This course is a practical introduction to natural language processing with TensorFlow 2.0. In this tutorial you will go from having zero knowledge to writing an artificial intelligence that can compose Shakespearean prose.
No prior experience with deep learning is required, though it is always helpful to have more background information. We’ll use a combination of embedding layers, recurrent neural networks, and fully connected layers to perform the classification.
⭐️Course Contents ⭐️
⌨️ (01:16) Getting Started with Word Embeddings
⌨️ (33:25) How to Perform Sentiment Analysis on Movie Reviews
⌨️ (59:32) Let’s Write An AI That Writes Shakespeare
⭐️Course Description ⭐️
The basic idea behind natural language processing is that we start out with words, i.e. strings of characters, that are almost impossible for the computer to meaningfully parse. We can transform these strings into a vector in a higher dimensional space. Different words will be represented as vectors of different lengths and directions in this space, and this allows us to find relationships between words by finding the component of one vector along another. Don’t worry, the TensorFlow library handles all of this, we just have to have some basic idea of how it works.
Since this is a type of supervised learning, we also have labels for our text. This allows the AI to compare the relationships between words to the training labels, and learn which sequences of words represent good and bad movie reviews. This would also work for finding toxic comments, fake product reviews… just about anything for which we need a multiclass classification of text – provided we have enough training data and labels.
The last step in complexity is to change the final layer that handles the classification. This allows us to actually output text that the AI thinks is meaningful. What’s really special about this is that the neural network starts out not even knowing that letters are a thing, or that we use spaces and punctuation, to producing something that approximates human level writing.
⭐️Code ⭐️
🔗Word Embeddings:
🔗Text Classification:
🔗Text Generation:
⭐️Resources ⭐️
As stated in the videos, these are from the official TensorFlow tutorials. You can find them here:
🔗
🔗
🔗
This course was created by Phil Tabor. If you’d like to see more deep learning, reinforcement learning, and artificial intelligence content, please check out his channel:
—
Learn to code for free and get a developer job:
Read hundreds of articles on programming:
And subscribe for new videos on technology every day:
Filed under: Web Design
13 seconds agi
First comment
I can’t believe I’ve learned so much from this channel. Love from Pakistan.
Questions, comments? Leave a comment below! For more deep learning content check out my channel. Thanks for watching!
Amazing course! Straight to the point and not too hand-wavy. I am an ML researcher in vision but had no clue about NLP. Was a real pleasure to watch a concise introduction!
@Undisclosed Music Glad you enjoyed it!
Glad to see you on freecodecamp
I am the one who must say thanks.
I learnt python with this channel, and now I’m creating my own course on a free platform (Stepik), To Give back to the Community ❤
Nice to hear that. I am also learning. What courses helped you the most?
@Ikechukwu ezeokwelume That Python for beginners by Mike helped me the most, it was one of the finest course
Thanks. I will check it out.
Happy you grabbed the Python skills. Try and start applying the knowledge asap so you won’t forget it.
@Ikechukwu ezeokwelume thanks and same to you😊
I am looking for an algorithm to answer reviewers 🤔
I guess u gotta build one by your own
@Danish Sharma I am looking for a self learning program, which can build itself
@Alex we can collab if you interested in building model from scratch
@Danish Sharma the problem is a training database
I’ve got warning with 2.0 but they are not funny😂
I want to run this project. Where can I find the datasets ? For doing this hands-on ?
Just added links to code in the description. Here they are:
⭐️Code ⭐️
🔗Word Embeddings: https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/text/word_embeddings.ipynb
🔗Text Classification: https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/text/text_classification_rnn.ipynb
🔗Text Generation: https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/text/text_generation.ipynb
Where is the GitHub for this project?
We’re using Google Colab this time instead of GitHub. There are links to the different codebases in the description.
Bruh they straight up copped the Fleet Farm logo
I have started a python programming ch named infinite programming …. Can you pliz see the channel and give me some suggestions and pliz give me blessings
Btw awesome video
look at these GPUs…
I got my first job as a software engineer thanks to freeCodeCamp. I cannot thank you guys enough. I will definitely donate soon
Are you self-taught , Where do you get the job? In Bangalore. ? If you don’t mind me asking can you tell your salary package .
@skt gaming Yeah mostly self taught. I knew a little bit of C before I started learning JS, HTML, CSS on FCC. Yes in Bangalore. I applied on angel list
@Shreyas Gopal is Angel list is good for job searching? I have been searching on indeed. Did you get the good salary package or not bc most of the companies looking for 2-4 yrs experience in Bangalore which is crazy bdw. Did you apply as a fresher ?
@skt gaming For startups, angel list is really good. For a fresher, salary package is decent
@Shreyas Gopal thank you. I didn’t know about Angel list . I will check 👍
God I am blessed to have known about freecodecamp. Thank you so much guys for all the effort you put in to provide us top quality content for free.
Basically recreate everything siraj did… but correctly. Boom! Million followers 😂
That’s the hope 🙂
You’re not really explaining what you’re doing as you’re going… Which is a shame. Appreciate there’s a lot of documentation to refer to, but ‘beginners course’ is a bit of a misnomer
I really wish freeCodeCamp would bring back the Shirts and Hoodies in their store!
For vim you should have a look at the coc.nvim plugin with the coc-python extension. It’ll prevent you missing syntax errors before running the file.
Hello, have you explored how to build a custom encoder decoder architecture with tf2? For example machine translation, but to be able to run with variable length sequences, not just pad to maximum overall length.
I am new to Python…And know all basic of Python…Is this video worth ??? Viewer please answer me