![DeepLearningAI](/img/default-banner.jpg)
- 445
- 19 402 702
DeepLearningAI
Registrace 22. 08. 2017
Welcome to the official DeepLearning.AI CZcams channel! Here you can find the videos from our Coursera programs on machine learning as well as recorded events.
DeepLearning.AI was founded in 2017 by machine learning and education pioneer Andrew Ng to fill a need for world-class AI education.
DeepLearning.AI has created high-quality AI programs on Coursera that have gained an extensive global following. By providing a platform for education and fostering a tight-knit community, DeepLearning.AI has become the pathway for anyone looking to build an AI career.
DeepLearning.AI was founded in 2017 by machine learning and education pioneer Andrew Ng to fill a need for world-class AI education.
DeepLearning.AI has created high-quality AI programs on Coursera that have gained an extensive global following. By providing a platform for education and fostering a tight-knit community, DeepLearning.AI has become the pathway for anyone looking to build an AI career.
Learn best practices for multimodal prompting using Google's Gemini model family!
Enroll now: bit.ly/3YPKAUa
Introducing Large Multimodal Model Prompting with Gemini, a new short course built in collaboration with Google Cloud, and taught by Erwin Huizenga, Developer Advocate for Generative AI at Google Cloud.
Large Multimodal Models (LMMs) represent a significant evolution from language models by integrating different data modalities, allowing for more comprehensive outputs based on varied input types such as text, images, and video.
For LMMs, prompt structure becomes even more important. For example, placing text inputs, such as a patient’s medical history, before image inputs like an X-ray, can improve the model’s interpretation. Conversely, for tasks like image captioning, leading with the image may yield better results. In this course, you'll explore best practices for multimodal prompting, and learn how to properly set parameters for optimized results.
Additionally, you’ll learn how to integrate Gemini with external APIs and databases using function calling, with the ability to infuse your applications with real-time data and dynamic content.
In detail, you’ll explore:
- Introduction to Gemini Models: Learn the differences and use cases for Gemini Nano, Pro, Flash, and Ultra. Understand how to select optimal models based on capability, latency, and cost.
- Multimodal Prompting and Parameter Control: Learn techniques for structuring effective text-image-video prompts. Fine-tune key parameters like temperature, top_p, top_k to control model creativity vs determinism.
- Best Practices for Multimodal Prompting: Get hands-on experience with prompt engineering for Gemini multimodal models, and role assignment, task decomposition, and formatting.
- Creating Use Cases with Images: Build engaging multimodal applications like interior design assistants and receipt itemization tools.
- Developing Use Cases with Videos: Implement "needle in the haystack" semantic video search powered by Gemini's large context window.
- Integrating Real-Time Data with Function Calling: Extend Gemini with external knowledge and live data via function calling and API integration.
Start building advanced AI applications that can reason across multiple data modalities today!
Note that due to technical requirements, this course features downloadable-only notebooks on the learning platform. You are free to download, review, and run these notebooks on your own.
Learn more: bit.ly/3YPKAUa
Introducing Large Multimodal Model Prompting with Gemini, a new short course built in collaboration with Google Cloud, and taught by Erwin Huizenga, Developer Advocate for Generative AI at Google Cloud.
Large Multimodal Models (LMMs) represent a significant evolution from language models by integrating different data modalities, allowing for more comprehensive outputs based on varied input types such as text, images, and video.
For LMMs, prompt structure becomes even more important. For example, placing text inputs, such as a patient’s medical history, before image inputs like an X-ray, can improve the model’s interpretation. Conversely, for tasks like image captioning, leading with the image may yield better results. In this course, you'll explore best practices for multimodal prompting, and learn how to properly set parameters for optimized results.
Additionally, you’ll learn how to integrate Gemini with external APIs and databases using function calling, with the ability to infuse your applications with real-time data and dynamic content.
In detail, you’ll explore:
- Introduction to Gemini Models: Learn the differences and use cases for Gemini Nano, Pro, Flash, and Ultra. Understand how to select optimal models based on capability, latency, and cost.
- Multimodal Prompting and Parameter Control: Learn techniques for structuring effective text-image-video prompts. Fine-tune key parameters like temperature, top_p, top_k to control model creativity vs determinism.
- Best Practices for Multimodal Prompting: Get hands-on experience with prompt engineering for Gemini multimodal models, and role assignment, task decomposition, and formatting.
- Creating Use Cases with Images: Build engaging multimodal applications like interior design assistants and receipt itemization tools.
- Developing Use Cases with Videos: Implement "needle in the haystack" semantic video search powered by Gemini's large context window.
- Integrating Real-Time Data with Function Calling: Extend Gemini with external knowledge and live data via function calling and API integration.
Start building advanced AI applications that can reason across multiple data modalities today!
Note that due to technical requirements, this course features downloadable-only notebooks on the learning platform. You are free to download, review, and run these notebooks on your own.
Learn more: bit.ly/3YPKAUa
zhlédnutí: 894
Video
Enroll in "Building AI Applications with Haystack," our new short course!
zhlédnutí 2,4KPřed 19 hodinami
Enroll now: bit.ly/4cvGBPJ We’re excited to introduce Building AI Applications with Haystack, a short course made in collaboration with Haystack. Haystack is a framework that simplifies the process of creating LLM applications, and in this course, taught by Tuana Çelik, Developer Relations Lead at Haystack, you will learn how to use this framework to build applications that are flexible, extend...
New course with Lamini and Meta: Improving Accuracy of LLM Applications
zhlédnutí 2,5KPřed 14 dny
Enroll now: bit.ly/3yEasaS Improving Accuracy of LLM Applications was made in collaboration with Lamini and Meta and taught by Lamini’s CEO and co-founder Sharon Zhou, and Meta’s Senior Director of Partner Engineering, Amit Sangani. Developers often face challenges with inconsistent outcomes when working with LLM applications. This course provides a structured approach to improve the accuracy a...
A new Data Engineering Professional Certificate is joining our catalog!
zhlédnutí 3,4KPřed 21 dnem
Pre-enroll now: bit.ly/3A6jQEp Announcing Data Engineering, a new advanced professional certificate offered through Coursera, now available for pre-enrollment! You can’t have good data analysis without data that is effectively ingested, stored, transformed, and served to meet the needs of downstream data stakeholders such as data scientists and machine learning engineers. Data engineering is th...
New course by Andrew Ng: AI Python for Beginners
zhlédnutí 19KPřed 21 dnem
Learn more: bit.ly/3WuCdKL AI Python for Beginners is designed to help you leverage the power of Python programming, even if your goal isn’t to become a software developer or AI engineer. This four-part course that teaches you to code practical AI applications from day one, even if you’ve never programmed before. You’ll learn with support from an AI chatbot that can help you get immediate feedb...
New course with Vectara! Embedding Models: From Architecture to Implementation
zhlédnutí 2,4KPřed 28 dny
Enroll today: bit.ly/3yfHmOP We’re excited to introduce Embedding Models: From Architecture to Implementation, a short course built in collaboration with Vectara, and taught by Ofer Mendelevitch, Vectara’s Head of Developer Relations. Many LLM apps use a single embedding model for both questions and answers. This leads to retrieval issues, such as getting responses similar to the question itsel...
New course series with Flower Labs: Federated Learning
zhlédnutí 2,2KPřed měsícem
Enroll now: bit.ly/4fe8azw Addressing security and privacy in applications is vital. Applications built on LLMs pose special challenges, especially regarding private data. Introducing Federated Learning, a two-part course series built in collaboration with Flower Labs, designed to help you learn how to use Flower, a popular open source framework, to build a federated learning system, and implem...
Learn to pretrain LLMs from scratch in our new short course with Upstage
zhlédnutí 3,2KPřed měsícem
Enroll now: bit.ly/4bZCtrb In Pretraining LLMs, created in collaboration with Upstage and taught by its CEO Sung Kim, and CSO, Lucy Park, you’ll explore the creation of large language models (LLMs) like Llama, Grok, and Solar using a technique called pretraining, which is the first step of training a large language model. You’ll learn to pretrain a model from scratch and also to take a model th...
Pre-enroll in Generative AI for Software Development, a new course from DeepLearning.AI
zhlédnutí 3,2KPřed měsícem
Pre-enroll here: bit.ly/3zJQ9sR Generative AI is transforming software development by enhancing and augmenting traditional coding practices. In this Skill Certificate from DeepLearning.AI, you’ll learn from Laurence Moroney, Chief AI Scientist at VisionWorks Studios and former AI lead at Google, as he guides you through a comprehensive pathway to understand and apply generative AI technologies ...
Prompt Compression and Query Optimization, a new course with MongoDB is coming soon
zhlédnutí 2,2KPřed měsícem
Enroll for free: bit.ly/3L8Gnmi This course focuses on integrating traditional database features with vector search capabilities to optimize the performance and cost-efficiency of large-scale Retrieval Augmented Generation (RAG) applications. You'll learn how to apply these key techniques: - Prefiltering and Postfiltering: These are techniques to filter results based on specific conditions. Pre...
Carbon Aware Computing for GenAI Developers, a new course with Google Cloud is live!
zhlédnutí 3,3KPřed 2 měsíci
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 pro...
Learn how to build an agent from scratch with LangGraph
zhlédnutí 3,9KPřed 2 měsíci
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
zhlédnutí 2,2KPřed 2 měsíci
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
zhlédnutí 3,6KPřed 2 měsíci
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
zhlédnutí 2,8KPřed 2 měsíci
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 on agents! Enroll in AI Agentic Design Patterns with AutoGen
zhlédnutí 4,8KPřed 3 měsíci
New course on agents! Enroll in AI Agentic Design Patterns with AutoGen
Learn to deploy AI models on edge devices like smartphones
zhlédnutí 2,8KPřed 3 měsíci
Learn to deploy AI models on edge devices like smartphones
New course with Qualcomm: Introduction to On-Device AI
zhlédnutí 3,9KPřed 3 měsíci
New course with Qualcomm: Introduction to On-Device AI
Learn How to Build Multimodal Search and RAG
zhlédnutí 4,6KPřed 3 měsíci
Learn How to Build Multimodal Search and RAG
Learn Multi AI Agent Systems with crewAI: Lesson 1
zhlédnutí 5KPřed 3 měsíci
Learn Multi AI Agent Systems with crewAI: Lesson 1
New short course: Multi AI Agent Systems with crewAI
zhlédnutí 4,6KPřed 3 měsíci
New short course: Multi AI Agent Systems with crewAI
New course with Weaviate: Building Multimodal Search and RAG
zhlédnutí 2,3KPřed 3 měsíci
New course with Weaviate: Building Multimodal Search and RAG
New course: Building Agentic RAG with LlamaIndex
zhlédnutí 4,3KPřed 3 měsíci
New course: Building Agentic RAG with LlamaIndex
New course with Hugging Face: Quantization in Depth 🤗
zhlédnutí 2,7KPřed 3 měsíci
New course with Hugging Face: Quantization in Depth 🤗
New course with Comet: Prompt Engineering for Vision Models
zhlédnutí 2,5KPřed 4 měsíci
New course with Comet: Prompt Engineering for Vision Models
New course! Getting Started with Mistral is live
zhlédnutí 4,4KPřed 4 měsíci
New course! Getting Started with Mistral is live
New course with Hugging Face: Quantization Fundamentals
zhlédnutí 3,2KPřed 4 měsíci
New course with Hugging Face: Quantization Fundamentals
New course with Unstructured: Preprocessing Unstructured Data for LLM Applications
zhlédnutí 4,4KPřed 4 měsíci
New course with Unstructured: Preprocessing Unstructured Data for LLM Applications
New course with Giskard: Red Teaming LLM Applications
zhlédnutí 2,7KPřed 4 měsíci
New course with Giskard: Red Teaming LLM Applications
I think 3 of the courses on Coursera are free right..why here only one is given..
jai jinendra sir & thanks for excellent explanation
I don't see the point in what he said about 1x1 convolution reducing filters? For any convolution filter 3x3, 5x5 or any size, the output channels are always determined by the number of filters not by filter size. So if you have 192 input channels, if you use 32 3x3 size filters, that will also reduce the channel dimension to 32 just like using 32 1x1 filters. So why decouple reducing height width and reducing channels? Filters of any size do both at the same time anyway.
Okay, One use case is explained in the next Inception motivation video
5:10 can someone tell me how it is negative 2 and not positive 2. we re taking it in positive x axis so it should be positive 2?
it's true that the y-axis is typically referred to as the positive axis, this does not mean it can't have negative values. In most graphs, including this one, the y-axis can extend into both positive and negative values. to be more clear you can visit this docs.google.com/document/d/1iGjDmuidb5-Kym1g1F8U_VSCtKXUc74gZL6tzjg8LUQ/edit?usp=sharing
how to conclude that we have reached global minima?
Hey there seems to be a delay. It says it's starting in September now?
Lee George White Thomas Moore Larry
I done this course what next
Do u watch yt video or buy couse?
@@Dontneedlearn55 it is free the link in bio you have to login deep learning ai website and then course will appear you
Then what is the initial value of W and B for first time calculation
we randomly choose one.
A thrilling announcement about the course! SymthOS offers sophisticated AI multi-agent workflows. #MultiAgentSystems #SymthOS #AI #TechLearning
Did he skipped fully connected layers
Please how do I get access to the optional Lab?
Idk why I cannot play the videos. Does that happen to everyone?
Super helpful course!!!
Where can I take it?
AI clowns get glocked
Please use open source APIs with free trial option. I can't replicate the steps due to paid OpenAI API.
Perez Laura Harris Kimberly Rodriguez Patricia
OPTIONAL LAB NOTEBOOKS, where are these, I am not getting the links.
When is it gonna launch? I can't see it online.
is the specialization on Coursera plus ?
Thank you so much really enjoyed it. It reminds me of CS229 !
Will there be any code?
can someone explain this video? im almost done with all the previous videos. but more i watch this video i feel like im missing out something i do still dont know why
How can i know what values of (w,b) are the best, I have to calculate all the combinations of w and b?
when its third module upload?
Great job 🎉
All the best❤🎉
I'm excited for this course. But when will you release a course on dspy?
Thankyou sir!!! Loved this course and the way it was taught especially the gradual simple to complex transition. We stayed in the goldilock zone and happy covered the course and learnings. ❤
28 zoom notifications! Travis working too hard
Will AI trained on code from millions of average/mediocre developers not produce just more mediocre developers with that course?
You got the point. It will lower the already poor average skill level of developers further
2:30 its almost there !
where is the OPTIONAL LAB notebook?
Could you please upload the reminding sessions😢
can we have the slides plz ?
paid?
Sounds like a great course 🎉
😂😂. Instant noodles
I have pre-enrolled
I am waiting
Amazing ....Thank you Dr. Andrew
For learning identity
How I read a paper: 1. Upload the entire pdf on ChatGPT and ask it to summarize. This will give you some idea of what the overall paper is. 2. Read the Abstract and Conclusion. I usually skip the Introduction part if I am not new to the field. 3. Glance through the results section (I usually come back to this section later if I find the overall paper interesting). 4. Spend more time on the discussion part. For me, this is the main part of the paper. 5. Carefully read the Future work sections and see if the authors have already worked on these topics since the date of publishing the paper. Having a group is always a good idea. Others might observe something about the paper that you haven't. What I don't do: 1. I do not take notes as I am reading the paper. I only highlight stuff. 2. After reading the whole paper, I try to summarize the overall paper in my own words. This can be used later while you are writing your literature review.
I paid for his course and he is giving it away for free here.. unfair.
The one which you paid for is updated i guess but it doesn't matter, the fundamental knowledge is same everytime everywhere, those who can't afford the Coursera, they can opt this one!
@@ayushmauryaofficial17 Honestly, I can't afford Coursera, even though I have applied for financial aid, but it is still hard for me, then finally I decided to pay for it. And now that I know he gave it away for free, I regret it.
This vids are free on coursera, only practical lessons and tests are paid
I super appreciate you make courses like this and make it avialable for free! This Machine Learning Specialization is up to date as of April 2021, correct?
*your course is very nice but your subtitles that work in course is very very bad please fix it as soon as possible*
Sounds pretty cool! Thank you for making the course available.