Most Popular
1500 questions
5
votes
1 answer
Are most things generally discovered because they work empirically and later justified mathematically, or vice-versa?
In the original GloVe paper, the authors discuss group theory when coming up with the equation (4). Is it possible that the authors came up with this model, figured out it was good, and then later found out various group theory justifications that…
Damien
- 169
- 1
5
votes
3 answers
How to make convnets aware what the image actually is, not what is depicted on it?
I've uploaded a picture to Wolfram's ImageIdentify of graffiti on the wall, but it recognized it as 'monocle'. Secondary guesses were 'primate', 'hominid', and 'person', so not even close to 'graffiti' or 'painting'.
Is it by design, or there are…
kenorb
- 10,483
- 3
- 44
- 94
5
votes
1 answer
Could AI kill the joy of competitive sports and games?
Lee Sedol, former world champion, and legendary Go player today announced his retirement with the quote "Even if I become the No. 1, there is an entity that cannot be defeated".
Is it possible that AIs could kill the joy of competitive games(Go,…
Vildemort
- 117
- 6
5
votes
2 answers
Can CNNs be applied to non-image data, given that the convolution and pooling operations are mainly applied to imagery?
When using CNNs for non-image (times series) data prediction, what are some constraints or things to look out for as compared to image data?
To be more precise, I notice there are different types of layers in a CNN model, as described below, which…
nilsinelabore
- 241
- 2
- 12
5
votes
1 answer
How does Wit.ai convert sentences into structured data?
The Wit.ai is a Siri-like voice interface which can can parse messages and predict the actions to perform.
Here is the demo site powered by Wit.ai.
How does it understand the spoken sentences and convert them into structured actionable data?…
kenorb
- 10,483
- 3
- 44
- 94
5
votes
1 answer
Should I train different models for detecting subsets of objects?
Suppose we have $1000$ products that we want to detect. For each of these products, we have $500$ training images/annotations. Thus we have $500,000$ training images/associated annotations. If we want to train a good object detection algorithm to…
NebulousReveal
- 113
- 5
5
votes
1 answer
Concrete example of latent variables and observables plugged into the Bayes' rule
In the context of the variational auto-encoder, can someone give me a concrete example of the application of the Bayes' rule
$$p_{\theta}(z|x)=\frac{p_{\theta}(x|z)p(z)}{p(x)}$$
for a given latent variable and observable?
I understand with VAE's…
user8714896
- 797
- 1
- 6
- 24
5
votes
1 answer
Does MMD-VAE solve the problem of blurred images of vanilla VAEs?
I understand that with vanilla VAEs, there are a few reasons justifying the production of blurred out images. The InfoVAE paper describes the case when the decoder is flexible enough to ignore the latent attributes and generate an averaged out image…
Ananda
- 148
- 9
5
votes
1 answer
How could decision tree learning algorithms cope with imbalanced classes?
Decision trees and random forests may or not be more suited to solve supervised learning problems with imbalanced labels (or classes) in datasets. For example, see the article Using Random Forest to Learn Imbalanced Data, this Stats SE question and…
jennifer ruurs
- 579
- 2
- 9
5
votes
1 answer
What is the "semantic level"?
I am reading the paper Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction (2018) by Yunzhe Tao et al.
In this paper, they use several times the expression "semantic levels". Some examples:
HRHN can adaptively select…
MikelBa
- 53
- 1
- 7
5
votes
1 answer
What is "conditioning" on a feature?
On page 98 of Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning the author writes;
Redacted phase space: Studying the distribution of inputs and the
network performance after conditioning on…
Clumsy cat
- 153
- 5
5
votes
2 answers
Is the Mask Needed for Masked Self-Attention During Inference with GPT-2
My understanding is that masked self-attention is necessary during training of GPT-2, as otherwise it would be able to directly see the correct next output at each iteration. My question is whether the attention mask is necessary, or even possible,…
D_s
- 51
- 3
5
votes
1 answer
Why would the application of boosting prevent underfitting?
"Why would the application of boosting prevent underfitting?"
I read in some paper that applying boosting would prevent you from underfitting. Why is that?
Source:
https://www.cs.cornell.edu/courses/cs4780/2015fa/web/lecturenotes/lecturenote13.html
jennifer ruurs
- 579
- 2
- 9
5
votes
1 answer
Context-based gap-fill face posture-mapper GAN
These images are handmade, not auto-generated like they will be in production. Apologies for inaccuracies in the graph overlay.
I am trying to build an AI like that displayed in the diagram: when given a training set of images with their…
Geza Kerecsenyi
- 51
- 6
5
votes
1 answer
Isn't deep fake detection bound to fail?
Deep fakes are a growing concern: the ability to credibly alter a video may have great (negative) impacts on our society. It is so much of a concern, that the biggest tech companies launched a specific challenge:…
Lucas Morin
- 252
- 2
- 13