ChatGPT를 다양하게 쓸 수 있는 다방면의 Prompt를 수집하고 이를 기반으로 서로 견해 및 경험을 나누고 의논하여 실생활의 다양한 업무 및 일상 생활에서 적용 가능한 Prompt들을 수집하고 그 기반으로 서비스 활성화를 도모하는 랩입니다. 검색엔진의 트렌드와 발전 방향성도 살펴볼 수 있고 이를 통해 다양한 딥러닝 알고리즘의 트렌드와 흐름을 알 수 있습니다. 기존의 indexing과 사용자 입력(query)을 바탕으로 한 Ranking Model기반 문서 추천 방식을 벗어나 대용량 언어 모델을 기반으로 한 ChatGPT의 등장으로 인하여 Zero Shot, One Shot, Few Shot Learning기법의 방법론 활용과 Prompt Engineering을 활용하여 질의를 개선하고 고도화 하려는 트렌드가 형성되고 있고 이를 이번 랩에서 증명하고 새로운 검색의 트렌드를 제시하고 싶습니다. * 본 모임은 열화와 같은 성원에 힘입어 모집인원보다 초과되어 조기 마감되었습니다.

A life worthy of oneself is a flea market where one experiences unexpected joy and joy while selling one's feet. 자기다운 삶이란 발품 팔고 다니다 예상치 못한 즐거움과 환희를 경험하는 벼룩시장이다. "이기적 유전자 반격의 사피엔스" 책 속의 구문 서로의 도메인과 역할이 다른 다양한 분야의 인사분들을 모았으면 좋겠습니다. 이를 바탕으로 다양한 시각에서 ChatGPT를 활용해보고 유용하게 활용했던 사례 기반으로 Prompt들을 모으고 엮어서 활용할 수 있는 서비스 형태를 함께 논의하고 고민해 보았으면 좋겠습니다. 7/3일 월요일은 개인적인 사유로 한 주 SKIP 1> Zero Shot Semantic Segmentation 논문 링크 - https://arxiv.org/abs/1906.00817 설명 링크 - https://deep-learning-study.tistory.com/872 2> Zero Shot Learning 논문 논문 링크 - https://arxiv.org/abs/2011.08641 설명 링크 - https://deep-learning-study.tistory.com/873 3> CaGNet - Context-aware Feature Generation for Zero-shot Semantic Segmentation 논문 링크 - https://arxiv.org/abs/2008.06893 설명 링크 - https://deep-learning-study.tistory.com/874 4> SIGN - Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation 논문 링크 - https://arxiv.org/abs/2108.12517 설명 링크 - https://deep-learning-study.tistory.com/875 5> Metric-based approaches to meta-learning 설명 링크 - http://dmqm.korea.ac.kr/activity/seminar/301 6> Few-Shot Learning https://paperswithcode.com/task/few-shot-learning 7> Language Models are Few-Shot Learners 설명 링크 - https://lee-soohyun.tistory.com/274 8> Few-shot Image Generation via Cross-domain Correspondence 논문 링크 - https://arxiv.org/abs/2104.06820 설명 링크 - https://jjuon.tistory.com/27 9> Meta-Learning with Task-Adaptive Loss function for Few-Shot Learning 논문 링크 - https://arxiv.org/abs/2110.03909 설명 링크 - https://jjuon.tistory.com/30 10> One Shot Learning, Siamese Network, Triplet Loss, Binary Loss 설명 링크 - https://wooono.tistory.com/239 Siamese Neural Networks 개념 이해하기 https://tyami.github.io/deep%20learning/Siamese-neural-networks/ OpenPrompt Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks, which modifies the input text with a textual template and directly uses PLMs to conduct pre-trained tasks. This library provides a standard, flexible and extensible framework to deploy the prompt-learning pipeline. OpenPrompt supports loading PLMs directly from huggingface transformers. In the future, we will also support PLMs implemented by other libraries. For more resources about prompt-learning, please check our paper list. https://thunlp.github.io/OpenPrompt/ https://github.com/thunlp/OpenPrompt Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools. Motivated by the high interest in developing with LLMs, we have created this new prompt engineering guide that contains all the latest papers, learning guides, lectures, references, and tools related to prompt engineering. Happy Prompting! https://github.com/dair-ai/Prompt-Engineering-Guide Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge. This library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include: https://github.com/hwchase17/langchain https://huyenchip.com/2023/04/11/llm-engineering.html Table of contents Part I. Challenges of productionizing prompt engineering …….. The ambiguity of natural languages ………… Prompt evaluation ………… Prompt versioning ………… Prompt optimization …….. Cost and latency ………… Cost ………… Latency ………… The impossibility of cost + latency analysis for LLMs …….. Prompting vs. finetuning vs. alternatives ………… Prompt tuning ………… Finetuning with distillation …….. Embeddings + vector databases …….. Backward and forward compatibility Part 2. Task composability …….. Applications that consist of multiple tasks …….. Agents, tools, and control flows ………… Tools vs. plugins ………… Control flows: sequential, parallel, if, for loop ………… Control flow with LLM agents ………… Testing an agent Part 3. Promising use cases …….. AI assistant …….. Chatbot …….. Programming and gaming …….. Learning …….. Talk-to-your-data ………… Can LLMs do data analysis for me? …….. Search and recommendation …….. Sales …….. SEO Conclusion

ChatGPT를 한번이라도 사용해 보신 분이면 가능합니다.

ChatGPT활용 경험 유무?

딥러닝에서 가장 중요한 요소 2가지는?

Prompt Learning이란 무엇인가?

Zero Shot, One Shot, Few Shot Learning에 대하여 설명해주세요

기존 검색엔진에 대한 이해를 서술해 보세요