Most Popular
1500 questions
5
votes
2 answers
Do genetic algorithms also evolve?
After witnessing the rise of deep learning as automatic feature/pattern recognition over classic machine learning techniques, I had an insight that the more you automate at each level, the better the results, and I, therefore, turned my focus to…
Kayonga Arnauld
- 59
- 1
5
votes
3 answers
Why diffusion model always use U-Net?
I want to know why diffusion models always use U-Net.
In my opinion, they use U-Net because you can see features of different resolutions and skip connection is good to add detail of images. But I am not sure if it is the main reason why they use…
Penguin.jpg
- 51
- 1
- 1
- 5
5
votes
3 answers
How can I determine if an input sentence is consistent with a certain subject?
How can I determine if an input sentence is consistent with a certain subject?
For example, suppose I am given the following dataset.
| Subject | User input | Output |
|---------------|----------------------|--------|
| Dog ownership…
bleand
- 161
- 2
5
votes
1 answer
Is large language model and foundation model the same thing?
I read a lot about foundation model and large language model.
However, I dont find a clear definition what exactly is a foundation model. Is large language model and foundation model the same thing?
Exploring
- 371
- 7
- 18
5
votes
2 answers
How to generate new data given a trained VAE - sample from the learned latent space or from multivariate Gaussian?
To generate synthetic dataset using a trained VAE, there is confusion between two approaches:
Use learned latent space: z = mu + (eps * log_var) to generate (theoretically, infinite amounts of) data. Here, we are learning mu and log_var vectors…
Arun
- 255
- 2
- 8
5
votes
6 answers
Why is exploitation necessary during training?
I have read many blog articles making all kinds of broad analogies to explain the exploration/exploitation trade-off. However, I still can't fully grasp it. On an extremely abstract level, I understand why you would want to "try new things to gain…
Vladimir Belik
- 362
- 3
- 15
5
votes
1 answer
Why are only neural networks (and not SVMs, for example) used for reinforcement learning?
I know that neural networks are the "universal function approximator", but they also have a huge number of trainable parameters and are extremely prone to overfitting.
So my question is: Why aren't SVMs or Random Forests used as the mediators in…
Vladimir Belik
- 362
- 3
- 15
5
votes
1 answer
Why can't computers be random?
I talked with a graduate computer science who said one challenge of making artificial human-like is making random decisions, and that computers can't be random, that they always need a "seed." But, if a computer's outcomes are determined by the…
RayOfHope
- 151
- 1
5
votes
1 answer
Does the term "data augmentation" imply increasing the training dataset?
I have a manuscript that has been reviewed and one of the reviewers commented on my use of the term " data augmentation", saying that it might not be the appropriate term in my case (explained below).
I collected a large dataset of short audio files…
Benjamin Cretois
- 181
- 5
5
votes
2 answers
Is there any way to draw a neural network's connections in a nice way?
I've been working with neural networks and artificial intelligence for a while. What I'm trying to do right now is, from a genotype I have (a sum of sensors, neurons and actuators) draw how the neural network is (with recurrent/recursive connections…
MiGu3X
- 53
- 3
5
votes
1 answer
What is the difference between simple reflex and model-based agents?
What is the difference between simple reflex and model-based agents?
What is the role of the internal state in the case of model-based agents?
Pierre P.
- 161
- 1
- 2
5
votes
1 answer
How can one find / collect data for, and come up with ideas for, using Deep Learning / AI to improve one's everyday life?
I can see a lot of tutorials and examples about using TensorFlow and other free, open-source AI/ML/DL frameworks on enterprise level where enough data was collected for such AI solutions.
How can one can collect enough data in normal everyday life…
user6933
5
votes
2 answers
Feasibility of an AI assistant to expedite game development?
Basically, an AI that can create, rig, and texture 3d models and game environments (by extrapolating from collections of reference models, according to user input), and that can set up physics and mechanics (assuming that the AI has access to a 3d…
Sebastian Hahn
- 119
- 2
5
votes
1 answer
Precise localization and characterization of rudimentary shapes with neural networks
I understand that there are flavors of (convolutional) neural networks that are useful for object localization and detection tasks of reasonable difficulty. In all of the examples I have seen so far, localization is formulated as finding the corners…
mbaytas
- 151
- 3
5
votes
1 answer
What is the difference between an on-policy distribution and state visitation frequency?
On-policy distribution is defined as follows in Sutton and Barto:
On the other hand, state visitation frequency is defined as follows in Trust Region Policy Optimization:
$$\rho_{\pi}(s) = \sum_{t=0}^{T} \gamma^t P(s_t=s|\pi)$$
Question: What is…
user529295
- 379
- 2
- 12