top of page

Introduction to Machine Learning

This AI course offers a comprehensive math overview of fundamental machine learning and neural network concepts, enabling practical implementation of models. Students will gain hands-on experience creating models independently, developing proficiency in building machine learning algorithms from scratch.

Teachers

Dedication. Expertise. Passion.

IMG_5099.webp

Charlie Huang

Hi! I am Charlie and I am currently a freshman at Mountain View High School. I have learned about Machine Learning for 3+ years. I have learned concepts like image segmentation and applied it to finding the mask of the fish. Furthermore, I have helped to build a chatbot that provides information about the FIRST Robotics Competition. The frameworks/langauges I have experience in are C++, Java, Javascript (Typescript + SvelteKit) and python (pytorch). Here is my github: https://github.com/charliehuang09?tab=repositories

images.png

Daniel Yang

Hi! I'm Daniel and I am a freshmen at The King's Academy. I have around a year's experience in AI, coding neural networks from scratch to do classification tasks such as MNIST. In addition, I participate in competitive math programming. The languages have experience with are C++, Python, Rust, and a tiny bit of Javascript. I enjoy Machine Learning because of the rapid pace of innovation and the underlying logic behind it all.

  1. ​

Times/Dates

Saturday 3PM - 4PM

 

Wednesday 3pm - 4PM

July 6, 2024
July 10, 2024
July 13, 2024
July 17, 2024
July 20, 2024
July 24, 2024
July 27, 2024
July 31, 2024

Class Location

Online

Prerequisites

  • Algebra 2

  • Basic Coding Knowledge

    • Variables

    • Functions

    • Objects

Materials

Computer

Course Conent

Week 1:

  • Teach derivatives (general ideas no proof)

  • Coding lab

 

Week 2:

  • Linear regression

  • Logistic regression

 

Week 3:

  • K-Nearest Neighbors

  • K-Means

 

Week 4

  • Decision, classification, regression trees

 

Week 5:

  • Feed forward

  • Backprop

 

Week 6: 

  • Implement MNIST

    • Activation functions

    • Gradient descent optimizers

    • Data normalization

    • Dropout

  • HW: find more optimization strategies

 

Week 7

  • Convolutional Neural Networks

 

Week 8

  • Kaggle Competition

2-removebg-preview (1).png
bottom of page