Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [ann]

20 questions
2
votes
1 answer

Why the test accuracy showing some odd behaviour in comparison to train accuracy?

I am currently training an ANN using Sequential(a class from Keras API within tensorflow), and I am optimizing the model's architecture and came across something I have not seen before. The graph of the test accuracy seems a bit odd. The graph…
Aach_copro
  • 23
  • 4
1
vote
1 answer

Understanding outputs from ANN and how to improve validation loss

I apologise if this is a bit long winded, but it was suggested by another user that I post. I will start by saying that I am very new to the world of machine learning and deep learning. As such, the most important thing I am after is the…
DDV
  • 125
  • 4
1
vote
1 answer

MLP sequential fitting

I am fitting a Keras model, using SGD Input dataset X_train has 55000 entries. Can anyone explain the yellow highlighted values? For me, when each epoch is done, this should correspond to 55000/55000. model =…
sidhom slim
  • 13
  • 3
1
vote
2 answers

How can ANN handle varied sized inputs?

I have a dataset with a message (string) and an associated mood. I am trying to use an ANN to predict one of the 6 moods using the encoded inputs. This is how my X_train looks like: array([list([1, 60, 2]), list([1, 6278, 14, 9137, 334, 9137,…
ChaoS Adm
  • 141
  • 3
1
vote
1 answer

How to properly train your Self-Organized Map?

I recently stumbled upon the Self-Organized Map - an ANN architecture used to cluster high dimensional data - while simultaneously imposing a neighborhood structure on it. It is trained through a competitive learning approach where neurons compete…
Steve
  • 41
  • 3
1
vote
1 answer

ANN Classifier for extracted discrete image features

I have a features extraction algorithm that works well to extract features from images. I want to develop an ANN to classify those images based on those features. I have extracted features in a csv file as columns and rows. I know we can use CNN to…
DevLoverUmar
  • 121
  • 7
1
vote
0 answers

ANN return many result differents

I made an application that uses neural networks, its function is to classify the type of user that is, it can be legitimate or intrusive, the data was saved in the database, when I give it in the classify button it returns several results that vary…
information
  • 141
  • 5
1
vote
1 answer

Combining standardizing and normalizing my input data for ML gives the best results, why?

When I combine standardizing and normalizing my input data for my hybrid ANN model, it gives the best results. But I can't find anywhere, why. I based it on a paper's approach but they don't justify their practice either. Anyone knows…
Mia May
  • 11
  • 2
1
vote
1 answer

Does derivative of an activation function refer to process of back-propogation in ANN?

I am confused that in ANN, we use Gradient Descent to find the curve of the optimal points of predicted values. Let's say we use MSE (Mean Squared Error) and the lost function is 1/2m * (y-y')^2 And the cost function is sum of lost function…
Mystheman
  • 13
  • 3
1
vote
1 answer

How to Improve MLP ANN accuracy

I am trying to improve the accuracy of my model over the UCI Breast Cancer Dataset. There's 426 records, and it is a binary classification model. X_train.shape (426, 30) X_test.shape (143, 30) y_train.shape (426, 1) y_test.shape (143, 1) I have…
No_Name
  • 11
  • 1
1
vote
1 answer

Understand the reason of embedding and the size inside it in Pytorch

I'm very new to pytorch - taking a course in udemy. There is something I find hard to understand and would like to get explaination about, in a bit simpler words than what I can find in the documentation. one of the lessons is about solving…
Reut
  • 299
  • 3
  • 15
1
vote
0 answers

Near duplicate detection algorithms for a near real time system

I'm looking for near-duplicate detection algorithms or techniques for a near-real-time system with large document volumes. I know LSH is the most popular industry-standard algorithm for syntactical use cases but I'm trying to find better…
Murali Mopuru
  • 61
  • 3
1
vote
0 answers

Some models are over fitting and some are under fitting, please help me where I am doing wrong

I am getting 100% accuracy for the below models. can you please advise me where I am doing wrong? If it is due to overfitting then why other models like below do not over-fit the model. Attached same code for random forest from sklearn.ensemble…
Deep
  • 11
  • 3
1
vote
1 answer

Combine multiple vector fields for approximate nearest neighbor search

I have multiple vector fields in one collection. My use-case is to find similar sentences in similar contexts. The sentences and contexts are encoded to float vectors. Therefore, I have one vector for the sentence and another vector for the context…
roemchine
  • 11
  • 1
0
votes
1 answer

In neural networks model, which number of hidden units to select?

In the neural networks model, how many numbers of hidden units need to keep to get an optimal result, as per Cybenko theorem which demonstrates that only one hidden layer is sufficient to solve any regression/classification problem but the selection…
coding_ninza
  • 139
  • 1
  • 2
  • 8
1
2