STEM majors are known for high dropoutsStudents need to have more information before jumping into STEM

Constructing an Autoencoder model looks like an art, if not computationally heavy work.

Recurrent Neural Network (RNN) is a neural network model that uses repeated processes with certain conditions.

Generative models are simply repeatedly updated model.

Feed forward and back propagation have significant advantage in terms of speed of calculation and error correction, but it does not mean that we can eliminate the errors.

Bayesian estimation tactics can be used to replace arbitrary construction of deep learning model's hidden layer.

As shown by RBM's autoencoder versions, if the neural network is well-designed, it can perform better than PCA in general when it comes to finding hidden factors.

[COM503] Deep Learning — Swiss Institute of Artificial Intelligence (siai.org) Model examination is available from above

본 문서는 GIAI 산하에서 운영되는 스위스AI대학(Swiss Institute of Artificial Intelligence, SIAI)의 강의노트 중 일부를 한국어로 번역한 것입니다. 영어 원문 및 전체 버전은 아래의 링크를 통해 확인하시기 바랍니다.

As was discussed in [COM502] Machine Learning, the introduction to deep learning begins with history of computational methods as early as 1943 where the concept of Neural Network first emerged.

Transition from column to matrix, matrix to tensor as a baseline of data feeding changed the scope of data science,

People following AI hype are mostly completely misinformedAI/Data Science is still limited to statistical methods

Math in AI/Data Science is not really math, but a shortened version of English paragraph.

Korean GDP growth was 6.4%/y for 50 years until 2022, but down to 2.1%/y in 2020s.Due to low birthrate down to 0.7, population is expected to 1/2 in 30 years.

아래는 지원자들에게 보내는 이메일입니다. 2023년 11월 지원부터 직접 이메일을 보내는 대신 일반에 과제를 공개하고 답안만 받습니다.

상권과 특정 세대 소비자 집중도 관계 분석시 동시성의 오류 발생할 가능성 높아 도구 변수를 이용해 둘 간의 복합 상관관계를 단순 상관관계로 분리해야 실제 기업 사례에서도 잘못된 계산 후 잘못된 결론 얻는 경우 많아 데이터 사이언스 관련 프로젝트를 하다보면, 비일비재하게 발생하는 사안이