fast.ai
O que é fast.ai?
fast.ai é um site que oferece cursos e recursos para aprendizado prático de deep learning, machine learning e inteligência artificial (IA). Ele se concentra em tornar as redes neurais acessíveis e fáceis de entender para todos, independentemente de seu conhecimento técnico. O site oferece uma variedade de cursos, tutoriais e artigos que abrangem diversos tópicos em IA e machine learning.
Como usar fast.ai?
Para usar o fast.ai, você pode começar explorando seus cursos e materiais educacionais. Eles oferecem cursos práticos de deep learning para programadores, onde você pode aprender como construir e treinar redes neurais usando frameworks populares como o PyTorch. Além disso, você pode acessar o blog deles, que apresenta artigos sobre ética em IA, avanços técnicos e aplicações do mundo real. O site também oferece recursos para cientistas de dados, incluindo bibliotecas e ferramentas que podem aprimorar seu fluxo de trabalho.
Principais recursos da fast.ai
Cursos práticos de Deep Learning para programadores
Tutoriais de Machine Learning e IA
Blog com artigos sobre ética em IA, avanços técnicos e aplicações do mundo real
Recursos para cientistas de dados, incluindo bibliotecas e ferramentas
Materiais educacionais sobre deep learning, machine learning e IA
Casos de uso da fast.ai
Aprender técnicas práticas de deep learning e machine learning
Explorar ética e avanços em IA
Implementar IA e machine learning em aplicações do mundo real
Acessar recursos e ferramentas para cientistas de dados
Perguntas frequentes de fast.ai
Quais cursos o fast.ai oferece?
Quais tópicos são abordados no blog do fast.ai?
Quais recursos estão disponíveis para cientistas de dados no fast.ai?
Iniciantes sem conhecimento técnico podem usar o fast.ai?
fast.ai Empresa
Mais sobre fast.ai, visite a página sobre nós(https://www.fast.ai/about.html) .
Twitter de fast.ai
Link de Twitter de fast.ai: https://twitter.com/fastdotai
Github de fast.ai
Link de Github de fast.ai: https://github.com/fastai
Avaliações de fast.ai (0)
Análise de fast.ai
fast.ai Análise de tráfego do site
Tráfego geográfico
Top 5 Regiões
fast.ai Iniciar incorporações
Use os emblemas do site para obter o apoio de sua comunidade para o lançamento do Toolify. Eles são fáceis de incorporar em sua página inicial ou rodapé.
Alternativa de fast.ai
16.07%Comparações de fast.ai
Mais conteúdo sobre fast.ai
11 Fascinantes Aplicações de Redes Neurais na Vida Cotidiana
Por Theodore em Maio 14 2024
Explore 11 Fascinantes Usos de Redes Neurais na Vida Diária!
10 Tutoriais Essenciais para Dominar Novas Habilidades
Por Elodie em Maio 17 2024
Desbloqueie a Maestria: 10 Tutoriais Essenciais para Dominar Habilidades!
Escuta de mídias sociais
A Hackers' Guide to Language Models
In this deeply informative video, Jeremy Howard, co-founder of fast.ai and creator of the ULMFiT approach on which all modern language models (LMs) are based, takes you on a comprehensive journey through the fascinating landscape of LMs. Starting with the foundational concepts, Jeremy introduces the architecture and mechanics that make these AI systems tick. He then delves into critical evaluations of GPT-4, illuminates practical uses of language models in code writing and data analysis, and offers hands-on tips for working with the OpenAI API. The video also provides expert guidance on technical topics such as fine-tuning, decoding tokens, and running private instances of GPT models. As we move further into the intricacies, Jeremy unpacks advanced strategies for model testing and optimization, utilizing tools like GPTQ and Hugging Face Transformers. He also explores the potential of specialized datasets like Orca and Platypus for fine-tuning and discusses cutting-edge trends in Retrieval Augmented Generation and information retrieval. Whether you're new to the field or an established professional, this presentation offers a wealth of insights to help you navigate the ever-evolving world of language models. (The above summary was, of course, created by an LLM!) For the notebook used in this talk, see https://github.com/fastai/lm-hackers. 00:00:00 Introduction & Basic Ideas of Language Models 00:18:05 Limitations & Capabilities of GPT-4 00:31:28 AI Applications in Code Writing, Data Analysis & OCR 00:38:50 Practical Tips on Using OpenAI API 00:46:36 Creating a Code Interpreter with Function Calling 00:51:57 Using Local Language Models & GPU Options 00:59:33 Fine-Tuning Models & Decoding Tokens 01:05:37 Testing & Optimizing Models 01:10:32 Retrieval Augmented Generation 01:20:08 Fine-Tuning Models 01:26:00 Running Models on Macs 01:27:42 Llama.cpp & Its Cross-Platform Abilities This is an extended version of the keynote given at posit::conf(2023). Thanks to @wolpumba4099 for chapter titles.
Agentic RAG Explained - Build Your Own AI Agent System from scratch! (Step-by-step code)
🤔 Looking for using AI Agents with RAG? In this episode, join Angelina and Mehdi, for a discussion about Agentic RAG. Who's Angelina: VP of AI and data, Co-founder of Transform AI Studio, two-time fast.ai fellows under Jeremy Howard, published author. https://www.linkedin.com/in/MeetAngelina/ Who's Mehdi: Professor of Computer Science, Co-founder and Chief AI Engineer at Transform AI Studio, NSF fellow, published author. https://www.linkedin.com/in/mehdiallahyari/ What You'll Learn: 🔎 System architecture of Agentic RAG 🚀 Components of an Agentic RAG system: LLM, memory, tools 🛠 Implementing Agentic RAG from scratch vs using frameworks like LangChain ✏️ In This Episode: 00:00 Intro 00:56 What's AI Agent 03:02 Basic architecture for Agentic RAG 09:27 LangChain Code 10:12 Implementation without frameworks 23:17 Minimizing dependencies 📝 Course survey: https://maven.com/forms/e48159 🗓️ Course landing page: https://maven.com/angelina-yang/mastering-rag-systems-a-hands-on-guide-to-production-ready-ai Implementation: https://github.com/mallahyari/twosetai/blob/main/13_agentic_rag.ipynb 🦄 Any specific contents you wish to learn from us? Sign up here: https://noteforms.com/forms/twosetai-youtube-content-sqezrz 🧰 Our video editing tool is this one!: https://get.descript.com/nf5cum9nj1m8 🔨 Implementation: coming soon 📬 Don't miss out on the latest updates - Subscribe to our newsletter: https://mlnotes.substack.com/ 📚 If you'd like to learn more about RAG systems, check out our book on the RAG system: https://angelinamagr.gumroad.com/ 🕴️ Our consulting firm: We help companies that don't want to miss the boat of the current wave of AI advancement by integrating these solutions into their business operations and products. https://www.transformaistudio.com/ Stay tuned for more content! 🎥 Thanks you for watching! 🙌
How Contextual Retrieval Elevates Your RAG to the Next Level
🤔 Looking to enhance your RAG performance? Before we dive in, we have some exciting news! Our RAG live course is coming up soon, and as a way of giving back to our amazing community, we're offering you 15% off. Just use this link: https://maven.com/angelina-yang/mastering-rag-systems-a-hands-on-guide-to-production-ready-ai?promoCode=TwoSetAI We'd love to see you there! 🎉 In the course, you'll have the chance to connect directly with Professor Mehdi (just like I do 😉 in the videos), and you can even ask him your questions 1:1. Bring your real work projects, and during our office hours, we'll help you tackle your day-to-day challenges. This course is for: 01 👇 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 & 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿𝘀: For AI engineers/developers looking to master production-ready RAG systems combining search with AI models. 02 👇 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁𝘀: Ideal for data scientists seeking to expand into AI by learning hands-on RAG techniques for real-world applications. 03 👇 𝗧𝗲𝗰𝗵 𝗟𝗲𝗮𝗱𝘀 & 𝗣𝗿𝗼𝗱𝘂𝗰𝘁 𝗠𝗮𝗻𝗮𝗴𝗲𝗿𝘀: Perfect for tech leads/product managers wanting to guide teams in building and deploying scalable RAG systems In this episode, Mehdi and Angelina introduce the concept of contextual retrieval in Retrieval-Augmented Generation (RAG). We compare it to traditional retrieval methods and discuss how this new approach by Anthropic can significantly reduce retrieval failures by up to 70%. The episode explains the importance of context for Language Learning Models (LLMs) and describes how contextual retrieval enriches document chunks with additional information for improved accuracy. We presents details of the the implementation process, cost considerations, and provide results from Anthropic's experiments showing how contextual retrieval decreases retrieval errors and enhances precision. Who's Angelina: VP of AI and data, Co-founder of Transform AI Studio, two-time fast.ai fellows under Jeremy Howard, published author. https://www.linkedin.com/in/MeetAngelina/ Who's Mehdi: Professor of Computer Science, Co-founder and Chief AI Engineer at Transform AI Studio, NSF fellow, published author. https://www.linkedin.com/in/mehdiallahyari/ What you’ll learn🤓: 🔎 How contextual retrieval works 🚀 Performance and implementation considerations 🛠 Cost considerations and using prompt caching ✏️ In This Episode: 00:00 Introduction to Contextual Retrieval in RAG 00:29 Understanding Contextual Retrieval 02:59 Challenges with Traditional RAG 05:45 Anthropic's Contextual Retrieval Solution 12:54 Implementation and Cost Considerations 15:44 Experimental Results and Recommendations 18:45 Conclusion and Upcoming Course Announcement 🦄 Any specific contents you wish to learn from us? Sign up here: https://noteforms.com/forms/twosetai-youtube-content-sqezrz 🧰 Our video editing tool is this one!: https://get.descript.com/nf5cum9nj1m8 🖼️ Blogpost for today: 🔨 Implementation: 📬 Don't miss out on the latest updates - Subscribe to our newsletter: https://mlnotes.substack.com/ 📚 If you'd like to learn more about RAG systems, check out our book on the RAG system: https://angelinamagr.gumroad.com/ 🕴️ Our consulting firm: We help companies that don't want to miss the boat of the current wave of AI advancement by integrating these solutions into their business operations and products. https://www.transformaistudio.com/ Stay tuned for more content! 🎥 Thanks you for watching! 🙌
Um total de 147 dados de mídia social precisam ser desbloqueados para visualização