This document presents a formula for calculating the loss function J(θ) in machine learning models. The formula averages the negative log likelihood of the predicted probabilities being correct over all samples S, and includes a regularization term λ that penalizes predicted embeddings being dissimilar from actual embeddings. It also defines the cosine similarity term used in the regularization.
데이터 분석가는 어떤 SKILLSET을 가져야 하는가? 2018 DATA MAGIC WEEK 취업콘서트 발표자료 대상 : 빅데이터 경진대회 수상자 및 대학생
2017 데이터야 놀자 발표 자료 최규민 탐색적 데이터 분석에 관하여 이야기 하고 있습니다.
* 행사 정보 :2016년 10월 14일 MARU180 에서 진행된 '데이터야 놀자' 1day 컨퍼런스 발표 자료 * 발표자 : Dylan Ko (고영혁) Data Scientist / Data Architect at Treasure Data * 발표 내용 - 데이터사이언티스트 고영혁 소개 - Treasure Data (트레저데이터) 소개 - 데이터로 돈 버는 글로벌 사례 #1 >> MUJI : 전통적 리테일에서 데이터 기반 O2O - 데이터로 돈 버는 글로벌 사례 #2 >> WISH : 개인화&자동화를 통한 쇼핑 최적화 - 데이터로 돈 버는 글로벌 사례 #3 >> Oisix : 머신러닝으로 이탈고객 예측&방지 - 데이터로 돈 버는 글로벌 사례 #4 >> 워너브로스 : 프로세스 자동화로 시간과 돈 절약 - 데이터로 돈 버는 글로벌 사례 #5 >> Dentsu 등의 애드테크(Adtech) 회사들 - 데이터로 돈을 벌고자 할 때 반드시 체크해야 하는 것
백날 자습해도 이해 안 가던 딥러닝, 머리속에 인스톨 시켜드립니다. 이 슬라이드를 보고 나면, 유명한 영상인식을 위한 딥러닝 구조 VGG를 코드 수준에서 읽으실 수 있을 거에요
MLOps KR 커뮤니티 그룹에서 진행한 MLOps 춘추 전국 시대 정리 발표자료입니다! 다운로드 받으시면 고화질로 볼 수 있습니다!! :)
파이썬으로 멀티코어, 멀티노드, 클라우드를 활용하는 방법에 대해 살펴봅니다. 파이썬으로 어떻게 하면 분산처리 병렬처리를 잘 할 수 있을까요?
http://ga.yonghosee.com 에서 진행하는 구글 어날리틱스(google analytics) 에 대한 강의 슬라이드 입니다. 이 슬라이드는 샘플이지만, 초반부는 실재 강의 교재 그대로 입니다. 이것 자체로도 여러분이 GA를 이해하는데 좀 도움이 된다면 기쁘겠습니다^^ 감사합니다.
The document discusses deep learning paper reading roadmaps and lists several github repositories that aggregate deep learning papers. It also discusses developing mobile applications that utilize machine learning and the differences between developing for iOS versus Android. Lastly, it mentions continuing to learn through practice and experimentation with deep learning techniques.
한빛데브그라운드에서 발표했던 내용입니다. 발표 영상 : https://youtu.be/ohpfSLf0V3Y -- 스타트업 비즈니스에서 데이터를 활용한 전략 수립과 의사결정은 필수적인 요소입니다. 서비스 운영 데이터에서부터 다양한 고객의 행동 로그, 소셜 미디어 데이터까지 다양한 데이터를 모두 모아 분석 환경을 구축하기 위해서는 많은 준비와 고민이 필요합니다. 스타트업에서 빠른 속도와 최소한의 비용, 다양한 분석 Tool들과 연동되는 Data Pipeline, Data Lake, Data Warehouse 구축 경험기를 공유하고자 합니다. 이 과정을 통해 애널리틱스 파이프라인을 구축 과정과 S3, Glue, Athena,EMR, Quicksight와 같은 서버리스 애널리틱스 서비스에 대한 구축 사례를 확인하실 수 있습니다.
OKKY 세미나에서 발표한 Data Science Intro 내용입니다 위키 : https://github.com/Team-Neighborhood/I-want-to-study-Data-Science/wiki
DEVIEW2015 DAY2. 실시간 추천엔진 머신한대에 구겨넣기
The document discusses various machine learning clustering algorithms like K-means clustering, DBSCAN, and EM clustering. It also discusses neural network architectures like LSTM, bi-LSTM, and convolutional neural networks. Finally, it presents results from evaluating different chatbot models on various metrics like validation score.
[233] 대형 컨테이너 클러스터에서의 고가용성 Network Load Balancing: Maglev Hashing Scheduler in IPVS, Linux Kernel
[236] 스트림 저장소 최적화 이야기: 아파치 드루이드로부터 얻은 교훈
The document discusses challenges with using reinforcement learning for robotics. While simulations allow fast training of agents, there is often a "reality gap" when transferring learning to real robots. Other approaches like imitation learning and self-supervised learning can be safer alternatives that don't require trial-and-error. To better apply reinforcement learning, robots may need model-based approaches that learn forward models of the world, as well as techniques like active localization that allow robots to gather targeted information through interactive perception. Closing the reality gap will require finding ways to better match simulations to reality or allow robots to learn from real-world experiences.
This document describes research on using deep learning to predict student performance in massive open online courses (MOOCs). It introduces GritNet, a model that takes raw student activity data as input and predicts outcomes like course graduation without feature engineering. GritNet outperforms baselines by more than 5% in predicting graduation. The document also describes how GritNet can be adapted in an unsupervised way to new courses using pseudo-labels, improving predictions in the first few weeks. Overall, GritNet is presented as the state-of-the-art for student prediction and can be transferred across courses without labels.
This document provides a summary of new datasets and papers related to computer vision tasks including object detection, image matting, person pose estimation, pedestrian detection, and person instance segmentation. A total of 8 papers and their associated datasets are listed with brief descriptions of the core contributions or techniques developed in each.
그림이 정상 출력되는 다음 링크의 자료를 확인해 주세요. https://www.slideshare.net/deview/233-network-load-balancing-maglev-hashing-scheduler-in-ipvs-linux-kernel
[225]NSML: 머신러닝 플랫폼 서비스하기 & 모델 튜닝 자동화하기
[216]Search Reliability Engineering (부제: 지진에도 흔들리지 않는 네이버 검색시스템)
The document discusses running a TensorFlow Serving (TFS) container using Docker. It shows commands to: 1. Pull the TFS Docker image from a repository 2. Define a script to configure and run the TFS container, specifying the model path, name, and port mapping 3. Run the script to start the TFS container exposing port 13377
The document discusses linear algebra concepts including: - Representing a system of linear equations as a matrix equation Ax = b where A is a coefficient matrix, x is a vector of unknowns, and b is a vector of constants. - Solving for the vector x that satisfies the matrix equation using linear algebra techniques such as row reduction. - Examples of matrix equations and their component vectors are shown.
This document describes the steps to convert a TensorFlow model to a TensorRT engine for inference. It includes steps to parse the model, optimize it, generate a runtime engine, serialize and deserialize the engine, as well as perform inference using the engine. It also provides code snippets for a PReLU plugin implementation in C++.
[242]컴퓨터 비전을 이용한 실내 지도 자동 업데이트 방법: 딥러닝을 통한 POI 변화 탐지
The document discusses machine reading comprehension (MRC) techniques for question answering (QA) systems, comparing search-based and natural language processing (NLP)-based approaches. It covers key milestones in the development of extractive QA models using NLP, from early sentence-level models to current state-of-the-art techniques like cross-attention, self-attention, and transfer learning. It notes the speed and scalability benefits of combining search and reading methods for QA.
This presentation explores the practical application of image description techniques. Familiar guidelines will be demonstrated in practice, and descriptions will be developed “live”! If you have learned a lot about the theory of image description techniques but want to feel more confident putting them into practice, this is the presentation for you. There will be useful, actionable information for everyone, whether you are working with authors, colleagues, alone, or leveraging AI as a collaborator. Link to presentation recording and transcript: https://bnctechforum.ca/sessions/details-of-description-part-ii-describing-images-in-practice/ Presented by BookNet Canada on June 25, 2024, with support from the Department of Canadian Heritage.
MuleSoft Meetup on APM and IDP