Learn TensorFlow and Deep Learning fundamentals with Python (code-first introduction) Part 1/2

Ready to learn the fundamentals of TensorFlow and deep learning with Python? Well, you’ve come to the right place.

After this two-part code-first introduction, you’ll have written 100s of lines of TensorFlow code and have hands-on experience with two important problems in machine learning: regression (predicting a number) and classification (predicting if something is one thing or another).

Open a Google Colab (if you’re not sure what this is, you’ll find out soon) window and get ready to code along.

Connect elsewhere:

Timestamps:
0:00 - Intro/hello/how to approach this video
1:50 - MODULE 0 START (TensorFlow/deep learning fundamentals)
1:53 - [Keynote] 1. What is deep learning?
6:31 - [Keynote] 2. Why use deep learning?
16:10 - [Keynote] 3. What are neural networks?
26:33 - [Keynote] 4. What is deep learning actually used for?
35:10 - [Keynote] 5. What is and why use TensorFlow?
43:05 - [Keynote] 6. What is a tensor?
46:40 - [Keynote] 7. What we're going to cover
51:12 - [Keynote] 8. How to approach this course
56:45 - 9. Creating our first tensors with TensorFlow
1:15:32 - 10. Creating tensors with tf Variable
1:22:40 - 11. Creating random tensors
1:32:20 - 12. Shuffling the order of tensors
1:42:00 - 13. Creating tensors from NumPy arrays
1:53:57 - 14. Getting information from our tensors
2:05:52 - 15. Indexing and expanding tensors
2:18:27 - 16. Manipulating tensors with basic operations
2:24:00 - 17. Matrix multiplication part 1
2:35:55 - 18. Matrix multiplication part 2
2:49:25 - 19. Matrix multiplication part 3
2:59:27 - 20. Changing the datatype of tensors
3:06:24 - 21. Aggregating tensors
3:16:14 - 22. Tensor troubleshooting
3:22:27 - 23. Find the positional min and max of a tensor
3:31:56 - 24. Squeezing a tensor
3:34:57 - 25. One-hot encoding tensors
3:40:44 - 26. Trying out more tensor math operations
3:45:31 - 27. Using TensorFlow with NumPy
3:51:14 - MODULE 1 START (neural network regression)
3:51:25 - [Keynote] 28. Intro to neural network regression with TensorFlow
3:58:57 - [Keynote] 29. Inputs and outputs of a regression model
4:07:55 - [Keynote] 30. Architecture of a neural network regression model
4:15:51 - 31. Creating sample regression data
4:28:39 - 32. Steps in modelling with TensorFlow
4:48:53 - 33. Steps in improving a model part 1
4:54:56 - 34. Steps in improving a model part 2
5:04:22 - 35. Steps in improving a model part 3
5:16:55 - 36. Evaluating a model part 1 ("visualize, visualize, visualize")
5:24:20 - 37. Evaluating a model part 2 (the 3 datasets)
5:35:22 - 38. Evaluating a model part 3 (model summary)
5:52:39 - 39. Evaluating a model part 4 (visualizing layers)
5:59:56 - 40. Evaluating a model part 5 (visualizing predictions)
6:09:11 - 41. Evaluating a model part 6 (regression evaluation metrics)
6:17:19 - 42. Evaluating a regression model part 7 (MAE)
6:23:10 - 43. Evaluating a regression model part 8 (MSE)
6:26:29 - 44. Modelling experiments part 1 (start with a simple model)
6:40:19 - 45. Modelling experiments part 2 (increasing complexity)
6:51:49 - 46. Comparing and tracking experiments
7:02:08 - 47. Saving a model
7:11:32 - 48. Loading a saved model
7:21:49 - 49. Saving and downloading files from Google Colab
7:28:07 - 50. Putting together what we've learned 1 (preparing a dataset)
7:41:38 - 51. Putting together what we've learned 2 (building a regression model)
7:55:01 - 52. Putting together what we've learned 3 (improving our regression model)
8:10:45 - [Code] 53. Preprocessing data 1 (concepts)
8:20:21 - [Code] 54. Preprocessing data 2 (normalizing data)
8:31:17 - [Code] 55. Preprocessing data 3 (fitting a model on normalized data)
8:38:57 - MODULE 2 START (neural network classification)
8:39:07 - [Keynote] 56. Introduction to neural network classification with TensorFlow
8:47:31 - [Keynote] 57. Classification inputs and outputs
8:54:08 - [Keynote] 58. Classification input and output tensor shapes
9:00:31 - [Keynote] 59. Typical architecture of a classification model
9:10:08 - 60. Creating and viewing classification data to model
9:21:39 - 61. Checking the input and output shapes of our classification data
9:26:17 - 62. Building a not very good classification model
9:38:28 - 63. Trying to improve our not very good classification model
9:47:42 - 64. Creating a function to visualize our model's not so good predictions
10:02:50 - 65. Making our poor classification model work for a regression dataset

#tensorflow #deeplearning #machinelearning

[mrdbourke]

Friends, here are some helpful links:


Happy Machine Learning!

[TeddyWarMan]

this style of teaching is so effective for people like me who have ADHD, thank you so much you absolute ledgend

[FarisSkt]

I cant thank you enough for all the efforts you do to teach ML. You can’t find quality content like this anywhere else, for free.

[pinehteshapple]

NOTE: If you are getting a TypeError at 4:39:49 while fitting the model you will need to add tf.expand_dims()
I don't know why but it worked for me.
example: model.fit(tf.expand_dims(x, axis=-1), y, epochs=5)

Edit: I did some studying the reason this error was there because the training data and evaluation data are not of the same dimensions and/or number similar to when tried to dot product the matrices.

[Mark-nmsm]

Im 5:47:41 hours deep, I have been wanting to say this from early on but I wanted to make sure I am not too fast to talk.
You are an excellent teacher, regardless of the topic you are teaching in this video, the way you teach is exactly the way it should be done. You arouse our critical thinking and you get us to make questions.
You might not be here in this room with me but i feel more energy from you than from my university teachers in person💯💯💯

[leonardopetribu]

*A playlist with 60 videos of 10 min each*
Me: meeeh, not today...

*A single video with a 10 hours marathon*
Also me: LET'S GO FOR IT!!

[eidmone]

Deep Learning is basically that one kid in middle school who "don't follow the rules, but make the rules."

[b.k.]

No has ever taught ML/DL better....seriously, this is my 4th attempt at ML and I think I might just get it this time! The teaching structure is absolutely beautiful. I am at 5:20:45 and I WILL comment when I get to the end.

[niteshkumar]

Friends I have been following this video for last 5 days to complete the code with practice simultaneously

[gautam.pamnani]

I am Computer Science student, this semester we were properly introduced to ML as a subject. I was searching for a tf courseware on NN & the moment I saw this video, I was hooked ! It's been 7 hrs now (used my entire weekend), coded along, learnt so much along the way - right from the basic algebra (vectors, scalars, tensors, matrices...) all the way through ML and NN. I'll complete this as well as part 2 before another weekend ! LEARNING HAS BEEN SO MUCH FUN & INTERESTING BECAUSE OF YOU, SIR 'D. BOURKE'. Thanks a lot for such awesome content, your hard work shines throughout the course curriculum. I recommend everyone to justify his hard work by completing the entire tutorial along with Programming.

[yasthirdhewnarian]

This video is extremely underrated my man. Amazing job! Please keep on making more videos. You are a terrific teacher

[rajatkmitra]

Daniel, if your were around when I was a student at my university and I happened to have you as a teacher.... well.... This is an amazing set of lectures! YOU my friend are well on your way to creating the next generation of world class scientists!! Keep up the great work!!!

[Vasko]

The fact that you have ZERO dislikes tells you that this is PURE GOLD. I think that these videos and the whole course should be recommended by the Tensorflow official team for learning TensorFlow.

Keep up the good work!

[mazerat]

For those who had a ValueError right from the getgo
There is one extra line that he didn't have to add with his version of TensorFlow

model = tf.keras.Sequential([
tf.keras.layers.Input(shape=(1, )), ###This extra line
tf.keras.layers.Dense(1)
])

model.compile(loss=tf.keras.losses.mae,
optimizer=tf.keras.optimizers.SGD(),
metrics=["mae"])

model.fit(X, Y, epochs=5)

[victoriawaldorf]

Daniel, thank you so much for your course! After completing this tutorial, I easily got a job offer because Im able to describe all deep learning concepts in details!

[dineshpatell]

I was searching ML and NN and found this channel and its continuous 5 hours and I learned a lot of things without getting bored. Its best on YouTube SIR DANIEL . Thank you so much for providing such a worthy of course free of cost.

[Asif-jdkm]

Seven months later I find your video from YouTube recommendations so helpful and easier to understand I’m a self thought programmer so I can’t understand what others YouTube video’s saying and confused and drop the topic and didn’t look at them, but your video is so understand and very details,
One sub from me:)

[shivambakshi]

Even better then paid courses ! Thank you Daniel for such amazing stuff.

[ComputerScienceWithBas]

After going through so many complicated and advanced tutorials (PS :- Didn't understand all the stuff there, this video literally made every concept clear). HATS OFF to such great creators like you sir !. Thank you so very much. Please make more advanced long tutorials so that we can become experts as well. Thank you !

[xdx]

I am aged 50+ and learning tensorflow now as a Process Excellence and LSS Expert! Hope this will help!