🖋️
noviceforever
CtrlK
  • About me
  • Miscellaneous
    • Introduction
      • 커리어 요약
      • 데이터 과학이란?
  • Machine Learning
    • Tabular Data
      • XGBoost Algorithm Overview
      • TabNet Overview
      • Imbalanced Learning
        • Introduction
        • Oversampling Basic (SMOTE variants)
        • Cost-sensitive Learning
        • RBF(Radial Basis Function)-based Approach
    • Computer Vision (CNN-based)
      • [Hands-on] Fast Training ImageNet on on-demand EC2 GPU instances with Horovod
      • R-CNN(Regions with Convolutional Neuron Networks)
      • Fast R-CNN
      • Faster R-CNN
      • Mask R-CNN
      • YOLO (You Only Look Once)
      • YOLO v2(YOLO 9000) Better, Faster, Stronger
      • YOLO v3
      • SSD (Single Shot Multibox Detector)
      • Data Augmentation Tips
    • Computer Vision (Transformer-based)
      • ViT for Image Classification
      • DeiT (Training Data-efficient Image Transformers & Distillation through Attention)
      • DETR for Object Detection
    • Natural Language Processing
      • QRNN(Quasi-Recurrent Neural Network)
      • Transformer is All You Need
      • BERT(Bi-directional Encoder Representations from Transformers)
      • DistilBERT, a distilled version of BERT
      • [Hands-on] Fine Tuning Naver Movie Review Sentiment Classification with KoBERT using GluonNLP
      • OpenAI GPT-2
      • XLNet: Generalized Autoregressive Pretraining for Language Understanding
    • Recommendation System
      • Recommendation System Overview
      • Learning to Rank
      • T-REC(Towards Accurate Bug Triage for Technical Groups) 논문 리뷰
    • Reinforcement Learning
      • MAB(Multi-Armed Bandits) Overview
      • MAB Algorithm Benchmarking
      • MAB(Multi-Armed Bandits) Analysis
      • Policy Gradient Overview
    • IoT on AWS
      • MXNet Installation on NVIDIA Jetson Nano
      • Neo-DLR on NVIDIA Jetson Nano
    • Distributed Training
      • Data Parallelism Overview
    • Deployment
      • MobileNet V1/V2/V3 Overview
      • TensorRT Overview
      • Multi Model Server and SageMaker Multi-Model Endpoint Overview
  • AWS AIML
    • Amazon Personalize
      • Amazon Personalize - User Personalization Algorithm Deep Dive
      • Amazon Personalize Updates(~2021.04) 및 FAQ
    • Amazon Bedrock AgentCore
      • AgentCore Runtime
      • AgentCore Gateway
      • AgentCore Identity
      • AgentCore Observability
      • AgentCore Code Interpreter
      • AgentCore Browser
      • AgentCore Memory
    • Customer Support
      • GenAI System Checklist
  • GenAI
    • Theory
      • [Paper Review] Zero-Shot Text-to-Image Generation (DALL-E)
      • [Paper Review] Diffusion 개념 정리
    • Synthetic Data
      • Part 1. 합성 데이터의 필요성
      • Part 2. Seed 데이터 기반 합성 데이터 생성 접근 방식
      • Part 3. Seedless 합성 데이터 생성 접근 방식
      • Part 4. 합성 데이터 생성 시 고려해야 할 일반적인 전략
      • [Paper Review] 10억 페르소나 합성 데이터
      • [Use-case w/ Hands-on] 실제 데이터로부터 합성 QnA 생성하기
    • MoE (Mixture-of-Experts)
      • MoE Overview
      • MoE 모델 비교 및 주요 기법 정리
      • 분산 훈련 기초 개념
      • 전문가 병렬화 (Expert Parallelism)
      • [Optional] NVSHMEM (NVIDIA Shared Memory)
      • 분산 훈련에서의 AWS 네트워킹: EFA (Elastic Fabric Adapter)
      • 분산 훈련 전략
      • ML 엔지니어와 인프라 엔지니어 간 분산 훈련 협업 가이드 및 체크리스트
      • 추론 최적화 개요 (Prefill과 Decoding에 따른 주요 기법 정리)
    • Open Source SLM-Based Hybrid Agent AI Architecture
      • Part 1: Overview & Background
      • Part 2: Agentic Patterns & Prompting
      • Part 3: Tool Integration & Fine-Tuning
    • Fine-tuning
      • [Use-case w/ Hands-on] Azure ML에서 torchtune을 사용한 언어 모델 미세 조정/평가/양자화
      • [Use-case w/ Hands-on] Azure ML Python SDK 및 MLflow를 활용한 Florence-2 모델 파인 튜닝
    • LLM Evaluation
      • Overview
      • 한국어 LLM 평가의 난제
      • [Paper review] KMMLU/KMMLU-Redux/KMMLU-Pro Dataset
      • [Paper review] FunctionChat-Bench
      • 호랑이 한국어 LLM 리더보드
Powered by GitBook
Page cover
On this page
  1. Miscellaneous

Introduction

커리어 요약데이터 과학이란?
PreviousAbout meNext커리어 요약

Last updated 4 years ago