specific color in an image with some targeted color for the purpose of exploration, design, image, and creation.

Lab: Contrast Enhancement

- a photometric measure of the [phtometric](<https://en.wikipedia.org/wiki/Photometry_(optics)>) measure of the **luminous intensity** per unit area o...

Lab: Hybrid Images

- Two different interpretations of a picture can be perceived by

5. Light

- We perceives color from the complex interacction of multiple factors

4. Denoising and Compression

- $FFT$ can be used to efficiently implement $SSD$

3. Template Matching

- $1 \rightarrow D$

3. Euler's Formula

---

1. Fourier Series - Prelude and Trigonometry

- defined on $(-\pi, \pi]$

2. Introduction to Sound Waves

```python

4. Introduction to ML Concepts

- **Inductive Bias**

3. Nonparametric Methods

- use of probability distributions that have specific functional forms governed by a small number of parameters whose values are to be determinied fro...

2. Frequency

$$

2. Perceptron

- A set of examples is `linearly separable` if there exists a linear decision boundary that can separate the points

1. Introduction and KNN

- A computer program is said to

2's Complement and Binary Operations

- Easy to store with bitsable elements

Git Commands

**To remove the last N commits:**

1. Pixels and Linear Filters

1. Light comes out from the sources

Supplement: NumPy Tutorial

> [!IMPORTANT]

Conditional Rendering

- `if` `&&` and `?:` operators can be used to render JSX conditionally.

Ensure python3.12 is installed

```yaml

Sample file for building C-code

```yaml

Heads-up

- Under the hood, JSX is transformed into plain JavaScript objectcs and you can't return two objects from a function without wrapping them into an arr...

Go app deployment with Dockerfile

```dockerfile

Go - Error

> [!CAUTION]

GCP service account with google drive

- [Read this first](https://stackoverflow.com/questions/23555040/access-google-drive-without-oauth2)

3. Pipeline

- `Single cycle` mechanism only allows instructions to be processed one at a time

2. Chapter 1 Review

*7 steps*

Homework 2 Review

>[!CAUTION]

onClick event is not triggered on iPhone

```tsx

1. Chapter 5

> [!CAUTION]

CORS - Errors encountered when trying to access my go backend from my react frontend

When I was authenticating a user, the backend returned a `200` status code,

Common Mistakes

- Remember when writing the callback function for `onClick`, the `MouseEvent` should be the `React's type` instead of the `vanilla javascript` one

How to use useContext correctly in React

- Create a folder named `contexts` in the `src` folder.