It was good that I could review the necessary parts by dividing them into short sections.
I wish I had had more basic mathematical knowledge, but I think it would have been easier to understand.
The practice assignments were presented step by step, and the files were provided so that I could compare and find the wrong parts, which was good.
To be honest, I didn't completely understand everything, but I was able to understand the important concepts in the big picture.

protestemail783195

This course teaches the “core concepts” of deep learning required to work in the deep learning field and the practical skills required to perform actual deep learning projects through hands-on training using PyTorch.

peterbyun969574

Complete mastery of deep learning theory + PyTorch practice

Hi! Thank you for your honest feedback and great review! I guess there are still some parts that are a bit difficult to explain. In the next lecture, I will focus on the basics and explaining them in a more understandable way!

이론과 실습 한 번에

이론 실습 모두

개념정리

딥러닝기초

딥러닝모델

자연어처리

ディープラーニング 現業に携わるために必要なディープラーニングの「核心概念」を学び、PyTorchを活用した実習を通じて実際のディープラーニングプロジェクトを遂行するのに必要な実務を教えてくれる講義です。

입문

초급

중급이상

Deep Learning(DL)

파이토치

PyTorch

Computer Vision(CV)

자연어처리(Natural Language Processing)

transformer

ディープラーニング理論+ PyTorch実務完全征服

講義紹介

PyTorch 環境設定 および PyTorch の基礎

ディープラーニングとは？

損失関数 (Loss Function)

Advanced Topics in Loss Function (損失関数 深化)

勾配降下法 (Gradient Descent)

勾配降下 (応用)

活性化関数 (Activation Function)

최적화 (Optimization)

PyTorchで全結合NNを作ってみる！

正則化 (Regularization)

学習率スケジューラ (Learning Rate Scheduler)

初期化 (Initialization)

標準化 (Normalization)

畳み込みニューラルネットワーク (CNN)

再帰型ニューラルネットワーク (RNN)

アテンションとトランスフォーマー