Most Popular
1500 questions
6
votes
2 answers
Current limitations to artificial consciousness
With some knowledge of machine learning and deep learning, it seems very unlikely for AI to develop into the consciousness that we imagine.
To me, consciousness requires a new framework that is very different from what we have today, as current…
sma
- 823
- 4
- 8
6
votes
1 answer
How feasible is it to automate Theorem Proving via Reinforcement Learning?
Theorem proving is basically a turn-based game with perfect information: you start from a given gamestate (a proposition) and make moves that lead to other valid gamestates. A piece of software can check whether the moves you make are legal and…
Blue Nebula
- 193
- 4
6
votes
1 answer
How are LSTM's trained for text generation?
I've seen some articles about text generation using LSTMs (or GRUs) for text generation.
Basically it seems you train them by folding them out, and putting a letter in each input. But say you trained it with text which includes the string:
"The dog…
zooby
- 2,260
- 1
- 14
- 22
6
votes
2 answers
Can Convolutional Neural Networks be applied in domains other than image recognition?
I'm new in this argument, my question is:
Can convolution be applied in other contexts different from image recognition?
Is there a good source to learn from?
Francesco Rizzi
- 169
- 1
- 2
6
votes
2 answers
What are examples of resources that describe the basics of Spiking Neural Networks in detail?
I'm very interested in writing a Spiking Neural Network engine (SNN) from scratch, but I can't find the basic information I need to get started.
For example, I've seen pictures of the individual signals that combine to form a neuron pulse in several…
Erin Loy
- 81
- 4
6
votes
1 answer
Is there a way of converting a neural network to another one that represents the same function?
I have read the paper Neural Turing Machines and the paper On the Computational Power of Neural Nets about the computational power of neural networks. However, it isn't still clear to me one thing.
Is there a way of converting a neural network to…
ViniciusArruda
- 179
- 4
6
votes
2 answers
DQN arXiv 10-year anniversary: What are the outstanding problems being actively researched in deep Q-learning since 2019?
Background
As of today (12-19-2023), the arXiv submission of the original deep Q-learning approach to achieve superhuman performance on ATARI games has turned a decade old. The original approach, sometimes referred to as vanilla DQN (2013), was the…
DeepQZero
- 1,733
- 1
- 10
- 36
6
votes
2 answers
What are the differences between seq2seq and encoder-decoder architectures?
I've read many tutorials online that use both words interchangeably. When I search and find that they are the same, why not just use one word since they have the same definition?
user78615
6
votes
2 answers
Does increasing the number of Q functions in Q-Learning scale?
Q-Learning (Watkins, 1989) uses a single function to estimate the value of actions and to choose the next action. Double Q-Learning (Hasselt, 2010) extends this and uses two functions which are updated using different subsets of experience. The…
foreverska
- 2,347
- 4
- 21
6
votes
2 answers
Why is the larger value, as opposed to the smaller one, chosen, in the hill climbing algorithm?
In the hill climbing algorithm, the greater value, compared to the current value, is selected, but I cannot understand why it takes the larger value instead of the smaller one. Why is that?
I greatly appreciate the inclusion of figures in your…
Khan
- 61
- 1
6
votes
5 answers
Why does Stable Diffusion use VAE instead of AE?
I am currently studying the Latent Diffusion Models (LDMs) and am interested in training my own model using a unique dataset. In my research, I came across Stable Diffusion (SD). Some sources suggest that SD employs VAEs for the encoding and…
P0TAT0
- 61
- 1
- 2
6
votes
1 answer
Why policy gradient theorem has two different forms?
I have been studying policy gradients recently but found different expositions from different sources, which greatly confused me. From the book "Reinforcement Learning: an Introduction (Sutton & Barto Chapter 13)", we get the following policy…
Yuxiang Wei
- 61
- 2
6
votes
1 answer
How does AI 'see' the images it generates- from what perspective?
I've been using AI image generation for a while now, and I've noticed how profoundly AI doesn't seem to see the image as a whole, sometimes generating an image with parts of fingers floating near objects supposed to be being held, VERY warped…
ben svenssohn
- 344
- 2
- 10
6
votes
3 answers
Why use a "square root" in the scaled dot product
In attention settings, typically when the both Query Q and Key K are of the same dimension d we can compute their attention score in the following manner:
$$\frac{Q^T K}{\sqrt{d}}$$
The justification being that the dot product tends to blow up in…
Sheed
- 163
- 1
- 5
6
votes
1 answer
Which situation will helpful using encoder or decoder or both in transformer model?
I have some questions about using (encoder / decoder / encoder-decoder) transformer models, included (language) transformer or Vision transformer.
The overall form of a transformer consists of an encoder and a decoder. Depending on the model, you…
Yang
- 79
- 1
- 6