Chans Lecture Note

읽고 나면 진짜 쉬워지는 자료 구조

Data Stuctures The Fun Way

Book

Data Structure

길벗 출판사에서 출판한 “읽고 나면 진짜 쉬워지는 자료구조”에 대한 리뷰

딥러닝의 정석 2판

Fundamentals of Deep Learning (2nd)

Book

Deep Learning

한빛미디어에서 출판한 “딥러닝의 정석 (2판)”에 대한 리뷰

러닝 레이

Book

Ray

한빛미디어에서 출판한 “러닝 레이”에 대한 리뷰

Actor-Critic Design Decisions

LectureReview

ReinforcementLearning

UC Berkeley CS285 (2023) Lecture 6-3 Review

Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies

Offline Sequential Evaluation

PaperReview

ReinforcementLearning

Sequential Approach to evaluate Offline RL algorithms as a function of the training set size

Kernel Density Estimation

Python

KAIST

Statistics

KAIST Data Science Programming 1 - 4-5-1. Kernel Density Estimation에 대한 내용입니다.

Pearson Correlation

Python

KAIST

Statistics

KAIST Data Science Programming 1 - 4-4. Pearson Correlation에 대한 내용입니다.

From Evaluation to Actor Critic

LectureReview

ReinforcementLearning

UC Berkeley CS285 (2023) Lecture 6-2 Review

Covariance Matrix

Python

KAIST

Statistics

KAIST Data Science Programming 1 - 4-3. Covariance Matrix에 대한 내용입니다.

Multivariate Gaussian Distribution

Python

KAIST

Statistics

KAIST Data Science Programming 1 - 4.1 Multivariate Gaussian Distribution 에 대한 내용입니다.

Active Offline Policy Selection

PaperReview

ReinforcementLearning

A sequential decision approach that combines logged data with online interaction to identify the best policy.

Actor-Critic Algorithms

LectureReview

ReinforcementLearning

UC Berkeley CS285 (2023) Lecture 6-1 Review

Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble

PaperReview

ReinforcementLearning

Balanced replay scheme that prioritizes samples encountered online while also encouraging the use of near-on-policy samples from offline dataset.

Offline Reinforcement Learning with Implicit Q-Learning

Implicit Q-Learning (IQL)

PaperReview

ReinforcementLearning

Offline RL method with only dataset actions.

신경망으로 구현하는 Logistic Regression

Python

Coursera

DeepLearning.AI

In this post, we will build a logistic regression classifier to recognize cats. This is the summary of lecture “Neural Networks and Deep Learning” from DeepLearning.AI. (slightly modified from original assignment)