Text Classification Using BERT & Tensorflow | Deep Learning Tutorial 47 (Tensorflow, Keras & Python)

Using BERT and Tensorflow 2.0, we will write simple code to classify emails as spam or not spam. BERT will be used to generate sentence encoding for all emails and after that we will use a simple neural network with one drop out layer and one output layer.

#️⃣ Social Media #️⃣

❗❗ DISCLAIMER: All opinions expressed in this video are of my own and not that of my employers'.

[chrisanderson]

This is excellent. The explanations are concise and the spoken words are easy to understand.

[pierocruz]

You're the best man, what I have been trying to learn for months, I just feel like i understand a little more with your video.
Thanks!

[studiousamateur]

I have started watching this DL series today... It is helping me a lot. Thanks for all your efforts.

[rt_shll]

This was amazing, if you can do more deep learning videos that would be great. Really well done.

[RezaNeiriz]

This is a really good video. You mention a lot of useful information in passing, making your video really useful. I really liked the way you talked about sequential and functional models. Thank you!

[alikara]

Consise, simple and easy to grasp! Your videos are very helpfull. Thank you

[dhairyashah]

I love this series a lot and would like to see a video of the implementation of same dataset with the help of hugging face. As hugging face can implement many transformers model

[preetinagarkar]

Much needed… I learned lots of stuff. Thank you so much 😊 🙏🏻

[maYYidtS]

Genius....greate lecture...I have been following you from a long back...
One request from my side...please do end to end.
you have explained it very well..
and
1. Create an evaluation script
2. Deploy it Aws
3. Show end results
as like real time how companies are doing...so that me and beginners will get to know exact procedure & life cycle...
you have already created videos on deployment..but please do this model in aws...thanks

Bert is the code word of joey and Chandler for danger 😂😂

[dushyyanta]

Thank you for such nice and easy explanations :)

[mahdiamrollahi]

Great....
Following the imbalanced dataset, I think we should have consider other metrics like precision, recall or ...

[Segmentsoflives]

Your accent , efforts and presentation on these complex topic to make things simpler is really wonderful compared to others. really grateful to you and waiting for more contents on tensorflow basics and real time projects. one more complete walk through on tensorflow.org documentation and where they are used can create one more quality content to your list . Thank you !

[HowYThink]

Nice, you covered everything I needed from BERT side, But you didn't take care of the imbalanced dataset, you have created a model that always predicts the same class.

[aditya_]

THANK U VERY MUCH SIR BEST VIDEO FOR BEGINNERS .THANK U VERY MUCH SIR

[dec]

Hello there! 😀

I have watched your Tensorflow tutorial since the beginning, it's really helpful to learn new stuff!

In very general terms, how would be BERT used, to identify some "custom keywords" (I'm trying to identify software names and skills, which I have already scrapped) in a text.

It would be interesting to see a third BERT video, with some similar topic 😀.

Best regards and keep it up with the good work!

[abhaygodbole]

Very informative video. Dhaval your explanation is really simple. I am going through this series and enjoying it... I have one question not related to TF or DL...
do you have any tutorial on predictive maintenance like for example predicting remaining useful life of Valves.
Please share the link or redirect me to resources which has solution approach Data sets etc.
Thanks

[vkrts]

Excellent!
Can we use BERT offline?

[rizwana]

Sir u r videos are awesome can u please make a video on text and image summarization that takes input as text and image and gives output summarized text and related image.

[annperera]

Sir please please do a video on Bayesian Networks.I told many of my friends sirs channel and they subscribe you also