Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [dimensionality]

9 questions
3
votes
2 answers

Problem extracting features from convolutional layer where the dimensions are big for feature maps

I have trained a convolutional neural network on images to detect emotions. Now I need to use the same network to extract features from the images and use them to train an LSTM. The problem is: the dimensions of the top layers are: [None, 4, 4, 512]…
I. A
  • 131
  • 3
1
vote
1 answer

Can I do state space quantization using a KMeans-like algorithm instead of range buckets?

Are there any reference papers where it is used a KMeans-like algorithm in state space quantization in Reinforcement Learning instead of range buckets?
ddaedalus
  • 919
  • 1
  • 6
  • 21
1
vote
0 answers

How to handle a high dimensional video (large number of frames per video) data for training a video classification network

I have a video dataset as follows. Dataset size: 1k videos Frames per video: 4k (average) and 8k (maximum) Labels: Each video has one label. So the size of my input will be (N, 8000, 64, 64, 3) 64 is height and width of video. I use keras. I am…
manv
  • 11
  • 2
0
votes
0 answers

How do transformers handle multidimensional input?

Transformers work with lists of vectors, i.e. sentence of length SEQ_LEN, with each word having size EMBEDDING_DIM. Now, since the model still makes use of Dense layers internally, i.e. as in https://www.tensorflow.org/text/tutorials/transformer,…
Daniel von Eschwege
  • 101
  • 1
0
votes
1 answer

How many directions of gradients exist for a function in higher dimensional space?

Gradients are used in optimization algorithms. Based on the values of gradients, we generally update the weights of a neural network. It is known that gradients have a direction and the direction opposite to the gradient should be considered for…
hanugm
  • 3,571
  • 3
  • 18
  • 50
0
votes
2 answers

How to visually or intuitively understand single element multi-dimensional tensors?

Consider the following code in PyTorch >>>torch.tensor([8]).shape torch.Size([1]) >>>torch.tensor([[8]]).shape torch.Size([1, 1]) >>>torch.tensor([[[8]]]).shape torch.Size([1, 1, 1]) We can notice that we want to store only a single element $8$…
hanugm
  • 3,571
  • 3
  • 18
  • 50
0
votes
1 answer

How does t-SNE preserves embedding orders?

According to the triplet loss Wikipedia page: t-SNE (t-distributed Stochastic Neighbor Embedding) preserves embedding orders via probability distributions, whereas triplet loss works directly on embedded distances. I don't understand how does…
Revolucion for Monica
  • 210
  • 1
  • 7
0
votes
0 answers

Huge dimensionality of input and output — any recommendations?

At work there is an idea of solving a problem with machine learning. I was assigned the task to have a look at this, since I'm quite good at both mathematics and programming. But I'm new to machine learning. In the problem a box would be discretized…
md2perpe
  • 1
  • 2
0
votes
0 answers

Finding whether an input column is missing

I am working on a problem similar to this one:(supervised, artificial…
munichmath
  • 1