Most Popular
1500 questions
7
votes
1 answer
Why does reinforcement learning using a non-linear function approximator diverge when using strongly correlated data as input?
While reading the DQN paper, I found that randomly selecting and learning samples reduced divergence in RL using a non-linear function approximator (e.g a neural network).
So, why does Reinforcement Learning using a non-linear function approximator…
강문주
- 71
- 2
7
votes
3 answers
When training a CNN, what are the hyperparameters to tune first?
I am training a convolutional neural network for object detection. Apart from the learning rate, what are the other hyperparameters that I should tune? And in what order of importance? Besides, I read that doing a grid search for hyperparameters is…
S.E.K.
- 71
- 4
7
votes
1 answer
How good is AI at generating new, unseen [visual] examples?
By new, unseen examples; I mean like the animals in No Man's Sky.
A couple of images of the animals are:
So, upon playing this game, I was curious about how good is AI at generating visual characters or examples?
Dawny33
- 1,371
- 13
- 29
7
votes
1 answer
Is Sanskrit still relevant for NLP/AI?
I came across a news article from 2018 where the president of India was saying that Sanskrit is the best language for ML/AI. I have no idea regarding his qualification on either AI or Sanskrit to say this but this idea has been floated earlier in…
Borun Chowdhury
- 190
- 1
- 6
7
votes
2 answers
Can training a model on a dataset composed by real images and drawings hurt the training process of a real-world application model?
I'm training a multi-label classifier that's supposed to be tested on underwater images. I'm wondering if feeding the model drawings of a certain class plus real images can affect the results badly. Was there a study on this? Or are there any past…
user
- 101
- 5
7
votes
1 answer
Are PAC learning and VC dimension relevant to machine learning in practice?
Are PAC learning and VC dimension relevant to machine learning in practice? If yes, what is their practical value?
To my understanding, there are two hits against these theories. The first is that the results all are conditioned on knowing the…
FourierFlux
- 843
- 1
- 7
- 16
7
votes
1 answer
How to use BERT as a multi-purpose conversational AI?
I'm looking to make an NLP model that can achieve a dual purpose. One purpose is that it can hold interesting conversations (conversational AI), and another being that it can do intent classification and even accomplish the classified task.
To…
junfanbl
- 323
- 1
- 7
7
votes
2 answers
Why is dropout favoured compared to reducing the number of units in hidden layers?
Why is dropout favored compared to reducing the number of units in hidden layers for the convolutional networks?
If a large set of units leads to overfitting and dropping out "averages" the response units, why not just suppress units?
I have read…
pascal sautot
- 241
- 1
- 8
7
votes
3 answers
Does each filter in each convolution layer create a new image?
Say I have a CNN with this structure:
input = 1 image (say, 30x30 RGB pixels)
first convolution layer = 10 5x5 convolution filters
second convolution layer = 5 3x3 convolution filters
one dense layer with 1 output
So a graph of the network will…
RocketNuts
- 205
- 2
- 6
7
votes
1 answer
Does adding a constant to all rewards change the set of optimal policies in episodic tasks?
I'm taking a Coursera course on Reinforcement learning. There was a question there that wasn't addressed in the learning material: Does adding a constant to all rewards change the set of optimal policies in episodic tasks?
The answer is Yes - Adding…
Maverick Meerkat
- 412
- 3
- 11
7
votes
1 answer
How many training data is required for GAN?
I'm beginning to study and implement GAN to generate more datasets. I'll just try to experiment with state-of-the-art GAN models as described here https://paperswithcode.com/sota/image-generation-on-cifar-10.
The problem is I don't have a big…
gameon67
- 215
- 3
- 12
7
votes
3 answers
Is there an open-source implementation for graph convolution networks for weighted graphs?
Currently, I'm using a Python library, StellarGraph, to implement GCN. And I now have a situation where I have graphs with weighted edges. Unfortunately, StellarGraph doesn't support those graphs
I'm looking for an open-source implementation for…
port trum
- 85
- 4
7
votes
1 answer
What is predicate argument recognition?
There is a study about The Necessity of Parsing for Predicate Argument Recognition, however I couldn't find much information about 'Predicate Argument Recognition' which could explain it.
What is it exactly and how does it work, briefly?
kenorb
- 10,483
- 3
- 44
- 94
7
votes
1 answer
How could an AI detect whether an enemy in a game can be blocked off/trapped?
Imagine a game played on a 10x10 grid system where a player can move up down left or right and imagine there are two players on this grid: An enemy and you. In this game, there are walls on the grid which you can't go through. The objective of this…
Ahmed
- 71
- 1
7
votes
1 answer
What would the Valkyrie AI robot do on Mars?
I was reading that the Valkyrie robot was originally designed to 'carry out search and rescue missions'.
However, there were some talks to send it to Mars to assist astronauts.
What kind of specific trainings or tasks are planned for 'him' to be…
kenorb
- 10,483
- 3
- 44
- 94