Thanks for your question.

I would recommend starting with Linear Regression since that will introduce the concepts more intuitively. Please see the Appendix lecture "What order should I take your courses in?" for more info.

## Search found 15 matches

- Wed Feb 05, 2020 11:06 pm
- Forum: General Discussion
- Topic: beginning of linear classification
- Replies:
**1** - Views:
**271**

- Thu Dec 19, 2019 7:35 am
- Forum: General Discussion
- Topic: Evaluating images collectively
- Replies:
**1** - Views:
**229**

### Re: Evaluating images collectively

Thanks for your question. You would be interested in the ROC and AUC. I believe you are taking the courses where this was discussed (Logistic Regression, Deep Learning part 1) so take a look there. In practice, multiple tests are done. E.g. an initial blood test, then follow up tests if the first te...

- Thu Sep 26, 2019 9:15 pm
- Forum: Deep Learning Prerequisites: The Numpy Stack in Python
- Topic: Seekibg Solution for user input translator machine.
- Replies:
**1** - Views:
**552**

### Re: Seekibg Solution for user input translator machine.

Thanks for your question!

The model should accept any text as input (provided you use the correct functions to convert it into a sequence of word indices).

The model should accept any text as input (provided you use the correct functions to convert it into a sequence of word indices).

- Tue Jul 02, 2019 5:50 pm
- Forum: General Discussion
- Topic: TensorFlow 2.0
- Replies:
**2** - Views:
**863**

### Re: TensorFlow 2.0

Yes, but actually it's very easy. "Just use Keras" is the new paradigm. So the courses that use Keras such as Advanced Computer Vision, Advanced NLP, and Recommender Systems are already covered. The only difference is instead of "keras" it'll be "tf.keras". ANNs and CNNs are nearly trivial. RNNs are...

- Tue Jun 04, 2019 6:47 pm
- Forum: Deep Learning: Convolutional Neural Networks in Python
- Topic: Use of SVHN/train_32x32.mat database
- Replies:
**1** - Views:
**573**

### Re: Use of SVHN/train_32x32.mat database

Thanks for your question!

That's actually fine because the CNN is learning where to look.

For example, a CNN that may recognize a dog in an imagine that also contains a tree.

That's actually fine because the CNN is learning where to look.

For example, a CNN that may recognize a dog in an imagine that also contains a tree.

- Tue Jun 04, 2019 6:41 pm
- Forum: Deep Learning Prerequisites: Linear Regression in Python
- Topic: numpy code in lesson 7
- Replies:
**1** - Views:
**577**

### Re: numpy code in lesson 7

Check out the subsequent quiz

- Sat May 11, 2019 12:40 am
- Forum: General Discussion
- Topic: Cutting-Edge AI: Deep Reinforcement Learning in Python, on Udemy?
- Replies:
**1** - Views:
**558**

### Re: Cutting-Edge AI: Deep Reinforcement Learning in Python, on Udemy?

Thanks for your question!

It will be on Udemy sometime in the near future, but without any VIP material (as per usual).

It will be on Udemy sometime in the near future, but without any VIP material (as per usual).

- Thu Jan 24, 2019 5:56 am
- Forum: Deep Learning Prerequisites: Linear Regression in Python
- Topic: Linear regression, L2 regularization
- Replies:
**11** - Views:
**2274**

### Re: Linear regression, L2 regularization

- the video on coding the L2 technique does not go through any normalization of the data. I thought this was needed Generally you use it when needed. E.g. do it if it leads to better results. - do you only normalize the X of each feature or do you also normalize the Y Both ways are typical. - any r...

- Mon Jan 21, 2019 6:51 pm
- Forum: Deep Learning Prerequisites: Linear Regression in Python
- Topic: Linear regression, L2 regularization
- Replies:
**11** - Views:
**2274**

- Sun Jan 20, 2019 8:02 pm
- Forum: Deep Learning Prerequisites: Linear Regression in Python
- Topic: Linear regression, L2 regularization
- Replies:
**11** - Views:
**2274**

### Re: Linear regression, L2 regularization

Thanks for your questions! 1) I interpret this as penalizing the answer in a way to reduce the weight of the linear regression. Is my understanding correct? Not really. You are penalizing large weights. 2) But what if the outlier points have y values lower than what the “good data set” suggests. Pen...