I believe the example code for the wide model given at 29:48 is wrong. The model should be created like this: wide_model = Model(inputs=[bow_inputs, variety_inputs], outputs=predictions)
Couple times I did not understand material I understood some of the detail I didn’t want their overall I think I better go back to asking what a blog is 🤙🏻🤗👂🏼🙏🏼Lol
How do you create ML for sifting through pubmed and analyzing medicine affects on specific genetic disorders? I know it would need 2 libraries, but how can one get it to connect missing dots overlooked by humans?
Great video, especially on AutoML : Is human labeling performed by real humans ? How do they know how to label, if not experts in the reviewed domain ? Is it possible to restrict the origin of API calls ? (Use case : don't want my competitors to use my prediction API) ? Is it possible to make predictions offline (something like compile model, then use it in JS in the browser) ?
@Denis Yes, the labeling will be performed using real humans and they will label the data based on the customer's instructions. Next, one can easily restrict/lock API calls to a particular domain for a given model's API endpoint. Finally, if you're using TensorFlow/Keras APIs, one can easily train, test, and deploy a model offline which can be consumed by a local Javascript client application. Please do see ua-cam.com/video/OmofOvMApTU/v-deo.html
this video doesn't make me want to use GCP for ML anytime soon. Most if not all what she talked about can be achieved quite easily in Jupyter notebook with opensource software (fast.ai etc)
Hi I'm Ariful Islam leeton im software engineer and members of the international organization who and members of the international telecommunications and development Google
It is surprising. This is an experienced presenter who knows her subject. I've noticed a lot of empty seats in many of the I/O '18 videos. Was everybody outside schmoozing in the hallways?
Excellent intro to ML on GCP, really appreciated the example scenarios for AutoML & TensorFlow.
Fascinating the way she explained google products ! Thank you Sara
Great intro... now ML is within eveyone's reach
I believe the example code for the wide model given at 29:48 is wrong. The model should be created like this:
wide_model = Model(inputs=[bow_inputs, variety_inputs], outputs=predictions)
Couple times I did not understand material I understood some of the detail I didn’t want their overall I think I better go back to asking what a blog is 🤙🏻🤗👂🏼🙏🏼Lol
How do you create ML for sifting through pubmed and analyzing medicine affects on specific genetic disorders? I know it would need 2 libraries, but how can one get it to connect missing dots overlooked by humans?
A thousand thumb ups! Answered so many questions! Thank you!
Great video, especially on AutoML :
Is human labeling performed by real humans ? How do they know how to label, if not experts in the reviewed domain ?
Is it possible to restrict the origin of API calls ? (Use case : don't want my competitors to use my prediction API) ?
Is it possible to make predictions offline (something like compile model, then use it in JS in the browser) ?
@Denis Yes, the labeling will be performed using real humans and they will label the data based on the customer's instructions. Next, one can easily restrict/lock API calls to a particular domain for a given model's API endpoint. Finally, if you're using TensorFlow/Keras APIs, one can easily train, test, and deploy a model offline which can be consumed by a local Javascript client application. Please do see ua-cam.com/video/OmofOvMApTU/v-deo.html
this video doesn't make me want to use GCP for ML anytime soon. Most if not all what she talked about can be achieved quite easily in Jupyter notebook with opensource software (fast.ai etc)
You are probably not the target demographic
where is the Cloud ML tutorial? Where do I start to learn?
Thanks Sara... so clear!!!
What types of machine learning algorithms are used for image recognition?
Convolutional Neural Networks
When will AutoML be released to the public?
That’s OK you can laugh at grandma lol 😆🤷🏼♀️🤔
I love watching Sara
Hi I'm Ariful Islam leeton im software engineer and members of the international organization who and members of the international telecommunications and development Google
Wow, why is the audience so empty?
It is surprising. This is an experienced presenter who knows her subject. I've noticed a lot of empty seats in many of the I/O '18 videos. Was everybody outside schmoozing in the hallways?
Because we have utube
Maybe it's just intended for a UA-cam audience.
Excellent
I apologize I don’t know why my speech sometimes is written now and other times it doesn’t compute I apologize for my speech texting
great...can i get the code pls?
🤙🏻👂🏼I’m learning if you didn’t learn one thing a day it was a wasted day no
i dont understand anything else
Whoever is the instructor, she speaks in 1.2x speed. Too much content. Less Details
I can't agree with you more.
ML problem 🤦🏻♂️ Ohhh God
Excellent