Questions tagged [binary-classification]

For questions about binary classification problems, i.e. problems where we want to classify inputs into 1 of 2 classes.

Filter by
Sorted by
Tagged with
1
vote
1answer
18 views

Why are CNN binary classifier output probability distributions often skewed?

I've been working on a lot of simple resnet18 binary classifiers lately and I've started to notice that the probability distributions are often skewed one way or the other. This figure shows one such ...
1
vote
1answer
45 views

What is the definition of the hinge loss function?

I came across the hinge loss function for training a neural network model, but I did not know the analytical form for the same. I can write the mean squared error loss function (which is more often ...
0
votes
0answers
17 views

How to perform data augmentation on multiple input classification task?

I would like to add some more samples to my dataset which consists of two parts: 1. image and 2. numerical data. For each image in the dataset there is its corresponding numerical data as well. If it ...
0
votes
1answer
30 views

Semantic segmentation failing in small instance detection

I performed semantic segmentation with U-net. My dataset consists of grayscale images of defects. After training the dataset for I got an metric accuracy of only 0.3 - 0.4 IOU. Eventhough it is merely ...
4
votes
2answers
210 views

How should we interpret this figure that relates the perceptron criterion and the hinge loss?

I am currently studying the textbook Neural Networks and Deep Learning by Charu C. Aggarwal. Chapter 1.2.1.2 Relationship with Support Vector Machines says the following: The perceptron criterion is ...
2
votes
1answer
75 views

Why doesn't the set $\{ -2, +2 \}$ in $E(X) = (y − \text{sign}\{\overline{W} \cdot \overline{X} \}) \in \{ −2, +2 \}$ include $0$?

I am currently studying the textbook Neural Networks and Deep Learning by Charu C. Aggarwal. Chapter 1.2.1.2 Relationship with Support Vector Machines says the following: The perceptron criterion is ...
0
votes
0answers
17 views

Is it a fair evaluation if each model of k-fold cross validation is trained with different epochs and the mean AUC score gathered out of k folds?

Let's say I have a dataset for binary classification. And I am going to conduct 5-fold cross-validation and get AUC scores for each fold (mean AUC score too). However, if I set the training epoch to $...
0
votes
1answer
23 views

Should binary feature be in one or two columns in deep neural networks?

Let's assume I have a simple feedforward neural network whose input contains binary 0/1 features and output is also binary two classes. Is it better, worse or maybe totally indifferent, for every of ...
2
votes
1answer
30 views

Support Vector Machine Convert optimisation problem from argmax to argmin

I'm new to the AI Stackexchange and wasn't certain if this should go here or to Maths instead but thought the context with ML may be useful to understand my problem. I hope posting this question here ...
0
votes
0answers
52 views

How to use residual learning applied to fully connected networks?

Is there any reason why skip connections would not provide the same benefits to fully connected layers as it does for convolutional? I've read the ResNet paper and it says that the applications should ...
0
votes
1answer
27 views

Image Classification for watermarks with poor results

Just starting learning things about tensorflow and NN. As an exercise I decided to create a dataset of images, watermarked and not, in order to binary classify these. First of all, the dataset ( you ...
2
votes
1answer
182 views

Why am I getting a difference between training accuracy and accuracy calculated with Keras' predict_classes on a subset of the training data?

I'm trying to solve a binary classification problem with AlexNet. I split the original dataset into training and validation datasets using a 70/30 ratio. I have trained my neural network with a ...
2
votes
1answer
61 views

How to perform binary classification when one class is more predominant than the other?

Assuming we have big $m \times n$ input dataset, with $m \times 1$ output vector. It's a classification problem with only two possible values: either $1$ or $0$. Now, the problem is that almost all ...
1
vote
1answer
63 views

Are there any advantages of using rules-based approaches versus models for detecting spam?

Suppose that we have unlabeled data. That is, all we have are a collection of emails and want to determine whether any of them is spam or not. Let's say we have $1,000$ rules to determine whether a ...
1
vote
1answer
54 views

How many parameter would there be in a logistic regression model used to classify reviews into “good” or “bad”?

Suppose we want to classify a review as good ($1$) or bad ($0$). We have a training data set of $10,000$ reviews. Also, suppose we have a vocabulary of $100,000$ words $w_1, \dots, w_{100,000}$. So ...
4
votes
1answer
80 views

How can I use Generative Adversarial Networks to solve the imbalanced class problem?

Problem setting We have to do a binary classification of data given a training dataset $D$, where most items belong to class $A$ and some items belong to class $B$, so the classes are heavily ...
1
vote
1answer
107 views

Why is my fine-tuned YOLO model detecting other objects as a human?

I am new to deep learning and computer vision. I have a problem where I use the YOLO to detect objects. For my problem, I just want to recognize 1 human only. So, I changed the final YOLO's layer (...
3
votes
4answers
149 views

If we want to classify something as either a cat/dog or neither, do we need 2 or 3 classes?

Suppose one trains a CNN to determine if something was either a cat/dog or neither (2 classes), would it be a good idea to assign all cats and dogs to one class and everything else to another? Or ...