A Step-by-step Guide to Few-Shot Learning
ArtificialIntelligence
Papers with Code - Zero-Shot Learning
**Zero-shot learning (ZSL)** is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.
Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.
Benchmark datasets for zero-shot learning include [aPY](/dataset/apy), [AwA](/dataset/awa2-1), and [CUB](/dataset/cub-200-2011), among others.
( Image credit: [Prototypical Networks for Few shot Learning in PyTorch
](https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch) )
Further readings:
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://paperswithcode.com/paper/zero-shot-learning-a-comprehensive-evaluation)
- [Zero-Shot Learning in Modern NLP](https://joeddav.github.io/blog/2020/05/29/ZSL.html)
- [Zero-Shot Learning for Text Classification](https://amitness.com/2020/05/zero-shot-text-classification/)
Prompt Engineering Guide
A Comprehensive Overview of Prompt Engineering
Zero-Shot Prompting | Prompt Engineering Guide
Few-Shot Prompting | Prompt Engineering Guide
小資料系列初篇-Few-Shot Learning簡介
“小”數據機器學習的生存之道
小样本学习(Few-shot Learning)综述
作者丨耿瑞莹、李永彬、黎槟华 单位丨阿里巴巴智能服务事业部小蜜北京团队分类非常常见,但如果每个类只有几个标注样本,怎么办呢? 笔者所在的阿里巴巴小蜜北京团队就面临这个挑战。我们打造了一个智能对话开发平…
SetFit: Efficient Few-Shot Learning Without Prompts
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Weights & Biases
Weights & Biases, developer tools for machine learning
huggingface/setfit: Efficient few-shot learning with Sentence Transformers
Efficient few-shot learning with Sentence Transformers - huggingface/setfit: Efficient few-shot learning with Sentence Transformers
Few-shot learning in practice: GPT-Neo and the 🤗 Accelerated Inference API
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
zero shot - Google Search
What is Zero-Shot Classification? - Hugging Face
Learn about Zero-Shot Classification using Machine Learning
零次学习(Zero-Shot Learning)入门
LlamaIndex - Data Framework for LLM Applications
LlamaIndex is a simple, flexible data framework for connecting custom data sources to large language models (LLMs).
imartinez/privateGPT: Interact with your documents using the power of GPT, 100% privately, no data leaks
Interact with your documents using the power of GPT, 100% privately, no data leaks - imartinez/privateGPT: Interact with your documents using the power of GPT, 100% privately, no data leaks
Ask - Stop searching, start asking | Slite
Access and uncover knowledge in your Slite workspace using AI.
Have a question? Just ask.
Chat with Llama 2
9万块的显卡A100 80G跑stable diffusion是什么体验
[译][论文] LLaMA 2:开放基础和微调聊天模型(Meta/Facebook,2023)
ikaijua/Awesome-AITools: Collection of AI-related utilities. Welcome to submit issues and pull requests /收藏AI相关的实用工具,欢迎提交issues 或者pull requests
Collection of AI-related utilities. Welcome to submit issues and pull requests /收藏AI相关的实用工具,欢迎提交issues 或者pull requests - ikaijua/Awesome-AITools: Collection of AI-related utilities. Welcome to subm...
PromtEngineer/localGPT: Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private. - PromtEngineer/localGPT: Chat with your documents on your local device using GPT model...
TensorFlow Hub
bhaskatripathi/pdfGPT: PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!