Ask Ghassem - Recent activity in Deep Learning

Commented: How to calculate convolutions on a CONV layer for a Convolutional Neural Network?

Sat, 03 Jul 2021 17:34:53 +0000

for part a I am getting below results fo rconcolved features:
R: 0 2 0 , 2 2 0, 3 3 2
G: -1 2 2 , -3 0 4 , 0 0 1
B: -2 -2 0, 1 2 2 , -1 1 3
How do we consider the bias for this section?

how many samples do we need to test image segmentation using synthetic data ?

Mon, 21 Jun 2021 12:26:32 +0000

Hello,

I trained a CNN using synthetic data to perform a segmentation task on human faces. During the test and to evaluate the prediction of this network, I used 200 examples from the database to compute precision and recall.

Is this number sufficient, knowing that I control myself the data generator and that I build the database by randomly drawing the elements using centered Gaussian distributions.

Thank you,

Binary Classification and neutral tag

Sat, 30 Jan 2021 10:08:01 +0000

I am trying to create a sentiment analysis model using binary classification as loss.I have a batch of tweets that some of them are tagged as positive (labeled as 1) and negative (labeled as 0).I manage to gather some tweets that are tagged as neutral but there are less tweets than positive and negative.My thinking is to tag them with 0.5 to balance the classification probability.Is this legit?

"Rare words" on vocabulary

Sat, 30 Jan 2021 09:57:31 +0000

I am trying to create a sentiment analysis model and I have a question.

After I preprocessed my tweets and created my vocabulary I've noticed that I have words that appear less than 5 times in my dataset (Also there are many of them that appear 1 time). Many of them are real words and not gibberish. My thinking is that if I keep those words then they will get wrong "sentimental" weights and gonna make my model worse.
Is my thinking right or am I missing something?

My vocab size is around 40000 words and those that are "rare" are around 10k.Should I "sacrifice" them?

Thanks in advance.

Commented: What loss function to use in CNN-SVM model

Thu, 13 Jun 2019 17:12:21 +0000

Quick question, why should you use SVM and implement the backpropagation? Why do not use the libraries?

Answered: is impossible predict hours time series to minutes time series?

Thu, 02 May 2019 16:47:35 +0000

I guess it is just similar to any other prediction. It can estimate the minute you want based on training data.

Commented: Training neutral net with Tensor Flow

Wed, 14 Nov 2018 17:19:46 +0000

The short answer is using OpenCV library for that purpose. Take a look at this article to know more about it.
https://towardsdatascience.com/analyse-a-soccer-game-using-tensorflow-object-detection-and-opencv-e321c230e8f2

Answered: Using Tensorflow.DNNClassifier, getting Error: assertion failed: [Labels must >= 0]

Thu, 25 Oct 2018 09:21:34 +0000

I think I found the issue. Th issue had two layers:

1- My data is positive integer, it does not need to be scaled! Scaler made some of my data negative! Removing scaler, resolved the error.

Then I got another error, complaining about data type. It is resolved by converting dataframe to np.

Thank you ght!

What are the best resources for studying Deep Learning?

Sun, 26 Aug 2018 07:43:30 +0000

I am wondering if anyone can suggest the best resources for studying Deep Learning?