Foundations Track · KOAI Subject 2

F2. KOAI Foundations II: Neural Networks & Deep Learning

Master the full scope of KOAI Subject 2 (Neural Networks and Deep Learning) through both theory and hands-on code. Students implement everything from MLPs to mini transformer models in PyTorch and reach a level where they can choose optimizer, regularization, and fine-tuning techniques to fit the data. Following F1, this is a required course that every KOAI applicant goes through.

🎯 For: F1 graduates ⏱ Recommended ~14 hours (1:1) 📘 Syllabus 2-1 to 2-2 🧩 Prerequisite: F1 completed

Published: May 16, 2026 | Last updated: May 16, 2026 · Based on the KOAI 2026 guidelines

At a Glance

Track

Foundation

Required for all KOAI applicants

Target

F1 graduates

Grade 9 to Grade 11

Recommended Hours

~14 hours

1:1 basis · varies 10-20 hours

KOAI Mapping

Full scope of Subject 2

Syllabus 2-1 to 2-2

Learning Goals

By the time they finish F2, students will master the full scope of KOAI Subject 2 (Neural Networks and Deep Learning) through both theory and practice. Starting from the mathematical derivation of perceptrons and gradient descent, the goal is to implement everything from MLPs to mini transformer models in PyTorch.

Rather than just running models, students reach a level where they can choose optimizer, regularization, and fine-tuning techniques to fit the data. In weeks 1-2 they implement perceptrons and backpropagation by hand in NumPy to understand the principles first, then move into PyTorch to cover attention, transformers, ViT, autoencoders, and LoRA fine-tuning. It's the common required course for every KOAI applicantIt is.

Who It's For & Prerequisites

Recommended for students who

  • Students who have completed F1 (Foundations I: Python + Classical ML)
  • Students preparing for the KOAI high-school or middle-school division
  • Students who have finished classical ML and want to move on to neural networks and deep learning
  • Students who want to implement models hands-on in PyTorch

Prerequisites

F2 is for F1 graduates students who have completed F1. If you can demonstrate equivalent competency from elsewhere, you may enroll by exception. If you haven't taken F1 yet, please complete F1. Foundations I first. F2 builds neural networks and deep learning on top of the NumPy, Pandas, and classical ML foundation laid in F1.

Week-by-Week Curriculum

Below is the standard plan on a 1:1 basis. Depending on the student's prior knowledge and pace, some weeks may be accelerated, compressed, or covered in greater depth. Key tools: NumPy, PyTorch, torchvision, Matplotlib, Hugging Face, PEFT/LoRA.

Week Topic Key Deliverable
1Perceptrons, gradient descent (mathematical derivation)Implement a single-layer model by hand in NumPy
2Backpropagation, activation functions (ReLU, Sigmoid, Tanh)Implement backprop by hand in NumPy
3Loss functions (MSE, MAE, Cross Entropy) + intro to PyTorchFirst PyTorch MLP
4MLPs, GPU training, tensor manipulationMNIST / Fashion-MNIST classification
5SGD, mini-batch, momentum, Adam/AdamWOptimizer comparison experiment
6Learning rate scheduling, convergence diagnosticsLR finder + lr schedule comparison
7Regularization (Dropout, Early Stopping, Weight Decay)Overfitting control experiment
8Weight initialization, batch normalizationBN on/off ablation
9Data embeddings (text/image/audio) + poolingEmbedding visualization
10Attention mechanism (theory)Implement scaled dot-product attention by hand
11Transformer text encoder (theory + practice)Train a mini Transformer
12Transformers for vision (ViT theory)Inference with a pretrained ViT model
13Autoencoders + model fine-tuning (full vs PEFT/LoRA)LoRA fine-tuning of a pretrained model
14Capstone: a DL pipeline on your own datasetEnd-to-end repo + report

※ Weeks are content units; actual time required varies by student. Recommended ~14 hours, ranging 10-20 hours.

Assessment & Deliverables

Weekly Deliverables

Each week students write a PyTorch notebook and an analysis of the results, in both Korean and English. This leverages international-school students' strength in English while simultaneously preparing for the KOAI Round 2 Korean written response exam.

Capstone

Students build an end-to-end deep learning pipeline for a problem they define themselves (choosing image or text). The problem definition, model design, experiments, and report all become portfolio assets.

Portfolio Impact: Depth Built Over Time

F2 leaves behind 1 GitHub repo koai-deep-learning as a cumulative asset, and the capstone is written up as one case study in Notion. This case study can be used directly as material for the 200-300 character Prompt 2 of the KOAI personal statement.

GitHub

1 organized repo koai-deep-learning

Notion

1 case study (capstone)

Personal statement

Prompt 2 material (200-300 characters)

This track record accumulates as dated evidence in the KOAI Round 1 application's Portfolio 40% · AI competency 30% items as dated evidence. The earlier you start, the more depth you'll have by exam time.

Where This Course Fits

F2 is the second course in the Foundations track of the KOAI curriculum. For the full track structure, see the KOAI Prep Curriculum Hub.

Previous Step (Prerequisite)

F1. Foundations I

Python + Classical ML

Current Course

F2. Foundations II

Neural Networks & Deep Learning

Next step

A1. Advanced I: Computer Vision

High-school division · middle-school division uses M1

Frequently Asked Questions

Do I need to take F1 before F2?

Yes. F2 is for students who have completed F1. If you can demonstrate equivalent competency from elsewhere, enrollment is possible by exception.

Which KOAI subject is F2?

The full scope of Syllabus Subject 2 (Neural Networks and Deep Learning), units 2-1 through 2-2. From perceptrons and backpropagation to transformers and LoRA fine-tuning.

Is it okay if this is my first time using PyTorch?

Yes. Week 3 covers an introduction to PyTorch, and in the preceding weeks 1-2 students implement perceptrons and backpropagation by hand in NumPy to understand the principles first.

Is the ~14 hours fixed?

It's a recommended figure on a 1:1 basis and varies from 10 to 20 hours per student. We estimate an individual time plan in the first diagnostic session.

What comes after F2?

High-school division applicants go deeper with A1 (CV) and A2 (NLP & Audio) and prep for the competition with C1, C2, and C3. Middle-school division applicants cover F1 and F2 in compressed form in the M1 middle-school comprehensive program. For the exact schedule, see the KOAI Competition Guide (https://citcoding.com/competitions/koai.html).

F2 Consultation

We assess your level of F1 completion and design an individualized F2 start point and time plan.

Related Pages

Get a Consultation (02) 540-2922