Questions tagged [alexnet]

For questions related to the convolutional neural network denoted as AlexNet, designed by Alex Krizhevsky (hence the name AlexNet), and published with Ilya Sutskever and Krizhevsky's doctoral advisor Geoffrey Hinton.

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

Can the (sparse) categorical cross-entropy be greater than one?

I am using AlexNet CNN to classify my dataset which contains 10 classes and 1000 data for each class, with 60-30-10, splits for train, validation, and test. I used different batch sizes, learning ...
user avatar
  • 110
1 vote
0 answers
53 views

What is the reason for different learned features in upper and lower half in AlexNet?

I was reading AlexNet paper and the authors quoted the kernels on one GPU were "largely color agnostic," whereas the kernels on the other GPU were largely "color-specific." The upper GPU takes ...
user avatar
  • 11
2 votes
1 answer
62 views

What could cause a big fluctuation of the loss in the last epochs of training an AlexNet?

I am training an AlexNet neural network, with about 12000 images which 80% is for training, 10% is for validation and another 10% is for testing. I have a problem in my plots. There is a big ...
user avatar
  • 110
2 votes
1 answer
369 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 ...
user avatar
  • 31
2 votes
1 answer
65 views

How is a neural network where the majority of inputs are 0 trained?

Consider AlexNet, which has 1000 output nodes, each of which classifies an image: The problem I have been having with training a neural network of similar proportions, is that it does what any ...
user avatar
  • 1,324
3 votes
2 answers
278 views

Why do we need 10 bits to represent the 1000 classes in AlexNet?

I'm reading the AlexNet paper. In section 4, where the authors explain how they prevent overfitting, they mention Although the 1000 classes of ILSVRC make each training example impose 10 bits of ...
user avatar
  • 33
6 votes
1 answer
484 views

How should the racing agent take into account the velocity of the vehicle, given the images with a speedometer?

I'm developing a game AI, which tries to master racing simulations. I already trained a CNN (AlexNet) on in-game footage of me playing the game and the pressed keys as the target. As the CNN is only ...
user avatar
  • 103
3 votes
0 answers
161 views

How can I calculate the number of matrix additions, multiplications and divisions in AlexNet?

I'm a first-year student in machine learning and I really recently started to immerse myself. I need to calculate number of: matrix additions matrix multiplications matrix divisions which are ...
user avatar