haotianblog

haotianblog

A bilingual blog-first personal site.

About

Background on the site, its topics, and why the work is published bilingually.

Blog

English entry point for AI foundations, technical articles, summaries, and bilingual posts.

Projects

Public project index for the site, algorithm work, and long-term technical notes.

Home

haotianblog

This is a bilingual technical blog for algorithm notes, programming write-ups, project logs, and downloadable companion materials. The goal is to publish durable references that remain useful after the initial work is done.

Start here

Popular articles, learning routes, and playgrounds

The home page now points directly to content you can read, run, and reuse.

Popular Articles

Start with the pages most likely to answer a search question or lead into a complete project.

Latest Learning Routes

Use the topic hubs when you want a sequence instead of one isolated article.

Algorithm Playground

Open the browser demos when reading is not enough and you want to step through the algorithm.

AI learning path

Start the AI foundations route

Read the AI series in order and continue from the next unfinished step.

Learning path

Read the algorithm notes in order

A short path through the strongest current articles, code, dataset, and diagrams.

Survey feedback

Active surveys appear here. Open one to answer it on a dedicated page and view statistics on a separate results page.

Active 6 questions 17 responses

The Usage of Social Media of College Students

A short questionnaire about how college students use social media.

Remotion animations

Short animations that make algorithm steps visible

These videos are rendered with Remotion and lazy-loaded so the first screen stays fast.

Structured navigation

All destinations

The top bar stays compact. This section provides the full site entry index.

4 links

Start here

Browse every public destination by topic. On desktop, this is the full structured entry map.

10 links

Learn and explore

Browse every public destination by topic. On desktop, this is the full structured entry map.

3 links

Resources and downloads

Browse every public destination by topic. On desktop, this is the full structured entry map.

7 links

Feedback, contact, and policies

Browse every public destination by topic. On desktop, this is the full structured entry map.

Explore next

What this site focuses on

  • Algorithm and data-structure articles with implementation details and debugging notes
  • C and Python code walkthroughs that explain why the implementation works
  • Project notes covering deployment, maintenance, and site-building decisions
  • Downloadable code, diagrams, datasets, and supporting files that belong to each article

Where to start

The current site is strongest on technical blog posts and downloadable materials. Start here if you want concrete examples:

Publishing direction

The Chinese side currently contains the most complete long-form articles. The English side is being expanded into a clearer landing surface for summaries, project context, and future translated or original posts.

Gradient Descent and Optimizer Geometry: Momentum, Adam, and Loss Surfaces

Hand-calculate early steps on a 2D quadratic, compare gradient descent, momentum, and Adam, and reproduce the loss-contour visualization.

Downloads

Search and jump

The translucent search box now floats inside the hero area below the banner title. Pick a dropdown suggestion and the page will jump to the matching item inside the same resource card with stronger highlighting.

This page hosts public download resources, including algorithm project files, handwritten digit project files, and the newly added calculus PDF.

Gaoshu Lianxi

A public advanced calculus practice PDF for local review or printing.

Gaoshu Lianxi PDF

Download Gaoshu Lianxi

The original uploaded file was 练习.pdf; the public filename is gaoshu-lianxi.pdf.

Iris K-means learning bundle

Everything below belongs to the same article: K-means 聚类算法入门:基于 Iris 数据集的 C 语言实现.

You can read the article first, or download the dataset, source code, flowchart, visualization, and zip archive from this single grouped card.

K-means article

Open the article

The article now includes a detailed flowchart and a 2D scatter visualization of the clustering result.

Iris.csv

Download Iris.csv

The original Iris dataset with 150 samples, 4 numeric features, and 3 species labels.

Iris_sort_K_mean.c

Download Iris_sort_K_mean.c

The refined C implementation with command-line file input, feature standardization, K-means++ initialization, multi-restart selection, and SSE reporting.

Cluster visualization

Download iris-kmeans-cluster-visual.svg

This scatter plot is generated from the current Iris_sort_K_mean.c clustering result using petal length and petal width as the 2D projection axes.

Iris K-means cluster visualization preview

Zip package

Download iris-kmeans-materials.zip

The archive contains Iris.csv, Iris_sort_K_mean.c, the SVG flowchart, and the SVG visualization.

Handwritten digit project bundle

This group belongs to the handwritten digit project series. The materials now connect the dataset article, the C softmax classifier, and the browser playground into one public bundle.

A good order is: start with the dataset article, continue with the C classifier article, and then try the playground.

Handwritten digit dataset article

Open the dataset article

Start with train.csv, test.csv, labels, and the 784-feature image format before reading the classifier implementation.

digit_softmax_classifier.c

Download digit_softmax_classifier.c

The C source includes CSV loading, normalization, softmax probability calculation, parameter updates, and submission export.

train.csv.zip

Download train.csv.zip

The compressed training set with 42000 labeled handwritten digit samples.

test.csv.zip

Download test.csv.zip

The compressed test set with 28000 unlabeled samples for final prediction export.

digit-playground-model.json

Download digit-playground-model.json

The compact softmax demo model and sample set used by the browser playground.

digit-sample-grid.svg

Download digit-sample-grid.svg

A small preview grid generated from the handwritten digit training set.

Handwritten digit preview

Handwritten digit bundle

Download handwritten-digits-materials.zip

The archive contains the C source, compressed train and test sets, submission files, the browser model JSON, and the preview SVG.

Contact

Contact

Email is the clearest way to reach me if you want to discuss an article, report an error, ask about a download, or continue a technical conversation from something published on the site.

Email

haotianblog@gmail.com

Good reasons to write

  • Questions about an algorithm article, code example, or diagram
  • Feedback on downloadable materials or broken resources
  • Discussion around site building, deployment, or technical writing
Scroll down