Introduction to Artificial Neural Networks

Please login to comment

38 Comments

Sasanapuri Meena Kumar

4 years ago

Hi,

I am unable to get the Slide deck. Can you please help

Regards

S Meena Kumar

Upvote Share

Vagdevi K

4 years ago

Sorry, I didn't get your concern. Please elaborate.

Upvote Share

Sasanapuri Meena Kumar

4 years ago

In the chapter "Introduction to Artificial Neural Networks" , the slide deck is not appearing to download. I mean the study material the slides for this course. Vedio is OK. Can u send the slide deck please.

Regards

Meena

Upvote Share

Vagdevi K

4 years ago

Hi,

In the above section of the PPT, click on the icon appearing on top-right corner. You can see the slides opening in a new tab. Now click on the 3 dots on top-right corner, you will see download option. Click on the download option,

Thanks.

Upvote Share

Sasanapuri Meena Kumar

4 years ago

Screen is as below

Upvote Share

Sasanapuri Meena Kumar

4 years ago

Hi Vagdevi

Can u please arrange the slide deck please.

Regards

Meena Kumar

Upvote Share

Vagdevi K

4 years ago

Hi,

I can see that you can access the slides. I checked with your credentials and everything seems perfectly fine. Please attach the screenshot if proble persists.

Thanks.

Upvote Share

Nirav Raj

4 years ago

I did not understand the backward prapogation.

Please tell how it back prapogates and how it predict the values

Please tell the whole mechanism of backward prapogation

Upvote Share

Rajtilak Bhattacharjee

4 years ago

Hi,

Here's a good article on backprop:

https://cloudxlab.com/blog/tag/backpropagtion/

Thanks.

Upvote Share

Nirav Raj

4 years ago

I did not understand at 2:33:59

DNN

How are you calculating

5 +15+..??

Please tell the mechanism

Upvote Share

Rajtilak Bhattacharjee

4 years ago

Hi,

Here we have 3 layers, input (1), hidden (1), and output (1). We are multiplying each of the inputs of the hidden and the output layers with these weights.

Thanks.

Upvote Share

Nirav Raj

4 years ago

I did not understand at 2:22:23

X1 =1

1 *1

How are you multiplying??

Where you multiplying this??

Please give me full explaination.

Upvote Share

Rajtilak Bhattacharjee

4 years ago

Hi,

Here we are multiplying weights with the features.

Thanks.

Upvote Share

Nirav Raj

4 years ago

y=(iris.target==0).astype(np.int)

What we are doing here??

How this machanism works??

Upvote Share

Rajtilak Bhattacharjee

4 years ago

Hi,

In this dataset we can predict 3 classes. The target variable is thus represented as 0, 1, and 2 for each class. Here we are predicting only the first of these 3 classes, which is the Iris Setosa class. So we are taking only those y where y is equal to the 0 class.

Thanks.

Upvote Share

Nirav Raj

4 years ago

I did not understand.

How are you taking petal length and petal width??

Please say

Upvote Share

Rajtilak Bhattacharjee

4 years ago

Hi,

The following line selects the columns for petal length and petal width:

X = iris.data[:, (2, 3)]

Thanks.

Upvote Share

Soham Hajra

4 years ago

Hi Team,

I see lot many comments regarding login to Tensorboard. The latest instructions of oprning Tensorboard is not working for most of the students because the provided path is not correct. Before putting the command - "tensorboard --logdir deep_learning/tflogs --port 4066" one has to change the directory to 'ml' (using cd ml). This is not indicated in the instruction. Another problem is the current instruction shows that the path is '/tflogs' but the logs are getting saved in the folder named 'tf_logs' so the correct command list will be -

export PATH=/usr/local/anaconda/bin:$PATH
source activate root

cd ml
tensorboard --logdir deep_learning/tf_logs --port 4066

I am requesting your team to update the commands properly to avoid any confusion in future.

1 Upvote Share

Abhinav Singh

4 years ago

Hi Soham,

We have already updated the instructions here https://discuss.cloudxlab.com/t/solved-cannot-start-tensorboard-server/5146

The working directory may change depending on your code.

Am I missing anything here? If yes, then please let me know and I'll ask one of the team members to update the instructions.

Upvote Share

Manjari Singh

5 years ago

which session, before this, did you take session on tensor flow?

Upvote Share

Rajtilak Bhattacharjee

5 years ago

Hi,

Could you please tell me a bit more about your issue?

Thanks.

Upvote Share

durvesh javle

5 years ago

Hi , in the topic of perceptron how this line converts from 3 class to 2 class

y = (iris.target == 0).astype(np.int)

Upvote Share

Rajtilak Bhattacharjee

5 years ago

Hi,

This line checks only for Iris Setosa. You can check slide 36 for this, also you can print y right after this line to check what it refers to.

Thanks,

Upvote Share

Srikanth Gedela

5 years ago

Unable to start TensorBoard
please help

Upvote Share

Srikanth Gedela

5 years ago

tf_logs has the following error:

Upvote Share

CloudxLab

5 years ago

Hi,

Would request you to follow the steps from the below link and then try once again:
https://discuss.cloudxlab.c...
Please let us know if this does not work.

Thanks.

-- Rajtilak Bhattacharjee

Upvote Share

CloudxLab

5 years ago

Hi,

Are you still facing this issue? If yes, then please follow the below steps for resolving the issue:
https://discuss.cloudxlab.c...
Thanks.

-- Rajtilak Bhattacharjee

Upvote Share

Mahesh Urkude

5 years ago

Unable to run TensorBoard. See the steps I followed in the screenshot :

Steps followed...
export PATH=/usr/local/anaconda/bin:$PATH
source activate root
(source activate py36 gave n error ...
Could not find conda environment: py36
You can list all discoverable environments with `conda info --envs`)
FIND PYTHON version: python --version
Version is 3.8.6

tensorboard --logdir ~/ml/deep_learning/tf_logs/ --port 6006
Following message shows on screen...
TensorBoard 1.14.0 at http://cxln5:6006/ (Press CTRL+C to quit)

On a CHROME browser, used the following URL…
http://f.cloudxlab.com:6006/
Tried with few other ports 9,10,11,13 but no luck.

Upvote Share

CloudxLab

5 years ago

Hi,

Would request you to follow the steps from the below link and then try once again:
https://discuss.cloudxlab.c...
Please let us know if this does not work.

Thanks.

-- Rajtilak Bhattacharjee

Upvote Share

Mahesh Urkude

5 years ago

Guys, I'm asking if there is an issue with the steps I have followed. I put up an issue only after a lot of trying n waiting as I know there might be server issues. So please guide.

Upvote Share

CloudxLab

5 years ago

export PATH=/usr/local/anaconda/bin:$PATH
source activate root
tensorboard --logdir deep_learning/tflogs --port 4066
*Please remember that the port number has to be between 4040 and 4140.* If you get an error saying "Tensorboard could not bind to port 4066, it was already in use", simply use another port number within this range. If you have performed these steps successfully, you would get a prompt on your screen which would look something like the following:

-- Praveen Pavithran

Upvote Share

Mahesh Urkude

5 years ago

No it didnot work

Upvote Share

CloudxLab

5 years ago

Hi,

Are you still facing this issue? If yes, then please follow the below steps for resolving the issue:
https://discuss.cloudxlab.c...
Thanks.

-- Rajtilak Bhattacharjee

Upvote Share