This is the series I've been looking for so soooo long..... 😭😭😭 Thank you so much. I've been in Automation space for 5 years now, but struggled to answer interviews when they asked for Prod level stuff that only people working in the industry gets a hands on. This series fills the biggest gap from just learning ML to become PRODUCTION level expert and learn MLOps 😇🥰😍🤩😘
This whole series is the most actionable ML/AI set of tutorials on TH-cam. I wish you had more videos! Thanks making these, Mike. Hope you continue building the channel.
My feeling just after watching only the first video is that I will learn a lot by following the next videos in the play list. You are talking in an exciting and enjoyable way. I love the Bayes formula on the wall, that is the only simple formula that usually takes a bit of time for me to remember and it is my favorite probabilistic formula. Thanks for the making this video specially in your beautiful office.
Hello Mike, Your videos on MLOPS are the best place for anyone who wants to get a great grasp on Vertex AI. I see there is lot of content over internet scattered everywhere and not organized and often distract the User. But, your videos are well structured, hands-on and provide a great depth. I dont see such great content on the Google offered courses too..Thanks a lot...
Hey, Mike! I have just finished this first Intro video and I want to thank you so much for this content! Right now, I'm looking for content to learn more model deployment on Cloud using Google Cloud and I believe I'll find such a rich content here and perhaps the answers that will help me solve the problems I'm facing right now. Thank you so much, and keep it up! The ML Community needs more people like you!
Mike, I'm so grateful to you for these series! I have watched already half of the videos and I can say that you definitely created one of the best free practical ML courses on TH-cam ( and I saw a lot ). Please keep going ! Thank you so much.
Hey Mike, just wanted to encourage you to keep going. We need people to share knowledge. Maybe the feedback does not come immediately after the release of the video, i found it 2 years after publishing, but you are doing a great work, keep doing...
Awesome! I watch a lot of tech on YT, and this is one of the best intros to a playlist I have viewed. I did an M.S. in Statistics in the early 90s, and it amazes me how new specialties like data science and machine learning have just exploded from virtual non-existence since then. These new ideas feel like colossally high-powered pattern-finding and forecasting methods that use non-experimental data. The difference between observational and experimental data is significant (but I see little discussion of this difference in modern explainers of data science and ML). I am trying to fit DS and ML into the framework of statistics that I learned back in the day because, in the end, it is all about data analysis, and it might be helpful to unify these fields that are all about data analysis.
Hi Mike, thank you so much for all the time and effort you put into this! what a master class! I already watched all 12 videos and most likely will have to rewatch them a couple of times to get all the gold nuggets in them. I wondered when/if you plan to generate the videos for the remaining notebooks 5a through 5i. There are so many fascinating topics on the pipeline that I would love to understand better; I am working through the notebook code right now, but it is not the same without the explanations.
Thank You! I am almost ready for the video on 05a through 05i. I have actually been working the past 2 months on building out the 05 Custom Models with TensorFlow series and the GitHub repository has many more tools to accompany these. I need to do another pass through to clean them up and work on a few more tools and then will make videos this Fall! Thank You for the feedback and motivation!
Let's work together to make the practice of AI and ML more collaborative, accurate, and more approachable to a wider and more connected audience. _StatMike!
Hi Mike, I was trying to do Automl forecasting on the same public dataset for bike rentals. And just for one station to kind of get some idea about how much time it takes. its taking very long time. So want to ask what should we consider before running this on entire dataset?
Hello Varsha, AutoML forecasting runtime configuration is basically a time budget based on number of hours to optimize. There is a chart on the following page from the documentation that shows recommended number of hours for various size range for rows and features: cloud.google.com/vertex-ai/docs/tabular-data/forecasting/train-model
![Environment Setup - Vertex AI for ML Operations [notebook 00]](http://i.ytimg.com/vi/pnQ5Rv4ZQfo/mqdefault.jpg)
![Environment Setup - Vertex AI for ML Operations [notebook 00]](/img/tr.png)
This is the series I've been looking for so soooo long..... 😭😭😭
Thank you so much. I've been in Automation space for 5 years now, but struggled to answer interviews when they asked for Prod level stuff that only people working in the industry gets a hands on.
This series fills the biggest gap from just learning ML to become PRODUCTION level expert and learn MLOps 😇🥰😍🤩😘
Mike you gotta give yourself more credit you are a natural teacher and I enjoy the level of depth and visuals you provide
Wow!! Thank you so much for this complement!!
Finally! Someone broke this mess down into manageable chunks. I'm few videos in and I'm already hooked. Thanks so much, Mike, this is really useful!
Happy to help!
This whole series is the most actionable ML/AI set of tutorials on TH-cam. I wish you had more videos! Thanks making these, Mike. Hope you continue building the channel.
My feeling just after watching only the first video is that I will learn a lot by following the next videos in the play list. You are talking in an exciting and enjoyable way. I love the Bayes formula on the wall, that is the only simple formula that usually takes a bit of time for me to remember and it is my favorite probabilistic formula. Thanks for the making this video specially in your beautiful office.
Hello Mike, Your videos on MLOPS are the best place for anyone who wants to get a great grasp on Vertex AI. I see there is lot of content over internet scattered everywhere and not organized and often distract the User. But, your videos are well structured, hands-on and provide a great depth. I dont see such great content on the Google offered courses too..Thanks a lot...
Hey, Mike! I have just finished this first Intro video and I want to thank you so much for this content! Right now, I'm looking for content to learn more model deployment on Cloud using Google Cloud and I believe I'll find such a rich content here and perhaps the answers that will help me solve the problems I'm facing right now.
Thank you so much, and keep it up! The ML Community needs more people like you!
Thank you for providing this great series, Mike! This makes learning GCP so much more interactive compared to just reading static docs.
This makes my day and motivates me to make more!
Super nice intro, I have a feeling, I am gonna love this series!
Mike, I'm so grateful to you for these series! I have watched already half of the videos and I can say that you definitely created one of the best free practical ML courses on TH-cam ( and I saw a lot ). Please keep going ! Thank you so much.
Thank you and I am so glad these are helpful. Many more are on the way!
Hey Mike, just wanted to encourage you to keep going. We need people to share knowledge. Maybe the feedback does not come immediately after the release of the video, i found it 2 years after publishing, but you are doing a great work, keep doing...
Your videos helped me through my dissertation ❤ so detailed , indepth and knowledgeable
Awesome! I watch a lot of tech on YT, and this is one of the best intros to a playlist I have viewed. I did an M.S. in Statistics in the early 90s, and it amazes me how new specialties like data science and machine learning have just exploded from virtual non-existence since then. These new ideas feel like colossally high-powered pattern-finding and forecasting methods that use non-experimental data. The difference between observational and experimental data is significant (but I see little discussion of this difference in modern explainers of data science and ML). I am trying to fit DS and ML into the framework of statistics that I learned back in the day because, in the end, it is all about data analysis, and it might be helpful to unify these fields that are all about data analysis.
TYSM Mike..
Moving one step towards GCP after watch this series.
Respectfully Regards
Vipin
3Blue1Brown gave a master explaining about the Fourier Transform. Highly recommended.
Amazing Mike, thank you very much for the course.
awsome stuff. thanks for the contribution, looking forward to working through the series
Hi Mike, thank you so much for all the time and effort you put into this! what a master class! I already watched all 12 videos and most likely will have to rewatch them a couple of times to get all the gold nuggets in them.
I wondered when/if you plan to generate the videos for the remaining notebooks 5a through 5i. There are so many fascinating topics on the pipeline that I would love to understand better; I am working through the notebook code right now, but it is not the same without the explanations.
Thank You! I am almost ready for the video on 05a through 05i. I have actually been working the past 2 months on building out the 05 Custom Models with TensorFlow series and the GitHub repository has many more tools to accompany these. I need to do another pass through to clean them up and work on a few more tools and then will make videos this Fall! Thank You for the feedback and motivation!
Amazing content, incredibly valuable! Can't believe this is free 🙌💫
Thanks so much for this Mike! I'm super grateful!
Super cool series. There are 12 vodeos in this series. Are there more videos for 06, 07 etc.
Thank you Mike for very detailed explanations
i usually dont comment,But Mike I need more vedios from youuuu!!
This series is great
thank you, you are so professional nice video hello from colombia :D
You are welcome!
Great content, thank you very much!
Hi Mike, do you have video link for Applied Forecasting?
Way to cut through the chaos. I really liked the accompanying GitHub repository.
Thank you for calling this out. I am trying to build what I wish I could find when I am learning a new tool.
Amazing, thanks a lot!
Great tutorials
Excelent Video!
What kind of experince do i need to take on this serious ? I work on IT filed but no experince on mechine learnig or coding ?
Hi Mike, I really liked playlist. please make a video how to reduce the training time in vertex ai.
This is a great idea - so many ideas! If you have anything specific in mind for your scenario let me know in the GitHub under issues!
I love this!
Can you please make video on GCP MLops
Let's work together to make the practice of AI and ML more collaborative, accurate, and more approachable to a wider and more connected audience. _StatMike!
thank you....... very much
Hi Mike, I was trying to do Automl forecasting on the same public dataset for bike rentals. And just for one station to kind of get some idea about how much time it takes. its taking very long time.
So want to ask what should we consider before running this on entire dataset?
Hello Varsha, AutoML forecasting runtime configuration is basically a time budget based on number of hours to optimize. There is a chart on the following page from the documentation that shows recommended number of hours for various size range for rows and features: cloud.google.com/vertex-ai/docs/tabular-data/forecasting/train-model
Mark 9:50. Just for myself to come back to review the available sources
Nice!
Hi Mike, could you make a lab using google managed workbench with a docker container please? . thank you in advance.
This is a great idea for a tools section I am planning. I will add it to the list for after the next round of videos!
If i could give 10 likes to a video, I would give 100 to this one
bro create community discord or WhatsApp or telegram ...........
For now I have setup a Discussion section on the GitHub page for this content. If it grows I might consider a Discord!