Community Digest

Top new questions this week:

Are humans superior to machines in chess?

A friend of mine, who is an International Master at chess, told me that humans were superior to machines provided you didn't impose the time constraints that exist in competitive chess (40 moves in 2 ...

comparison chess  
asked by petitrien 11 votes
answered by serali 21 votes

What does AI software look like, and how is it different from other software?

What does AI software look like? What is the major difference between AI software and other software?

comparison implementation  
asked by Anatoly Wein 6 votes
answered by Oliver Mason 13 votes

What do the subscripts mean in $N_{t,n,\sigma,L}$?

A neural network can apparently be denoted as $N_{t,n,\sigma,L}$. What do these subscripts $t, n, \sigma$ and $L$ mean? Could you link me to a paper, article or webpage with an explanation for this? ...

neural-networks math definitions notation  
asked by J. Doe 4 votes
answered by serali 3 votes

How to create an AI to solve a word search?

This at first sounds ridiculous. Of course there is an easy way to write a program to solve a wordsearch. But what I would like to do is write a program that solves a word-search like a human. That ...

deep-learning search architecture reasoning  
asked by zooby 4 votes
answered by John Doucette 3 votes

If an heuristic is not admissible, can it be consistent?

I am solving a problem in which, according to the given values, the heuristic is not admissible. According to my calculation from other similar problems, it should be consistent, as well as keeping in ...

search proofs heuristics admissible-heuristic consistent-heuristic  
asked by Awa 4 votes
answered by John Doucette 1 vote

Why does the binary cross-entropy work better than categorical cross-entropy in a multi-class single label problem?

I was just doing a simple NN example with the fashion MNIST dataset, where I was getting 97% accuracy, when I noticed that I was using Binary cross-entropy instead of categorical cross-entropy by ...

neural-networks classification loss-functions cross-entropy  
asked by joão correia 4 votes
answered by Michael Hearn 1 vote

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 ...

generative-adversarial-networks adversarial-ml deepfakes  
asked by lcrmorin 3 votes
answered by Michael Hearn 0 votes

Greatest hits from previous weeks:

Was the corruption of Microsoft's "Tay" chatbot an example of catastrophic forgetting?

Tay was a chatbot, who learned from Twitter users. Microsoft's AI fam from the internet that's got zero chill. The more you talk the smarter Tay gets. — Twitter tagline. Microsoft trained the AI ...

chat-bots history catastrophic-forgetting  
asked by wizzwizz4 5 votes
answered by mico 6 votes

How could self-driving cars make ethical decisions about who to kill?

Obviously, self-driving cars aren't perfect, so imagine that the Google car (as an example) got into a difficult situation. Here are a few examples of unfortunate situations caused by a set of ...

philosophy ethics autonomous-vehicles decision-theory  
asked by kenorb 76 votes
answered by Doxosophoi 56 votes

Are the dialogs at Sophia's (the robot) appearings scripted?

I talk about the robot from: Hanson Robotics, which was granted the right to citizenship from Saudi Arabia. I have found the following articles: Your new friend is a humanoid robot source: ...

natural-language-processing applications robots  
asked by tgogos 8 votes
answered by Rebecca Merrett 11 votes

Permutation invariant neural networks

Given a neural network $f$ that takes as input $n$ data points: $x_1, \dots, x_n$. We say $f$ is permutation invariant if $$f(x_1 ... x_n) = f(pi(x_1 ... x_n))$$ for any permutation $pi$. ...

neural-networks machine-learning reference-request  
asked by Josef Ondrej 14 votes
answered by BlueMoon93 2 votes

What sort of mathematical problems are there in AI that people are working on?

I recently got a 18-month postdoc position in a math department. It's a position with relative light teaching duty and a lot of freedom about what type of research that I want to do. Previously I was ...

research math  
asked by ablmf 8 votes
answered by nbro 9 votes

What is a Dynamic Computational Graph?

Frameworks like PyTorch and TensorFlow through TensorFlow Fold support Dynamic Computational Graphs and are receiving attention from data scientists. However, there seems to be a lack of resource to ...

asked by Blaszard 19 votes
answered by Douglas Daseeco 8 votes

What is a Recurrent Neural Network?

Surprisingly this wasn't asked before - at least I didn't find anything besides some vaguely related questions. So, what is a recurrent neural network, and what are their advantages over regular NNs? ...

asked by olinarr 12 votes
answered by naive 6 votes

Can you answer these questions?

Are embeddings in multi-lingual language models comparable across languages?

Facebook has just pushed out a bigger version of their multi-lingual language model XLM, called XLM-R. My question is: do these kind of multi-lingual models imply, or even ensure, that their ...

deep-learning natural-language-processing transformer language-model  
asked by Bram Vanroy 2 votes

AlphaGo Zero: Does the policy head give a probability for every possible move?

If I understood correctly, the AlphaGo Zero network returns two values: a vector of logit probabilities p and a value v. My question is: in this vector that it is outputted, do we have a probability ...

deep-learning policy deepmind alphago-zero  
asked by ihavenoidea 1 vote

Quantization techniques and new GPU architectures

Quantization means using low resolution formats for some variables some of the time: binary (e.g. BinaryConnect), ternary, etc. The Turing architecture recently introduced by Nvidia is much faster ...

hardware performance  
asked by Mathieu Bouville 1 vote
You're receiving this message because you subscribed to the Artificial Intelligence community digest.
Unsubscribe from this community digest       Edit email settings       Leave feedback       Privacy
Stack Overflow

Stack Overflow, 110 William Street, 28th floor, New York, NY 10038