DeepLearningAI
DeepLearningAI
  • 435
  • 18 667 545
Carbon Aware Computing for GenAI Developers, a new course with Google Cloud is live!
Enroll for free: bit.ly/3KUeqyw
Today we’re launching Carbon Aware Computing for GenAI Developers, a new short course made in collaboration with Google Cloud and taught by Nikita Namjoshi, Developer Advocate at Google Cloud and Google Fellow on the Permafrost Discovery Gateway.
Training, fine-tuning, and serving generative AI models can be demanding in terms of compute and energy. But these processes don't have to be as carbon-intensive if you choose when and where to run them in the cloud. In this course, you’ll learn how to perform model training and inference jobs with cleaner, low-carbon energy in the cloud.
Explore how to measure the environmental impact of your machine learning jobs and how to optimize their use of clean electricity, and:
- Query real-time electricity grid data: Explore the world map, and based on latitude and longitude coordinates, get the power breakdown of a region (e.g. wind, hydro, coal etc.) and the carbon intensity (CO2 equivalent emissions per kWh of energy consumed).
- Train a model with low-carbon energy: Select a region that has a low average carbon intensity to upload your training job and data. Optimize even further by selecting the lowest carbon intensity region using real-time grid data from ElectricityMaps.
- Retrieve measurements of the carbon footprint for ongoing cloud jobs.
- Use the Google Cloud Carbon Footprint tool, which provides a comprehensive measure of your carbon footprint by estimating greenhouse gas emissions from your usage of Google Cloud.
Throughout the course, you'll work with ElectricityMaps, a free API for querying electricity grid information globally. You'll also use Google Cloud to run a model training job in a cloud data center that is powered by low-carbon energy.
Get started, and learn how to make more carbon-aware decisions as a developer!
Learn more: bit.ly/3KUeqyw
Переглядів: 741

Відео

Learn how to build an agent from scratch with LangGraph
Переглядів 1,5 тис.12 годин тому
Enroll in the full course: bit.ly/3Xz0Hol LangChain, a popular open source framework for building LLM applications, recently introduced LangGraph. This extension allows developers to create highly controllable agents. In this course you will learn to build an agent from scratch using Python and an LLM, and then you will rebuild it using LangGraph, learning about its components and how to combin...
New course with Nexusflow: Function-Calling and Data Extraction with LLMs
Переглядів 1,6 тис.14 годин тому
Enroll now: bit.ly/3VKPUGA Introducing Function-Calling and Data Extraction with LLMs, a short course made in collaboration with Nexusflow and taught by its co-founder and CEO, Jiantao Jiao, and founding engineer, Venkat Srinivasan. This course focuses on two key skills for building LLM applications: function-calling and structured data extraction. Function-calling allows LLMs to execute extern...
New course with Microsoft: Building Your Own Database Agent
Переглядів 3 тис.День тому
Enroll now: bit.ly/3Kz18r0 We’re excited to launch a new course on agentic AI in collaboration with Microsoft: Building Your Own Database Agent. In this course, taught by Adrian Gonzalez Sanchez, Data & AI Specialist at Microsoft, you will develop an AI agent that interacts with tabular data and SQL databases using natural language, simplifying the process for querying and extracting insights. ...
Learn to build multi-agent systems with diverse roles and capabilities with AutoGen
Переглядів 2,2 тис.14 днів тому
Enroll in the full course: bit.ly/3Rg3VcA Explore the first lesson of AI Agentic Design Patterns with AutoGen, a short course made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators Chi Wang, Principle Researcher at Microsoft Research, and Qingyun Wu, Assistant Professor at Penn State University. In this course, you’ll learn how to build and customize mult...
New Course: AI Agents in LangGraph
Переглядів 3,5 тис.21 день тому
Enroll now: bit.ly/4e4FxUQ LangChain, a popular open source framework for building LLM applications, recently introduced LangGraph. This extension allows developers to create highly controllable agents. In this course you will learn to build an agent from scratch using Python and an LLM, and then you will rebuild it using LangGraph, learning about its components and how to combine them to build...
New course on agents! Enroll in AI Agentic Design Patterns with AutoGen
Переглядів 3,6 тис.28 днів тому
Enroll now: bit.ly/3UX0OHg Today we’re launching AI Agentic Design Patterns with AutoGen, a short course made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators Chi Wang, Principle Researcher at Microsoft Research, and Qingyun Wu, Assistant Professor at Penn State University. In this course, you’ll learn how to build and customize multi-agent systems, enab...
Learn to deploy AI models on edge devices like smartphones
Переглядів 2,4 тис.28 днів тому
Enroll in the full course 👉 bit.ly/4bzZD7L We’re excited to announce that Introduction to On-Device AI, a new short course made in collaboration with Qualcomm and taught by Krishna Sridhar, Senior Director of Engineering at Qualcomm, is live! As AI moves beyond the cloud, on-device inference is rapidly expanding to smartphones, IoT devices, robots, AR/VR headsets, and more. Over 6 billion mobil...
New course with Qualcomm: Introduction to On-Device AI
Переглядів 3,2 тис.Місяць тому
Enroll now: bit.ly/3QQzF7O We’re excited to announce that Introduction to On-Device AI, a new short course made in collaboration with Qualcomm and taught by Krishna Sridhar, Senior Director of Engineering at Qualcomm, is live now! As AI moves beyond the cloud, on-device inference is rapidly expanding to smartphones, IoT devices, robots, AR/VR headsets, and more. Over 6 billion mobile devices an...
Learn How to Build Multimodal Search and RAG
Переглядів 3,2 тис.Місяць тому
Enroll in the full course ➡️ bit.ly/4bLKe40 Learn how to build multimodal search and RAG systems. RAG systems enhance an LLM by incorporating proprietary data into the prompt context. Typically, RAG applications use text documents, but, what if the desired context includes multimedia like images, audio, and video? This course covers the technical aspects of implementing RAG with multimodal data...
Learn Multi AI Agent Systems with crewAI: Lesson 1
Переглядів 4,1 тис.Місяць тому
Enroll in the full course 👉 bit.ly/3K9y1u4 Multi AI Agent Workflows with CrewAI is taught by João Moura, founder and CEO of crewAI, and it will teach you key principles of designing effective AI agents and how to organize a team of agents to perform complex, multi-step tasks. Explore key components of multi-agent systems: - Role-playing: Assign specialized roles to agents - Memory: Provide agen...
New short course: Multi AI Agent Systems with crewAI
Переглядів 3,7 тис.Місяць тому
Enroll now: bit.ly/3WHOmxY Announcing a new short course on agents built in collaboration with crewAI! Multi AI Agent Workflows with CrewAI is taught by João Moura, founder and CEO of crewAI, and it will teach you key principles of designing effective AI agents and how to organize a team of agents to perform complex, multi-step tasks. Explore key components of multi-agent systems: - Role-playin...
New course with Weaviate: Building Multimodal Search and RAG
Переглядів 1,9 тис.Місяць тому
Enroll now: bit.ly/3JVgIwW Learn how to build multimodal search and RAG systems. RAG systems enhance an LLM by incorporating proprietary data into the prompt context. Typically, RAG applications use text documents, but, what if the desired context includes multimedia like images, audio, and video? This course covers the technical aspects of implementing RAG with multimodal data to accomplish th...
New course: Building Agentic RAG with LlamaIndex
Переглядів 3,3 тис.Місяць тому
Enroll today: bit.ly/3JN6gaN Introducing Building Agentic RAG with LlamaIndex, made in collaboration with LlamaIndex and taught by its co-founder and CEO, Jerry Liu. Unlike the standard retrieval augmented generation (RAG) pipeline-suitable for simple queries across a few documents-agentic RAG adapts based on initial findings to enhance further data retrieval. You'll use this framework to build...
New course with Hugging Face: Quantization in Depth 🤗
Переглядів 2,3 тис.Місяць тому
Enroll now: bit.ly/44nXDNa We’re excited to introduce Quantization in Depth, a new short course built in collaboration with Hugging Face, taught by Younes Belkada and Mark Sun, and designed to provide a deep technical understanding of quantization. This course lets you build and customize your own linear quantizer from scratch, going beyond standard open source libraries such as PyTorch and Qua...
New course with Comet: Prompt Engineering for Vision Models
Переглядів 2,3 тис.Місяць тому
New course with Comet: Prompt Engineering for Vision Models
New course! Getting Started with Mistral is live
Переглядів 4,2 тис.2 місяці тому
New course! Getting Started with Mistral is live
New course with Hugging Face: Quantization Fundamentals
Переглядів 3 тис.2 місяці тому
New course with Hugging Face: Quantization Fundamentals
New course with Unstructured: Preprocessing Unstructured Data for LLM Applications
Переглядів 3,8 тис.2 місяці тому
New course with Unstructured: Preprocessing Unstructured Data for LLM Applications
New course with Giskard: Red Teaming LLM Applications
Переглядів 2,3 тис.2 місяці тому
New course with Giskard: Red Teaming LLM Applications
New course with LlamaIndex: JavaScript RAG Web Apps with LlamaIndex
Переглядів 2,8 тис.2 місяці тому
New course with LlamaIndex: JavaScript RAG Web Apps with LlamaIndex
New course with Predibase: Efficiently Serving LLMs
Переглядів 1,8 тис.3 місяці тому
New course with Predibase: Efficiently Serving LLMs
New course with Neo4J: Knowledge Graphs for RAG
Переглядів 7 тис.3 місяці тому
New course with Neo4J: Knowledge Graphs for RAG
New course with Hugging Face: Open Source Models with Hugging Face
Переглядів 4,9 тис.3 місяці тому
New course with Hugging Face: Open Source Models with Hugging Face
New course with Meta: Prompt Engineering with Llama 2
Переглядів 4,7 тис.3 місяці тому
New course with Meta: Prompt Engineering with Llama 2
New course with AWS: Serverless LLM apps with Amazon Bedrock
Переглядів 3,9 тис.4 місяці тому
New course with AWS: Serverless LLM apps with Amazon Bedrock
New course with Pinecone: Building Applications with Vector Databases
Переглядів 3,6 тис.4 місяці тому
New course with Pinecone: Building Applications with Vector Databases
New course with CircleCI: Automated Testing for LLMOps
Переглядів 2,7 тис.5 місяців тому
New course with CircleCI: Automated Testing for LLMOps
New course with Google Cloud: LLMOps
Переглядів 3,8 тис.5 місяців тому
New course with Google Cloud: LLMOps
New course with LangChain: Build LLM Apps with LangChain.js
Переглядів 3,3 тис.5 місяців тому
New course with LangChain: Build LLM Apps with LangChain.js

КОМЕНТАРІ

  • @uberalus
    @uberalus 11 годин тому

    Before we came along, the world experienced periods with much higher levels of carbon in the atmosphere than we have now, and yet plants thrived, and life in general flourished. You are certainly not unintelligent, so you must have sold out and become a propagandist in exchange for... what? It's hard to respect a scientist who publicly pushes a carbon-based climate hoax.

  • @bodanerius
    @bodanerius 12 годин тому

    Im reducing the carbon footprint by unsubscribing to this channel. If you'll excuse. Im off to watch trees grow using photosynthesis, ie eating CO2

  • @MAFIMA
    @MAFIMA 12 годин тому

    Zzzzzz

  • @NidhiPatel-lg4ui
    @NidhiPatel-lg4ui 13 годин тому

    good explaination

  • @umarfarooq-su3dz
    @umarfarooq-su3dz 13 годин тому

    is it the same course on coursera

  • @pranavgandhiprojects
    @pranavgandhiprojects 19 годин тому

    Loved the explaination...thanks

  • @lautaropavez
    @lautaropavez 2 дні тому

    Is anyone who is starting this in june 2024?

  • @fire_nakamura
    @fire_nakamura 2 дні тому

    Here to learn English

  • @SaritadeviSao
    @SaritadeviSao 2 дні тому

    I don't get it this one

  • @dahiruibrahimdahiru2690
    @dahiruibrahimdahiru2690 2 дні тому

    Any advice about looking at the code? I usually find myself jogging between the code and the paper.

  • @aniketbhand1824
    @aniketbhand1824 2 дні тому

    in relu's derivative it should be (z) for z>=0 or 1 for (z)>=0 ?

  • @bharatbhimshetty4766
    @bharatbhimshetty4766 3 дні тому

    non-convex loss function to convex loss function using log loss is a turning point.

  • @ArtificialIntelligenceIs
    @ArtificialIntelligenceIs 4 дні тому

    It's the present, can you imagine the future?

  • @bharatbhimshetty4766
    @bharatbhimshetty4766 4 дні тому

    But when to do each of them? which case suits standard scaling and which case suits mean normalization?

  • @Constantine_the_great.
    @Constantine_the_great. 5 днів тому

    You are a good man

  • @Hanaa_MuslimaYemen
    @Hanaa_MuslimaYemen 5 днів тому

    I am your sister from Yemen, and by Allah I only spoke out of hunger and distress. My mother, my brothers, and I lessons and tears. We are in a situation that only God knows about. God is sufficient for us, and He is the best disposer of affairs for those who brought us to this situation. By Allah Almighty, I did not write this appeal out of distress and distress. Poverty, O world, they have felt it So, I hope for you. By Allah Almighty, Lord of the Great Throne, he ate what I had in the house. By Allah, my brothers, he is my brothers by sitting in the house. Who has no food? By God, we are in a very difficult situation. We have 6 people entering the house, and my father has died, and there is no one who can depend on us and who lives in it.We live in a rented house because we cannot pay the rent we owe. '''''''''''''''''''''''''''''''''''''''''' ''''''''''''''''''''''''''''''''''''''''''''''''' ''''''''''''''''''''''''''''''''''''''''''''''''' ''''''''''''' My brother, my first words are: I swear to God that I will not lie to you or deceive you. I am a Yemeni girl displaced from the war. My family and I live in a rented house in Al-Shahrab 15,000 Yemenis among us, and now we owe 45,000 for 3 months. The owner of the house is one of the people who does not have mercy, by God, my brother. He comes every day, insulting us, talking about us, and moving from the house to the street because we were unable to pay him the rent. The neighbors saw us crying and came back.They came back to talk to the neighbors and we were given the weekend. So we made him swear by God. He will take us out into the street. Have mercy on him and us. Our country is due to this war and we do not find food for our day, and my brothers and I live in a difficult life. Our father died, may God have mercy on him, and we have no one in this world who was with us in these harsh circumstances. My younger brothers went out into the street and saw...The neighbors eat and stand at their door in order to give them bread even if they break it. By God, to whom belongs the dominion of the heavens and the earth, they closed the door and expelled them and came back crying. They are dying of hunger. No one has mercy on them and a holiday is returned. I have made a living, and now if one of us helps us with a kilo of flour, I swear to God, I am dying of hunger. My brother, I am an alien to God. Then, I ask you to help me for the sake of God. I ask you, by God, to love goodness and to help me, even if you can, by messaging me on WhatsApp.On this number 00967736246190 and ask for the name of my card and send it and do not be late and may God reward you with all the best, my brothers Sagar, see how they are and help us and save us before they throw us out in the street, you will be lost or we will die of hunger. My family and I ask you, by God, if you are able to help us, do not be late and may God reward you well..`/--~«««~-♡~♡~♡~~•~•~♡~♡~♡~♡~♡~♡♡؟?♡~~~: ~:~.~¡~~¡~¡~.~;I.i.i.i.i.i. i.I.|-.&__...،،.....،.،،،،،...،،..،،،،،،،،;"🎉😮🎉😮🎉

  • @FelipeCampelo0
    @FelipeCampelo0 5 днів тому

    Now that I have taken an AI course in my university, I can finally fully appreciate this series of videos. I mean, it was quite hard during the first time, but it finds like perfect now!

  • @marcomaher4601
    @marcomaher4601 6 днів тому

    super great explanation . Thank you

  • @portableff1233
    @portableff1233 6 днів тому

    My dream become ai ml enginner i am not giveup try my best for contribuate in ai Love from india i am biggner in that field that day i am learning python

    • @jorgesanabria6484
      @jorgesanabria6484 6 днів тому

      Never give up sir, so many ppl in my company were born in India and made it senior in UK as ml engineer

  • @ReflectionOcean
    @ReflectionOcean 7 днів тому

    By YouSum Live 00:00:31 Introduction to workshop on llm agents 00:01:01 Utilizing cutting-edge tools like L index and true lens 00:01:16 Importance of gaining insights into llm agent building 00:05:00 Significance of interleaving reasoning and actions in llm apps 00:08:56 Limitations in llm agents: failures, infinite loops, hallucinations 00:10:09 Evolution from rag to agents for dynamic query handling 00:10:23 Data agents' role in automating knowledge with search and synthesis 00:15:25 Core components of agents: reasoning loop and tools 00:17:24 Llama index's architecture for advanced reasoning with query engines 00:19:33 Example of agent using query tools for Uber and Lyft comparison 00:21:00 Strategies for handling large tool responses 00:21:11 On-demand loader and load/search tool for data indexing 00:21:42 Mitigating overflow by indexing data beforehand 00:21:48 Agents struggling with tool overload 00:22:00 Indexing tools and metadata for efficient query handling 00:29:19 Importance of context relevance, groundedness, and answer relevance 00:29:25 Evaluating llm agents using the rag Triad and agent quad 00:42:03 Building agents over external APIs like Yelp 00:42:20 Utilizing tool specs for agent interactions 00:43:58 Implementing efficient data retrieval for agents 00:44:06 Utilizing convenient abstractions for data indexing 00:44:18 Incorporating top-k search for relevant results 00:44:45 Setting up agent with Yelp tool specifications 00:46:18 Establishing feedback functions for evaluation 00:47:12 Evaluating similarity between user and agent queries 00:49:08 Setting up ground truth for baseline evaluations 00:49:33 Monitoring and analyzing performance metrics 01:00:02 Applying MLOps principles to enhance LM and GPTs By YouSum Live

  • @raphaelnoronha1419
    @raphaelnoronha1419 9 днів тому

    Ok, but what I am looking at the end of it? (1) The weights (W) that transform the image matrix (Ii) in a vector (such as f(a)) --> Ii * W = F(Ii) = vector with n dimensions? (2) Such parameters (W) should be constant for any image?

  • @Michel-gv1sr
    @Michel-gv1sr 9 днів тому

    There are also algorithms and tools (de-esser) to remove the annoying sssss 😅

  • @ComplexOne
    @ComplexOne 11 днів тому

    This is formula of the EMA responds quicker than the LWMA...

  • @hyderfida5977
    @hyderfida5977 11 днів тому

    please someone tell me how can i access optional lab?

  • @HarvinderSingh-ki8pl
    @HarvinderSingh-ki8pl 12 днів тому

    Sir, thanks for the lesson but the voice is way too low. Can you please speak louder or somehow improve the voice quality in future videos. I have to read captions all the time because I cannot hear.🙏

  • @HarvinderSingh-ki8pl
    @HarvinderSingh-ki8pl 12 днів тому

    Sir, thanks for the lesson but the voice is way too low. Can you please speak louder or somehow improve the voice quality in future videos. I have to read captions all the time because I cannot hear.🙏

  • @akan3350
    @akan3350 12 днів тому

    This is high quality content but I feel it's also ML generated 😂😂

  • @user-vg7zr5fz4z
    @user-vg7zr5fz4z 12 днів тому

    Sir in every video your dress code is same . Is this is your uniform ?

  • @Astute_
    @Astute_ 12 днів тому

    Sir can you use a better mic?

  • @engineeringmadeasy
    @engineeringmadeasy 13 днів тому

    Hello there, I'd like to jump into Tech Industry. I want to become Software Engineer and I think these AI course can help me alot. I have dropped an email twice to your team but never heard back from them. Is there any other way to reach you guys out? Any sort of help would be appreciated. Thanks

    • @HarvinderSingh-ki8pl
      @HarvinderSingh-ki8pl 12 днів тому

      bro no offence but what do u want them to do about u becoming a software engineer. If you want a roadmap there are plenty on yt and yes its very hard at first.

  • @dikshadayal4300
    @dikshadayal4300 13 днів тому

    x should be a column matrix because if it is a row matrix then W . X would be w1x1 + w1x2 + w3x3 + ............. + wnxn

  • @brunofilipeaguiar
    @brunofilipeaguiar 14 днів тому

    How many takes Andrew Ng took to draw the horse without laughing?

  • @DogSneeze
    @DogSneeze 14 днів тому

    Is there a custom GPT to edit out the obnoxious self-flattery to access the 10 minutes of useful content? "Pants" was a horrible metaphor and her inability to even understand the question at the end about linguistic clarity shows you how terrible she is with language in the first place.

  • @user-qf3vg2sm6w
    @user-qf3vg2sm6w 14 днів тому

    I´m doing the course right now, it´s exactly the right speed, level of knowledge and I love the interactive panel beside the video content. Well done and thanks for creating the course, it will be useful to my work!

  • @maryamii0414
    @maryamii0414 14 днів тому

    Thank you so much , very informative video!!

  • @black-sci
    @black-sci 14 днів тому

    I don't why but I'm getting faster performance with simple SGD than with the momentum.

  • @hyderfida5977
    @hyderfida5977 15 днів тому

    how can i access optional lab?

  • @ajeethkumar6296
    @ajeethkumar6296 16 днів тому

    Thanks for the clear cut explanation

  • @pnachtwey
    @pnachtwey 17 днів тому

    It would have been nice to see it work with real python code and real data. What instructors don’t understand is they all use different symbols and terminology. I also don’t like their scribbling. I have data I use to test. There are 5 different parameters. The ‘terrain is more like the grand canyon and not a bowl so the path is extremely narrow. Adagrad works best so far. I will try ADAM.

  • @ojasvisingh786
    @ojasvisingh786 17 днів тому

    🎉

  • @JourneyToSAP
    @JourneyToSAP 17 днів тому

    Nice

  • @lampham7874
    @lampham7874 18 днів тому

    I have watched a few videos about few shot learning before this on but this is the most understandable.

  • @user-sh6jm9pz9s
    @user-sh6jm9pz9s 19 днів тому

    I know this maybe a silly question but at 21:47 how do I know that the "item_id" is going to be "7"?

  • @Makima-qi3zg
    @Makima-qi3zg 20 днів тому

    great🧠

  • @dkierans
    @dkierans 20 днів тому

    Please tell me you revoked that key!

  • @fft4752
    @fft4752 21 день тому

    thank you for making this videos

  • @syedistiukraja2454
    @syedistiukraja2454 24 дні тому

    Is these videos are AI generated?

  • @sumankhatri2679
    @sumankhatri2679 24 дні тому

    Thank you professor for this great mastercourse

  • @sumankhatri2679
    @sumankhatri2679 24 дні тому

    Thank you professor for this nice course

  • @cdtavijit
    @cdtavijit 26 днів тому

    This was quite amazing. It covered quite a lot in that one hour including various agentic workflows, reflection and tool calling. Of course it was just a starter, but I kept taking notes to search for more in depth materials or code on autogen.